WO1998049630A1 - Bibliographic music data base with normalized musical themes - Google Patents

Bibliographic music data base with normalized musical themes Download PDF

Info

Publication number
WO1998049630A1
WO1998049630A1 PCT/IB1998/000362 IB9800362W WO9849630A1 WO 1998049630 A1 WO1998049630 A1 WO 1998049630A1 IB 9800362 W IB9800362 W IB 9800362W WO 9849630 A1 WO9849630 A1 WO 9849630A1
Authority
WO
WIPO (PCT)
Prior art keywords
musical
input
data
memory means
themes
Prior art date
Application number
PCT/IB1998/000362
Other languages
French (fr)
Inventor
Mark B. Hoffberg
Original Assignee
Koninklijke Philips Electronics N.V.
Philips Ab
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Koninklijke Philips Electronics N.V., Philips Ab filed Critical Koninklijke Philips Electronics N.V.
Priority to JP10529340A priority Critical patent/JP2000513846A/en
Priority to EP98905577A priority patent/EP0919033A1/en
Publication of WO1998049630A1 publication Critical patent/WO1998049630A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/683Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10HELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H1/00Details of electrophonic musical instruments
    • G10H1/0033Recording/reproducing or transmission of music for electrophonic musical instruments
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10HELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2240/00Data organisation or data communication aspects, specifically adapted for electrophonic musical tools or instruments
    • G10H2240/121Musical libraries, i.e. musical databases indexed by musical parameters, wavetables, indexing schemes using musical parameters, musical rule bases or knowledge bases, e.g. for automatic composing methods
    • G10H2240/131Library retrieval, i.e. searching a database or selecting a specific musical piece, segment, pattern, rule or parameter set
    • G10H2240/135Library retrieval index, i.e. using an indexing scheme to efficiently retrieve a music piece
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10HELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2240/00Data organisation or data communication aspects, specifically adapted for electrophonic musical tools or instruments
    • G10H2240/121Musical libraries, i.e. musical databases indexed by musical parameters, wavetables, indexing schemes using musical parameters, musical rule bases or knowledge bases, e.g. for automatic composing methods
    • G10H2240/131Library retrieval, i.e. searching a database or selecting a specific musical piece, segment, pattern, rule or parameter set
    • G10H2240/141Library retrieval matching, i.e. any of the steps of matching an inputted segment or phrase with musical database contents, e.g. query by humming, singing or playing; the steps may include, e.g. musical analysis of the input, musical feature extraction, query formulation, or details of the retrieval process
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99934Query formulation, input preparation, or translation
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99941Database schema or data structure
    • Y10S707/99943Generating database or data structure, e.g. via user interface
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99941Database schema or data structure
    • Y10S707/99944Object-oriented database structure
    • Y10S707/99945Object-oriented database structure processing

Definitions

  • the invention relates to an information processing system for interacting with a music data base, to a method of operating a music data base, and to a memory module with a music data base.
  • U.S. patent 5,402,339 discloses a system for creating a music data base of musical information that can be processed by a computer and for retrieving a string of note data items from the music data base.
  • the known system comprises an input converter that converts music data supplied by an electronic device into note data items.
  • the electronic device that supplies the music data is a computer, an electrical musical instrument, a music sampler or a reproducing device.
  • Each note data item represents a time period and a scale degree of a sound identified by a single musical note. Both period and scale degree have digital values.
  • the system further comprises a position information unit for producing position data items that specify the relative position in a sequence of the note data items in the piece of music represented by the music data.
  • the note data items and position data items are stored together with an index table that links the data note items, the position data items, and the number of times a specific data note item occurs in the piece of music thus stored.
  • the known system comprises means to retrieve a particular piece of stored music. Music information is supplied to the system as a string of note data items and associated position data items. A particular seek algorithm is employed to find a match between the string and a particular piece of music. The algorithm uses a histogram for each theme specifying the number of times a particular note occurs in this theme. The query for a matching theme is then facilitated by focusing on the rarest notes as the characterizing elements of the theme.
  • the known system reproduces a piece of music stored upon finding a match between the stored piece and an entered string of musical notes.
  • the known system processes note data items in a range that extend from the lowest to the highest musical notes audible (including flat and sharp) in order to cover all possible musical themes. That is, the note data items should be encoded as digital words wide enough to cover the range. As a consequence, memory capacity must be large enough to store these wide words. Further, the absolute magnitude of the pitch, or scale degree, of every note entered in the query must be accurate enough in order to match the one stored.
  • the retrieval algorithm used is rather complicated in that it requires the storage and creation of note data items, position data items, index tables and histograms to control access to any sequence of note data items stored. The algorithm requires a histogram of each piece of music to keep track of how many times a given note occurs in a given sequence of notes stored, this number of times being a retrieval key.
  • the invention provides an information processing system that comprises first memory means storing a data base having respective bibliographic information items corresponding with respective ones of multiple musical themes.
  • the system further comprises second memory means for storing respective reference data representing respective reference sequences of reference musical components of respective ones of the musical themes.
  • the system has an input for receiving an input data representative of an input sequence of input musical components, and retrieval means coupled to the input and to the first and second memory means for providing a particular bibliographic information item upon finding a match between a particular one of multiple reference data and the input data.
  • each respective one of the input musical components comprises a respective input musical note
  • each respective one of the reference musical components comprises a respective reference musical note
  • the system of the invention associates an entered sequence of notes with one or more bibliographic information items upon finding a match with a stored sequence of notes.
  • the bibliographic information item may include, for example, the name and biography of the composer, the name of the text writer, the lyrics, the title of the album, context information about the theme, related works.
  • a MIDI file of the melody from which the reference sequence is a sample, or a recording of the actual performance, a video clip, etc, could be provided as well.
  • a musical theme as represented by a single sequence of notes is, by definition, homophonic.
  • a musical theme within this context is a line of music that people find easy to remember, e.g., DA-DA-DA- DUMMM (Beethoven's Fifth Symphony), and DA-DAAA- da -da- daa - da -da- daa - da -da- a -DA-DAA ('Jumping Jack Flash', Rolling
  • a musical theme easily remembered is the first couple of bars of a song or of a chorus (national anthems) or another dominant portion, or the theme is associated with a catching line of the lyrics (e.g., Andrew Lloyd Webber's rock opera's) or with an impressive riff (e.g., Keith Richards on guitar).
  • the invention is especially of interest to record shops. Customers can retrieve in this manner the information about a musical theme, of which they have only remembered a couple of bars. Heretofore, clients had to rely on the expertise of the staff of the shop.
  • the invention is also of interest to organizations like ASCAP (American Society of Composers, Authors and Publishers) whose function it is to protect the rights of composers, songwriters, lyricists and music publishers by licensing and negotiating royalties for the public performances of the copyrighted works of their members.
  • ASCAP American Society of Composers, Authors and Publishers
  • a preferred embodiment of the invention is characterized in that the multiple musical themes as represented by the reference sequences are uniformly normalized with regard to one and the same predetermined scale degree.
  • This aspect of the invention is based on the following insight.
  • One and the same musical theme can be represented by an infinite number of note sequences.
  • the ratio between the frequencies of the scale degrees of successive notes stays invariant in each such representation, but the frequency of a particular note can have any value. That is, the recognizability of a theme is substantially invariant under a gauge transformation that shifts the frequency of all notes of the sequence by the same fixed amount.
  • the absolute pitch of any other note in the same theme is fixed under this constraint.
  • the themes are normalized with regard to the one and the same scale degree. For example, the first note of each reference sequence as stored is always of the same pitch, e.g.
  • the first note of each reference sequence as stored is always such that if it were preceded by another note of the same theme, this preceding virtual note would have always the same pitch, uniform for all themes. This is a unique identification of the succeeding note, i.e., the first note in the reference sequence as stored, since the musical themes are known in advance.
  • the scale degrees of the homophonic representation of the majority of the musical themes do not span more than two or three octaves. In the invention all themes are normalized to these two or three octaves.
  • the memory for the reference sequences stores and routes much shorter words than in the prior art cited above.
  • the input sequence is normalized with regard to the same scale degree as well in order to carry out the query.
  • the input data represents an input sequence of input musical notes.
  • the input data is provided through some appropriate interface. For example, a simple keyboard is used. Alternatively, the user hums the part of the tune into a microphone.
  • the user can employ a tuning fork of the appropriate pitch, or the system has means to generate a sound of this pitch, that helps the user to catch at least the first few notes. If necessary, filtering and quantization techniques are applied to extract from the tune, hummed or entered in another way, the appropriate notes for further processing.
  • the input sequence of input notes and the reference sequences of reference notes are represented as series of ratios between pairs of successive scale degrees. In this manner, the absolute scale degree of the first note, used as a direction in the previous embodiment, is not required anymore.
  • scale degrees or ratios of pairs of successive scale degrees are mapped onto an ordered set, e.g. , onto that of the integers.
  • the mapping per scale degree or ratio onto an element of an ordered set allows for lexicographic ordering of the reference data and the usage of a simple search strategy, e.g., an N-ary search strategy similar to that for a dictionary.
  • the input data is a sequence of musical notes, entered through a keyboard or hummed into a microphone.
  • a further advantage of the lexicographic ordering is then that the query continues while the individual notes are being entered one after the other. Each next one of the notes successively decreases the number of candidate reference sequences, owing to the lexicographic ordering.
  • the input data comprises rhythm information about a musical theme.
  • the rhythm information comprises the time signature (meter) and the accentuations of the theme.
  • the time signature determines the number of beats to the measure.
  • the accentuation determines which beat gets an accent and which one does not.
  • the sign 6 8 in a musical score is the time signature indicating that the meter is 6 beats to the measure and that an eighth note gets one beat.
  • Flamenco music has a variety of different styles, each determined by its own compas (rhythmic accentuation pattern). Typical examples of flamenco music are Alegrias, Bulerias, Siguiriyas and Soleares that all have 12 beats to the measure. In the Alegrias, Bulerias and Soleares, the third, sixth, eighth, tenth and twelfth beats are accentuated. The first, third, fifth, eighth and eleventh beats are emphasized in the Siguiriyas style.
  • rhythmic accentuation patterns are used as input data in order to retrieve bibliographic information.
  • the user enters the rhythmic accentuation pattern into the system as a substantially monotonic sequence of accentuated and unaccentuated sounds through, e.g. , humming into a microphone or manipulating a particular key of a keyboard, or drumming the rhythm with his or her fingers.
  • the input data then is represented by, e.g. , a sequence of beats or peaks of varying height in the time domain.
  • the relative distances between successive peaks represent the temporal aspects of the pattern and the relative heights represent the accentuations in the pattern.
  • the sequence of beats and rests in between is represented by a digital word.
  • the words can again be stored lexicographically to enable a fast and orderly retrieval.
  • Fig. 1 is a diagram of an information processing system according the invention
  • Fig. 2 is a diagram illustrating the lexicographically organized data base.
  • Fig. 1 is a block diagram of a system 100 according to the invention.
  • System 100 comprises a first memory 102 storing a data base.
  • the data base has respective bibliographic information items corresponding with respective ones of multiple musical themes.
  • System 100 has a second memory 104 for storing respective reference data representing respective reference sequences of musical notes of respective ones of the musical themes.
  • System 100 has an input 106 for receiving an input data representative of an input sequence of input musical notes.
  • System 100 further has a retrieval engine 108 coupled to input 106 and to first and second memories 102 and 104.
  • Retrieval engine 108 provides a particular bibliographic information item at an output 112 upon a match between a particular one of multiple reference data and the input data.
  • each reference data in memory 104 has a pointer to an associated bibliographic information item stored in memory 102.
  • the corresponding pointer identifies the associated bibliographic information item in memory 102.
  • Memories 102 and 104 in this example are combined in a memory module 110 such as an optical memory (e.g., a CD, or a DVD) or a solid-state memory.
  • Module 110 is physically detachable from retrieval engine 108.
  • system 100 can be provided with different modules for different categories of music (e.g., symphonies, jazz, rock, folk) or for different kinds of bibliographic information (e.g., lyrics, biographies of composers).
  • memory means 102 and 104 are stored at a server.
  • the browser software is provided by retrieval means 108.
  • the user is enabled to transmit his input data to the server and receives the appropriate category of bibliographic information if there is match.
  • the multiple musical themes as stored in memory 104 and as represented by the reference sequences are uniformly normalized with regard to one and the same predetermined scale degree.
  • the first note of each reference sequence as stored is always of the same pitch, e.g., 220 cps.
  • the first note of each reference sequence as stored in memory 104 is always such that, if it were preceded by another note of the same theme, this preceding virtual note would have always the same pitch uniform for all themes. This is a unique identification of the succeeding note, i.e., the first note in the reference sequence, since the musical themes are known in advance.
  • the input sequence is normalized as well with regard to the same scale degree in order to carry out the query.
  • Each respective one of the reference data comprises a respective ordered set of elements.
  • a position of a specific element and a value of the specific element in the respective ordered set are determined by a position and scale degree of a specific one of the musical notes in the respective reference sequence.
  • each note, middle, or with an associated sharp, or with an associated flat is represented in a data format that identifies its linear position in an octave and that identifies the linear position of the octave within the range of octaves covered by the musical themes in the data base.
  • each note is assigned one of the integers in the range from 1 to K.
  • the ratios of successive scale degrees in a sequence are elements in an ordered set.
  • sequences of notes or ratios are mapped onto an ordered set of elements. These ordered sets are then lexicographically arranged in the data base. Comparison between the input data and the reference data then proceeds lexicographically, i.e., in the same way as looking up a word in a dictionary, for example, according to an N-ary tree search strategy.
  • a tree within this context is an ordered set of components wherein each component has exactly one predecessor and each component has at the most a number of N direct successors.
  • a dictionary of, e.g., the English language orders words as finite sets of, say, L letters at the most. Each of the L letters assumes one of twenty-six possible values. Words that have as a first letter the letter “a” come before words with a first letter "b”, and words that begin with the letter "c” come after the "b" -words. Within the category of the "a"-words, words that have as a second letter the letter "b” are arranged after those that have as the second letter the letter "a”, etc.
  • Fig. 2 is a diagram to illustrate the lexicographic organization of reference sequences and the carrying out of a query in a tree 200.
  • each of the ordered sets represents a reference sequence as stored and that each set has three elements.
  • Each element is represented by an integer in the range from "one" to "seven”.
  • An element represents a scale degree or a ratio of successive scale degrees in a sequence as explained above.
  • Only set 202 has been assigned a reference numeral among the lexicographically arranged sets stored in memory 104 in order to not obscure the drawing.
  • Each of the sets has a different pointer, indicated by a letter "P".
  • an input data 204 represents a sequence of normalized scale degrees having the values: 5, 2, 7 and 1, respectively.
  • the reference sequences are normalized to the scale degree "5". That is, a more complete reference sequence as stored should have begun with a "5". However, if all reference sequences were stored beginning with the same "5", the "5" at the begin would not contribute to discriminating between different reference sequences and only waste storage space. Therefore, the "5" as normalizing agent for the reference sequences is left out when the latter is stored in memory 104. The "5" is also left out from the input sequence in order to carry out the query.
  • the query starts with an input sequence 2,7, 1.
  • a first node 206 in tree 200 leads to all reference sequences whose ordered sets start with a "2".
  • the MIDI (Musical Instrument Digital Interface) protocol can be used to provide a standardized means to provide music as digital electronic data.
  • the normalizing of the input sequence to the predetermined scale degree can be accomplished in real time by proper data processing and is known in the art, e.g. , from toys that change the pitch of the user's voice.
  • the input data are then to be put into the same format: an ordered set of ratios.
  • the first element is then not discarded.
  • the MIDI protocol can be used to convert an input sequence of music notes into an input sequence of ratios in real-time.
  • the input data comprises rhythm information about a musical theme.
  • the rhythm information comprises the time signature (meter) and the accentuations of the theme.
  • the time signature determines the number of beats to the measure.
  • the accentuation determines which beat gets an accent and which one does not.
  • rhythmic accentuation patterns are used as input data in order to retrieve bibliographic information and/or a sample of the pre-recorded musical theme.
  • the user enters the rhythmic accentuation pattern into the system as a substantially monotonic sequence of accentuated and unaccentuated sounds through humming or manipulating a particular key of a keyboard, or drumming the rhythm with his or her fingers.
  • the input data is then represented by, e.g., a sequence of peaks of varying height in the time domain. The relative distances between successive peaks represent the temporal aspects of the pattern and the heights represent the accentuations in the pattern.
  • the pattern is assumed to repeat itself.
  • the input data is processed as a two-dimensional array.
  • One dimension represents the time sequence of peaks, such as: 10110101010101100 etc.
  • the “1” represents the occurrence of a peak, the "0" the absence.
  • a single “0” represents the shortest time interval that is needed to characterize the rhythm. If the rhythm is more complicated, i.e., if there are shorter and longer time periods between successive peaks, the shorter time period is taken to be the base unit. That is, the time stamping is related to the shortest time period characterizing the pattern, thus normalizing the pattern.
  • the other dimension relates to the relative intensity of the peaks. The intensity levels are, for example, assigned a "high” or a "low”.
  • a query then proceeds as follows. The user enters the rhythmic pattern into the system.
  • the pattern is converted into the string of "l"'s and "0"'s as specified above. Once the repetitive character is determined the pattern is a finite digital word.
  • the reference sequences are digital words and are, again, ordered lexicographically. This enables the system to find one or more matching reference words upon receiving an input word. The system then pursues the query by finding the matching distribution of the accentuations within the reference words thus retrieved. Alternatively, the system could provide some bibliographic information regarding all of the matching reference words thus retrieved, leaving it to the user to determine whether the results provided show the accentuations.

Abstract

An information processing system has a music data base. The music data base stores homophonic reference sequences of music notes. The reference sequences are all normalized to the same scale degree so that they can be stored lexicographically. Upon finding a match between a string of input music notes and a particular reference sequence through an N-ary query, the system provides bibliographic information associated with the matching reference sequence.

Description

Bibliographic music data base with normalized musical themes.
FIELD OF THE INVENTION
The invention relates to an information processing system for interacting with a music data base, to a method of operating a music data base, and to a memory module with a music data base.
BACKGROUND ART
U.S. patent 5,402,339 discloses a system for creating a music data base of musical information that can be processed by a computer and for retrieving a string of note data items from the music data base. The known system comprises an input converter that converts music data supplied by an electronic device into note data items. The electronic device that supplies the music data is a computer, an electrical musical instrument, a music sampler or a reproducing device. Each note data item represents a time period and a scale degree of a sound identified by a single musical note. Both period and scale degree have digital values. The system further comprises a position information unit for producing position data items that specify the relative position in a sequence of the note data items in the piece of music represented by the music data. The note data items and position data items are stored together with an index table that links the data note items, the position data items, and the number of times a specific data note item occurs in the piece of music thus stored. The known system comprises means to retrieve a particular piece of stored music. Music information is supplied to the system as a string of note data items and associated position data items. A particular seek algorithm is employed to find a match between the string and a particular piece of music. The algorithm uses a histogram for each theme specifying the number of times a particular note occurs in this theme. The query for a matching theme is then facilitated by focusing on the rarest notes as the characterizing elements of the theme.
OBJECT OF THE INVENTION
The known system reproduces a piece of music stored upon finding a match between the stored piece and an entered string of musical notes. The known system processes note data items in a range that extend from the lowest to the highest musical notes audible (including flat and sharp) in order to cover all possible musical themes. That is, the note data items should be encoded as digital words wide enough to cover the range. As a consequence, memory capacity must be large enough to store these wide words. Further, the absolute magnitude of the pitch, or scale degree, of every note entered in the query must be accurate enough in order to match the one stored. The retrieval algorithm used is rather complicated in that it requires the storage and creation of note data items, position data items, index tables and histograms to control access to any sequence of note data items stored. The algorithm requires a histogram of each piece of music to keep track of how many times a given note occurs in a given sequence of notes stored, this number of times being a retrieval key.
It is an object of the invention to provide an alternative kind of information processing system having a music data base.
SUMMARY OF THE INVENTION
To this end, the invention provides an information processing system that comprises first memory means storing a data base having respective bibliographic information items corresponding with respective ones of multiple musical themes. The system further comprises second memory means for storing respective reference data representing respective reference sequences of reference musical components of respective ones of the musical themes. The system has an input for receiving an input data representative of an input sequence of input musical components, and retrieval means coupled to the input and to the first and second memory means for providing a particular bibliographic information item upon finding a match between a particular one of multiple reference data and the input data.
In a particular embodiment, each respective one of the input musical components comprises a respective input musical note, and each respective one of the reference musical components comprises a respective reference musical note.
The system of the invention associates an entered sequence of notes with one or more bibliographic information items upon finding a match with a stored sequence of notes. The bibliographic information item may include, for example, the name and biography of the composer, the name of the text writer, the lyrics, the title of the album, context information about the theme, related works. A MIDI file of the melody from which the reference sequence is a sample, or a recording of the actual performance, a video clip, etc, could be provided as well.
A musical theme as represented by a single sequence of notes is, by definition, homophonic. Typically, a musical theme within this context is a line of music that people find easy to remember, e.g., DA-DA-DA-DUMMM (Beethoven's Fifth Symphony), and DA-DAAA-da-da-daa-da-da-daa-da-da- a -DA-DAA ('Jumping Jack Flash', Rolling
Stones), etc. As another example, a musical theme easily remembered is the first couple of bars of a song or of a chorus (national anthems) or another dominant portion, or the theme is associated with a catching line of the lyrics (e.g., Andrew Lloyd Webber's rock opera's) or with an impressive riff (e.g., Keith Richards on guitar). The invention is especially of interest to record shops. Customers can retrieve in this manner the information about a musical theme, of which they have only remembered a couple of bars. Heretofore, clients had to rely on the expertise of the staff of the shop. The invention is also of interest to organizations like ASCAP (American Society of Composers, Authors and Publishers) whose function it is to protect the rights of composers, songwriters, lyricists and music publishers by licensing and negotiating royalties for the public performances of the copyrighted works of their members.
It is another object of the invention to enable fast and orderly identification of a given piece of music in a user-friendly manner using simplified hardware and software. It is a further object to provide a system that requires less storage space for the storage of musical notes. To this end, a preferred embodiment of the invention is characterized in that the multiple musical themes as represented by the reference sequences are uniformly normalized with regard to one and the same predetermined scale degree.
This aspect of the invention is based on the following insight. One and the same musical theme can be represented by an infinite number of note sequences. The ratio between the frequencies of the scale degrees of successive notes stays invariant in each such representation, but the frequency of a particular note can have any value. That is, the recognizability of a theme is substantially invariant under a gauge transformation that shifts the frequency of all notes of the sequence by the same fixed amount. Once the frequency of a particular note in the theme has been chosen, the absolute pitch of any other note in the same theme is fixed under this constraint. In the data base of the invention, the themes are normalized with regard to the one and the same scale degree. For example, the first note of each reference sequence as stored is always of the same pitch, e.g. , 220 cps. Alternatively, the first note of each reference sequence as stored is always such that if it were preceded by another note of the same theme, this preceding virtual note would have always the same pitch, uniform for all themes. This is a unique identification of the succeeding note, i.e., the first note in the reference sequence as stored, since the musical themes are known in advance.
This normalization reduces the width required of the words to represent the scale degrees in digital format as compared to the cited prior art. The scale degrees of the homophonic representation of the majority of the musical themes do not span more than two or three octaves. In the invention all themes are normalized to these two or three octaves. The memory for the reference sequences stores and routes much shorter words than in the prior art cited above. The input sequence is normalized with regard to the same scale degree as well in order to carry out the query. The input data represents an input sequence of input musical notes. The input data is provided through some appropriate interface. For example, a simple keyboard is used. Alternatively, the user hums the part of the tune into a microphone. If necessary, the user can employ a tuning fork of the appropriate pitch, or the system has means to generate a sound of this pitch, that helps the user to catch at least the first few notes. If necessary, filtering and quantization techniques are applied to extract from the tune, hummed or entered in another way, the appropriate notes for further processing.
In still another embodiment, the input sequence of input notes and the reference sequences of reference notes are represented as series of ratios between pairs of successive scale degrees. In this manner, the absolute scale degree of the first note, used as a direction in the previous embodiment, is not required anymore.
According to another aspect of the invention, scale degrees or ratios of pairs of successive scale degrees are mapped onto an ordered set, e.g. , onto that of the integers. The mapping per scale degree or ratio onto an element of an ordered set allows for lexicographic ordering of the reference data and the usage of a simple search strategy, e.g., an N-ary search strategy similar to that for a dictionary.
Assume that the input data is a sequence of musical notes, entered through a keyboard or hummed into a microphone. A further advantage of the lexicographic ordering is then that the query continues while the individual notes are being entered one after the other. Each next one of the notes successively decreases the number of candidate reference sequences, owing to the lexicographic ordering.
Alternatively, or supplementarily, the input data comprises rhythm information about a musical theme. The rhythm information comprises the time signature (meter) and the accentuations of the theme. The time signature determines the number of beats to the measure. The accentuation determines which beat gets an accent and which one does not. For example, the sign 6 8 in a musical score is the time signature indicating that the meter is 6 beats to the measure and that an eighth note gets one beat. Flamenco music has a variety of different styles, each determined by its own compas (rhythmic accentuation pattern). Typical examples of flamenco music are Alegrias, Bulerias, Siguiriyas and Soleares that all have 12 beats to the measure. In the Alegrias, Bulerias and Soleares, the third, sixth, eighth, tenth and twelfth beats are accentuated. The first, third, fifth, eighth and eleventh beats are emphasized in the Siguiriyas style.
In the invention, rhythmic accentuation patterns are used as input data in order to retrieve bibliographic information. For example, the user enters the rhythmic accentuation pattern into the system as a substantially monotonic sequence of accentuated and unaccentuated sounds through, e.g. , humming into a microphone or manipulating a particular key of a keyboard, or drumming the rhythm with his or her fingers. The input data then is represented by, e.g. , a sequence of beats or peaks of varying height in the time domain. The relative distances between successive peaks represent the temporal aspects of the pattern and the relative heights represent the accentuations in the pattern. The sequence of beats and rests in between is represented by a digital word. The words can again be stored lexicographically to enable a fast and orderly retrieval.
BRIEF DESCRIPTION OF THE DRAWINGS
The invention is explained by way of example and with reference to the accompanying drawings, wherein:
Fig. 1 is a diagram of an information processing system according the invention; and Fig. 2 is a diagram illustrating the lexicographically organized data base.
Throughout the figures, same reference numerals indicate similar or corresponding features.
PREFERRED EMBODIMENTS System
Fig. 1 is a block diagram of a system 100 according to the invention. System 100 comprises a first memory 102 storing a data base. The data base has respective bibliographic information items corresponding with respective ones of multiple musical themes. System 100 has a second memory 104 for storing respective reference data representing respective reference sequences of musical notes of respective ones of the musical themes. System 100 has an input 106 for receiving an input data representative of an input sequence of input musical notes. System 100 further has a retrieval engine 108 coupled to input 106 and to first and second memories 102 and 104. Retrieval engine 108 provides a particular bibliographic information item at an output 112 upon a match between a particular one of multiple reference data and the input data. For example, each reference data in memory 104 has a pointer to an associated bibliographic information item stored in memory 102. Upon a match between the input data supplied via input 106 and a specific one of the reference data in memory 104, the corresponding pointer identifies the associated bibliographic information item in memory 102.
Memories 102 and 104 in this example are combined in a memory module 110 such as an optical memory (e.g., a CD, or a DVD) or a solid-state memory. Module 110 is physically detachable from retrieval engine 108. In this manner, system 100 can be provided with different modules for different categories of music (e.g., symphonies, jazz, rock, folk) or for different kinds of bibliographic information (e.g., lyrics, biographies of composers).
In an alternative embodiment, memory means 102 and 104 are stored at a server. The browser software is provided by retrieval means 108. The user is enabled to transmit his input data to the server and receives the appropriate category of bibliographic information if there is match.
Lexicographically organized data base
The multiple musical themes as stored in memory 104 and as represented by the reference sequences are uniformly normalized with regard to one and the same predetermined scale degree. The first note of each reference sequence as stored is always of the same pitch, e.g., 220 cps. Alternatively, the first note of each reference sequence as stored in memory 104 is always such that, if it were preceded by another note of the same theme, this preceding virtual note would have always the same pitch uniform for all themes. This is a unique identification of the succeeding note, i.e., the first note in the reference sequence, since the musical themes are known in advance. The input sequence is normalized as well with regard to the same scale degree in order to carry out the query.
Each respective one of the reference data comprises a respective ordered set of elements. A position of a specific element and a value of the specific element in the respective ordered set are determined by a position and scale degree of a specific one of the musical notes in the respective reference sequence. For example, each note, middle, or with an associated sharp, or with an associated flat, is represented in a data format that identifies its linear position in an octave and that identifies the linear position of the octave within the range of octaves covered by the musical themes in the data base. Alternatively, each note is assigned one of the integers in the range from 1 to K. In still another embodiment, the ratios of successive scale degrees in a sequence are elements in an ordered set. In these manners, sequences of notes or ratios are mapped onto an ordered set of elements. These ordered sets are then lexicographically arranged in the data base. Comparison between the input data and the reference data then proceeds lexicographically, i.e., in the same way as looking up a word in a dictionary, for example, according to an N-ary tree search strategy.
A tree within this context is an ordered set of components wherein each component has exactly one predecessor and each component has at the most a number of N direct successors. A dictionary of, e.g., the English language, orders words as finite sets of, say, L letters at the most. Each of the L letters assumes one of twenty-six possible values. Words that have as a first letter the letter "a" come before words with a first letter "b", and words that begin with the letter "c" come after the "b" -words. Within the category of the "a"-words, words that have as a second letter the letter "b" are arranged after those that have as the second letter the letter "a", etc. That is, given the j-th letter of a word, there are at most twenty-six direct successors determined by the values of the (j - l)-th letter. Accordingly, looking up a particular word, say: "hello", in a lexicon proceeds as follows. First, the letter at the begin of the word is determined. This is an "h" in the word "hello". One proceeds to the chapter of words starting with an "h". Then, the second letter is determined. Assume this is an "e". One then proceeds to the sub-category of words in the "h" -chapter that start with "he", and so on. Note that each next step requires making a selection out of at the most twenty-six possibilities. A similar search strategy is adopted for the purpose of finding a match between the particular input sequence and one of the reference sequences of notes on the chromatic scale in music (the scale with twelve half tones to the octave).
Fig. 2 is a diagram to illustrate the lexicographic organization of reference sequences and the carrying out of a query in a tree 200. For the sake of simplicity it is assumed that each of the ordered sets represents a reference sequence as stored and that each set has three elements. Each element is represented by an integer in the range from "one" to "seven". An element represents a scale degree or a ratio of successive scale degrees in a sequence as explained above. Only set 202 has been assigned a reference numeral among the lexicographically arranged sets stored in memory 104 in order to not obscure the drawing.
Each of the sets has a different pointer, indicated by a letter "P".
Assume that an input data 204 represents a sequence of normalized scale degrees having the values: 5, 2, 7 and 1, respectively. The reference sequences are normalized to the scale degree "5". That is, a more complete reference sequence as stored should have begun with a "5". However, if all reference sequences were stored beginning with the same "5", the "5" at the begin would not contribute to discriminating between different reference sequences and only waste storage space. Therefore, the "5" as normalizing agent for the reference sequences is left out when the latter is stored in memory 104. The "5" is also left out from the input sequence in order to carry out the query.
Accordingly, the query starts with an input sequence 2,7, 1. A first node 206 in tree 200 leads to all reference sequences whose ordered sets start with a "2". A next, second node
208 leads to all references sequences whose ordered sets start with "2,7". A third node 210 leads to the reference sequence represented by the ordered set "2,7, 1". Accordingly, there is a match between the input data and the reference data. Pointer "P" associated with stored set
"2,7,1" is used by retrieval engine 108 to retrieve from memory 102 the bibliographic information item or items corresponding to reference sequence "2,7,1".
The MIDI (Musical Instrument Digital Interface) protocol can be used to provide a standardized means to provide music as digital electronic data. The normalizing of the input sequence to the predetermined scale degree can be accomplished in real time by proper data processing and is known in the art, e.g. , from toys that change the pitch of the user's voice.
A similar procedure is followed if the elements in the ordered sets represent ratios of pairs of successive musical notes in the reference sequence. The input data are then to be put into the same format: an ordered set of ratios. The first element is then not discarded. The MIDI protocol can be used to convert an input sequence of music notes into an input sequence of ratios in real-time.
Alternatively, or supplementarily, the input data comprises rhythm information about a musical theme. The rhythm information comprises the time signature (meter) and the accentuations of the theme. The time signature determines the number of beats to the measure. The accentuation determines which beat gets an accent and which one does not.
In the invention, rhythmic accentuation patterns are used as input data in order to retrieve bibliographic information and/or a sample of the pre-recorded musical theme. For example, the user enters the rhythmic accentuation pattern into the system as a substantially monotonic sequence of accentuated and unaccentuated sounds through humming or manipulating a particular key of a keyboard, or drumming the rhythm with his or her fingers. The input data is then represented by, e.g., a sequence of peaks of varying height in the time domain. The relative distances between successive peaks represent the temporal aspects of the pattern and the heights represent the accentuations in the pattern. The pattern is assumed to repeat itself. The input data is processed as a two-dimensional array. One dimension represents the time sequence of peaks, such as: 10110101010101100 etc. The "1" represents the occurrence of a peak, the "0" the absence. A single "0" represents the shortest time interval that is needed to characterize the rhythm. If the rhythm is more complicated, i.e., if there are shorter and longer time periods between successive peaks, the shorter time period is taken to be the base unit. That is, the time stamping is related to the shortest time period characterizing the pattern, thus normalizing the pattern. The other dimension relates to the relative intensity of the peaks. The intensity levels are, for example, assigned a "high" or a "low". A query then proceeds as follows. The user enters the rhythmic pattern into the system. The pattern is converted into the string of "l"'s and "0"'s as specified above. Once the repetitive character is determined the pattern is a finite digital word. The reference sequences are digital words and are, again, ordered lexicographically. This enables the system to find one or more matching reference words upon receiving an input word. The system then pursues the query by finding the matching distribution of the accentuations within the reference words thus retrieved. Alternatively, the system could provide some bibliographic information regarding all of the matching reference words thus retrieved, leaving it to the user to determine whether the results provided show the accentuations.

Claims

CLAIMS:
1. An information processing system comprising:
- first memory means storing a data base having respective bibliographic information items corresponding with respective ones of multiple musical themes;
- second memory means for storing respective reference data representing respective reference sequences of reference musical components of respective ones of the musical themes;
- an input for receiving an input data representative of an input sequence of input musical components; characterized in that the system further comprises retrieval means coupled to the input and to the first and second memory means for providing a particular bibliographic information item upon finding a match between a particular one of multiple reference data and the input data.
2. The system of claim 1, wherein:
- each respective one of the input musical components comprises a respective input musical note; and - each respective one of the reference musical components comprises a respective reference musical note.
3. The system of claim 2, wherein the multiple musical themes as represented by the reference sequences are uniformly normalized with regard to one and the same predetermined scale degree.
4. The system of claim 3, wherein:
- each respective one of the reference data comprises a respective ordered set of elements;
- a position of a specific element and a value of the specific element in the respective ordered set are determined by a position and scale degree of a specific one of the reference musical notes in the respective reference sequence; and - the reference data are organized lexicographically in the second memory means.
5. The system of claim 2, wherein:
- the second memory means stores the respective reference sequences as respective series of ratios between pairs of successive scale degrees of the reference musical notes; and
- the input receives the input data representative of an input sequence of ratios between pairs of successive scale degrees of the input musical notes.
6. The system of claim 5, wherein:
- each respective one of the reference data comprises a respective ordered set of elements;
- a position of a specific element and a value of the specific element in the respective ordered set are determined by a position and a magnitude of the ratio of scale degrees of a specific pair of the reference musical notes in the respective reference sequence; and
- the reference data are organized lexicographically in the second memory means.
7. A memory module comprising:
- first memory means storing a data base having respective bibliographic information items corresponding with respective ones of multiple musical themes;
- second memory means for storing respective reference data representing respective reference sequences of reference musical components of respective ones of the musical themes and for storing pointers that link a specific one of the reference data to a specific one of the bibliographic information items.
8. The module of claim 7, wherein:
- each respective one of the reference musical components comprises a respective reference musical note; and
- the multiple musical themes as represented by the reference sequences are uniformly normalized with regard to one and the same predetermined scale degree.
9. The module of claim 8, wherein:
- each respective one of the reference data comprises a respective ordered set of elements;
- a position of a specific element and a value of the specific element in the respective ordered set are determined by a position and scale degree of a specific one of the musical notes in the respective reference sequence; and - the reference data are organized lexicographically in the second memory means.
10. A method of creating a music data base, the method comprising:
- storing in a memory respective bibliographic information items corresponding with a respective one of multiple musical themes;
- storing, lexicographically, in the memory respective reference sequences of reference musical components representative of respective ones of the musical themes; and
- providing respective pointers for linking a respective one of the reference sequences to a respective one of the bibliographic information items.
11. A method of enabling interacting with an information processing system, the system comprising: - first memory means storing a data base having respective bibliographic information items corresponding with respective ones of multiple musical themes;
- second memory means for storing respective reference data representing respective reference sequences of musical notes of respective ones of the musical themes, wherein - the reference sequences are uniformly normalized with regard to one and the same predetermined scale degree;
- an input for receiving an input data representative of an input sequence of further musical notes; and
- retrieval means coupled to the input and to the first and second memory means for providing a particular bibliographic information item upon finding a match between a particular one of multiple reference data and the input data; the interacting comprising:
- normalizing the input sequence to the predetermined scale degree.
PCT/IB1998/000362 1997-04-28 1998-03-16 Bibliographic music data base with normalized musical themes WO1998049630A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP10529340A JP2000513846A (en) 1997-04-28 1998-03-16 Recorded music database based on standardized music themes
EP98905577A EP0919033A1 (en) 1997-04-28 1998-03-16 Bibliographic music data base with normalized musical themes

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US08/840,356 1997-04-28
US08/840,356 US5963957A (en) 1997-04-28 1997-04-28 Bibliographic music data base with normalized musical themes

Publications (1)

Publication Number Publication Date
WO1998049630A1 true WO1998049630A1 (en) 1998-11-05

Family

ID=25282145

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB1998/000362 WO1998049630A1 (en) 1997-04-28 1998-03-16 Bibliographic music data base with normalized musical themes

Country Status (4)

Country Link
US (1) US5963957A (en)
EP (1) EP0919033A1 (en)
JP (1) JP2000513846A (en)
WO (1) WO1998049630A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000172693A (en) * 1998-12-01 2000-06-23 Nippon Telegr & Teleph Corp <Ntt> Device and method for retrieving music and recording medium with music retrieval program recorded therein
WO2001003000A2 (en) * 1999-07-01 2001-01-11 Koninklijke Philips Electronics N.V. Internet browser
EP1703488A2 (en) * 2004-09-30 2006-09-20 Kabushiki Kaisha Toshiba Music search system and music search apparatus
CN100421112C (en) * 2000-12-07 2008-09-24 索尼公司 Communication apparatus and communication method

Families Citing this family (86)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7313251B2 (en) 1993-11-18 2007-12-25 Digimarc Corporation Method and system for managing and controlling electronic media
US8094949B1 (en) 1994-10-21 2012-01-10 Digimarc Corporation Music methods and systems
US6560349B1 (en) 1994-10-21 2003-05-06 Digimarc Corporation Audio monitoring using steganographic information
US7224819B2 (en) 1995-05-08 2007-05-29 Digimarc Corporation Integrating digital watermarks in multimedia content
US6760463B2 (en) 1995-05-08 2004-07-06 Digimarc Corporation Watermarking methods and media
US7805500B2 (en) 1995-05-08 2010-09-28 Digimarc Corporation Network linking methods and apparatus
US6829368B2 (en) 2000-01-26 2004-12-07 Digimarc Corporation Establishing and interacting with on-line media collections using identifiers in media signals
US6411725B1 (en) 1995-07-27 2002-06-25 Digimarc Corporation Watermark enabled video objects
US6505160B1 (en) 1995-07-27 2003-01-07 Digimarc Corporation Connected audio and other media objects
US6965682B1 (en) 1999-05-19 2005-11-15 Digimarc Corp Data transmission by watermark proxy
US7562392B1 (en) 1999-05-19 2009-07-14 Digimarc Corporation Methods of interacting with audio and ambient music
US8180844B1 (en) 2000-03-18 2012-05-15 Digimarc Corporation System for linking from objects to remote resources
US7505605B2 (en) 1996-04-25 2009-03-17 Digimarc Corporation Portable devices and methods employing digital watermarking
US7930546B2 (en) * 1996-05-16 2011-04-19 Digimarc Corporation Methods, systems, and sub-combinations useful in media identification
US6243725B1 (en) 1997-05-21 2001-06-05 Premier International, Ltd. List building system
US6504089B1 (en) * 1997-12-24 2003-01-07 Canon Kabushiki Kaisha System for and method of searching music data, and recording medium for use therewith
US7689532B1 (en) 2000-07-20 2010-03-30 Digimarc Corporation Using embedded data with file sharing
US6263345B1 (en) * 1998-09-28 2001-07-17 Compaq Computers, Corporation Histogram synthesis modeler for a database query optimizer
JP2000221988A (en) * 1999-01-29 2000-08-11 Sony Corp Data processing device, data processing method, program providing medium, and recording medium
US8055588B2 (en) * 1999-05-19 2011-11-08 Digimarc Corporation Digital media methods
US8874244B2 (en) 1999-05-19 2014-10-28 Digimarc Corporation Methods and systems employing digital content
US7406214B2 (en) * 1999-05-19 2008-07-29 Digimarc Corporation Methods and devices employing optical sensors and/or steganography
US7194752B1 (en) 1999-10-19 2007-03-20 Iceberg Industries, Llc Method and apparatus for automatically recognizing input audio and/or video streams
US7174293B2 (en) * 1999-09-21 2007-02-06 Iceberg Industries Llc Audio identification system and method
DE19948974A1 (en) 1999-10-11 2001-04-12 Nokia Mobile Phones Ltd Method for recognizing and selecting a tone sequence, in particular a piece of music
US7257536B1 (en) * 1999-11-23 2007-08-14 Radiant Systems, Inc. Audio request interaction system
US7310629B1 (en) 1999-12-15 2007-12-18 Napster, Inc. Method and apparatus for controlling file sharing of multimedia files over a fluid, de-centralized network
US6742023B1 (en) 2000-04-28 2004-05-25 Roxio, Inc. Use-sensitive distribution of data files between users
US6366907B1 (en) 1999-12-15 2002-04-02 Napster, Inc. Real-time search engine
JP4785168B2 (en) 2000-01-13 2011-10-05 ディジマーク コーポレイション Metadata authentication and embedding metadata in watermarks in media signals
US6389467B1 (en) * 2000-01-24 2002-05-14 Friskit, Inc. Streaming media search and continuous playback system of media resources located by multiple network addresses
US6519648B1 (en) * 2000-01-24 2003-02-11 Friskit, Inc. Streaming media search and continuous playback of multiple media resources located on a network
US7281034B1 (en) 2000-01-24 2007-10-09 Friskit, Inc. System and method for media playback over a network using links that contain control signals and commands
US7444353B1 (en) * 2000-01-31 2008-10-28 Chen Alexander C Apparatus for delivering music and information
US20020073098A1 (en) * 2000-02-28 2002-06-13 Lei Zhang Methodology and system for searching music over computer network and the internet based on melody and rhythm input
US6225546B1 (en) * 2000-04-05 2001-05-01 International Business Machines Corporation Method and apparatus for music summarization and creation of audio summaries
US8121843B2 (en) 2000-05-02 2012-02-21 Digimarc Corporation Fingerprint methods and systems for media signals
US6307139B1 (en) * 2000-05-08 2001-10-23 Sony Corporation Search index for a music file
KR100399502B1 (en) * 2000-06-08 2003-09-26 (주)오롬정보 Mass bibliography searching service system
JP2002045567A (en) * 2000-08-02 2002-02-12 Konami Co Ltd Portable terminal device, game perfomance support device and recording medium
US7089301B1 (en) 2000-08-11 2006-08-08 Napster, Inc. System and method for searching peer-to-peer computer networks by selecting a computer based on at least a number of files shared by the computer
FI20002161A (en) * 2000-09-29 2002-03-30 Nokia Mobile Phones Ltd Method and system for recognizing a melody
US7688306B2 (en) * 2000-10-02 2010-03-30 Apple Inc. Methods and apparatuses for operating a portable device based on an accelerometer
AU2002245191A1 (en) 2000-10-26 2002-07-24 Digimarc Corporation Method and system for internet access
EP1619599A1 (en) * 2000-11-27 2006-01-25 Yamaha Corporation Information retrieval system and information retrieval method using network
US7908338B2 (en) * 2000-12-07 2011-03-15 Sony Corporation Content retrieval method and apparatus, communication system and communication method
US8055899B2 (en) 2000-12-18 2011-11-08 Digimarc Corporation Systems and methods using digital watermarking and identifier extraction to provide promotional opportunities
US20020157034A1 (en) * 2001-02-21 2002-10-24 Koninklijke Philips Electronics N.V. Data streaming system substituting local content for unicasts
US7003515B1 (en) 2001-05-16 2006-02-21 Pandora Media, Inc. Consumer item matching method and system
US7962482B2 (en) 2001-05-16 2011-06-14 Pandora Media, Inc. Methods and systems for utilizing contextual feedback to generate and modify playlists
US6747201B2 (en) 2001-09-26 2004-06-08 The Regents Of The University Of Michigan Method and system for extracting melodic patterns in a musical piece and computer-readable storage medium having a program for executing the method
US6528715B1 (en) * 2001-10-31 2003-03-04 Hewlett-Packard Company Music search by interactive graphical specification with audio feedback
US6995309B2 (en) * 2001-12-06 2006-02-07 Hewlett-Packard Development Company, L.P. System and method for music identification
US6933432B2 (en) 2002-03-28 2005-08-23 Koninklijke Philips Electronics N.V. Media player with “DJ” mode
CN1703734A (en) * 2002-10-11 2005-11-30 松下电器产业株式会社 Method and apparatus for determining musical notes from sounds
JP4302967B2 (en) * 2002-11-18 2009-07-29 パイオニア株式会社 Music search method, music search device, and music search program
AU2003286383A1 (en) * 2002-12-20 2004-07-14 Koninklijke Philips Electronics N.V. Query by indefinite expressions
US9818136B1 (en) 2003-02-05 2017-11-14 Steven M. Hoffberg System and method for determining contingent relevance
JP4538449B2 (en) * 2003-03-03 2010-09-08 コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ String search method and equipment
US7385130B2 (en) * 2003-10-09 2008-06-10 Pioneer Corporation Music selecting apparatus and method
USRE43379E1 (en) 2003-10-09 2012-05-15 Pioneer Corporation Music selecting apparatus and method
CN100454298C (en) 2003-12-08 2009-01-21 皇家飞利浦电子股份有限公司 Searching in a melody database
US20060059159A1 (en) * 2004-09-15 2006-03-16 Vu Hao Thi Truong Online dating service providing response status tracking for a service subscriber
JP4315101B2 (en) * 2004-12-20 2009-08-19 ヤマハ株式会社 Music content providing apparatus and program
JP2006318182A (en) * 2005-05-12 2006-11-24 Sharp Corp Sound retrieval device, sound retrieval method, sound reproduction method, portable reproduction device, musical piece retrieval device, musical piece retrieval method and musical piece reproduction method
JP2007072023A (en) * 2005-09-06 2007-03-22 Hitachi Ltd Information processing apparatus and method
CN100367279C (en) * 2005-09-08 2008-02-06 上海交通大学 Leap over type high speed matching device of numerical music melody
EP1785891A1 (en) * 2005-11-09 2007-05-16 Sony Deutschland GmbH Music information retrieval using a 3D search algorithm
US7518052B2 (en) * 2006-03-17 2009-04-14 Microsoft Corporation Musical theme searching
US20100205628A1 (en) 2009-02-12 2010-08-12 Davis Bruce L Media processing methods and arrangements
US9390167B2 (en) 2010-07-29 2016-07-12 Soundhound, Inc. System and methods for continuous audio matching
CN101916250B (en) * 2010-04-12 2011-10-19 电子科技大学 Humming-based music retrieving method
US9047371B2 (en) 2010-07-29 2015-06-02 Soundhound, Inc. System and method for matching a query against a broadcast stream
JP5552968B2 (en) * 2010-08-30 2014-07-16 ヤマハ株式会社 Music search apparatus and music search method
US10019995B1 (en) 2011-03-01 2018-07-10 Alice J. Stiebel Methods and systems for language learning based on a series of pitch patterns
US11062615B1 (en) 2011-03-01 2021-07-13 Intelligibility Training LLC Methods and systems for remote language learning in a pandemic-aware world
US9035163B1 (en) 2011-05-10 2015-05-19 Soundbound, Inc. System and method for targeting content based on identified audio and multimedia
US10957310B1 (en) 2012-07-23 2021-03-23 Soundhound, Inc. Integrated programming framework for speech and text understanding with meaning parsing
US9507849B2 (en) 2013-11-28 2016-11-29 Soundhound, Inc. Method for combining a query and a communication command in a natural language computer system
US9292488B2 (en) 2014-02-01 2016-03-22 Soundhound, Inc. Method for embedding voice mail in a spoken utterance using a natural language processing computer system
US11295730B1 (en) 2014-02-27 2022-04-05 Soundhound, Inc. Using phonetic variants in a local context to improve natural language understanding
US9564123B1 (en) 2014-05-12 2017-02-07 Soundhound, Inc. Method and system for building an integrated user profile
US9721564B2 (en) * 2014-07-31 2017-08-01 Rovi Guides, Inc. Systems and methods for performing ASR in the presence of heterographs
US9280960B1 (en) * 2014-12-15 2016-03-08 Amazon Technologies, Inc. Navigating music using an index including musical symbols
CN107481706B (en) * 2017-08-08 2021-08-03 腾讯音乐娱乐(深圳)有限公司 Song skewer burning method and device
US11712637B1 (en) 2018-03-23 2023-08-01 Steven M. Hoffberg Steerable disk or ball

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5402339A (en) * 1992-09-29 1995-03-28 Fujitsu Limited Apparatus for making music database and retrieval apparatus for such database
JPH08123818A (en) * 1994-10-25 1996-05-17 Nippon Telegr & Teleph Corp <Ntt> Musical information retrieving system and method thereof
EP0766225A1 (en) * 1995-09-29 1997-04-02 Yamaha Corporation Music data processing system
JPH09138691A (en) * 1995-11-15 1997-05-27 Brother Ind Ltd Musical piece retrieval device
JPH09293083A (en) * 1996-04-26 1997-11-11 Toshiba Corp Music retrieval device and method

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4945804A (en) * 1988-01-14 1990-08-07 Wenger Corporation Method and system for transcribing musical information including method and system for entering rhythmic information
US5341457A (en) * 1988-12-30 1994-08-23 At&T Bell Laboratories Perceptual coding of audio signals
US5451709A (en) * 1991-12-30 1995-09-19 Casio Computer Co., Ltd. Automatic composer for composing a melody in real time
JP3271282B2 (en) * 1991-12-30 2002-04-02 カシオ計算機株式会社 Automatic melody generator
BR9507545A (en) * 1994-04-28 1997-08-05 Music Vending Inc Music selling system
US5616876A (en) * 1995-04-19 1997-04-01 Microsoft Corporation System and methods for selecting music on the basis of subjective content
US5728960A (en) * 1996-07-10 1998-03-17 Sitrick; David H. Multi-dimensional transformation systems and display communication architecture for musical compositions

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5402339A (en) * 1992-09-29 1995-03-28 Fujitsu Limited Apparatus for making music database and retrieval apparatus for such database
JPH08123818A (en) * 1994-10-25 1996-05-17 Nippon Telegr & Teleph Corp <Ntt> Musical information retrieving system and method thereof
EP0766225A1 (en) * 1995-09-29 1997-04-02 Yamaha Corporation Music data processing system
JPH09138691A (en) * 1995-11-15 1997-05-27 Brother Ind Ltd Musical piece retrieval device
JPH09293083A (en) * 1996-04-26 1997-11-11 Toshiba Corp Music retrieval device and method

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000172693A (en) * 1998-12-01 2000-06-23 Nippon Telegr & Teleph Corp <Ntt> Device and method for retrieving music and recording medium with music retrieval program recorded therein
WO2001003000A2 (en) * 1999-07-01 2001-01-11 Koninklijke Philips Electronics N.V. Internet browser
WO2001003000A3 (en) * 1999-07-01 2003-12-24 Koninkl Philips Electronics Nv Internet browser
KR100808399B1 (en) * 1999-07-01 2008-02-29 코닌클리케 필립스 일렉트로닉스 엔.브이. Internet browser
CN100421112C (en) * 2000-12-07 2008-09-24 索尼公司 Communication apparatus and communication method
EP1703488A2 (en) * 2004-09-30 2006-09-20 Kabushiki Kaisha Toshiba Music search system and music search apparatus
EP1703488A3 (en) * 2004-09-30 2007-02-07 Kabushiki Kaisha Toshiba Music search system and music search apparatus
US7368652B2 (en) 2004-09-30 2008-05-06 Kabushiki Kaisha Toshiba Music search system and music search apparatus

Also Published As

Publication number Publication date
JP2000513846A (en) 2000-10-17
US5963957A (en) 1999-10-05
EP0919033A1 (en) 1999-06-02

Similar Documents

Publication Publication Date Title
US5963957A (en) Bibliographic music data base with normalized musical themes
US6678680B1 (en) Music search engine
US6188010B1 (en) Music search by melody input
McNab et al. The new zealand digital library melody index
Typke et al. A survey of music information retrieval systems
US6307139B1 (en) Search index for a music file
US7488886B2 (en) Music information retrieval using a 3D search algorithm
JPH06110945A (en) Music data base preparing device and retrieving device for the same
KR20060132607A (en) Searching in a melody database
JP2000356996A (en) Music retrieval system
JPH1115468A (en) Method, device, and system for music retrieval, and recording medium
EP2024965A1 (en) Method and electronic device for aligning a song with its lyrics
US7962530B1 (en) Method for locating information in a musical database using a fragment of a melody
US20060253433A1 (en) Method and apparatus for knowledge-based music searching and method and apparatus for managing music file
KR100512143B1 (en) Method and apparatus for searching of musical data based on melody
JP2000155759A (en) Retrieval device and storage device, and retrieving method and storing method for music information, and storage medium where programs thereof are recorded
Lee et al. Korean traditional music genre classification using sample and MIDI phrases
JP2001109471A (en) Music retrieval device, music retrieval method and recording medium recording music retrieval program
KR20060019096A (en) Hummed-based audio source query/retrieval system and method
Gurjar et al. Comparative Analysis of Music Similarity Measures in Music Information Retrieval Systems.
JP2002055695A (en) Music search system
US6313390B1 (en) Method for automatically controlling electronic musical devices by means of real-time construction and search of a multi-level data structure
JP4103715B2 (en) Music information distribution system
KR100481575B1 (en) Method for constructing a music database and retrieving a music information using the statistical properties of musical speech
JPH06202621A (en) Music retrieval device utilizing music performance information

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): JP

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH DE DK ES FI FR GB GR IE IT LU MC NL PT SE

WWE Wipo information: entry into national phase

Ref document number: 1998905577

Country of ref document: EP

121 Ep: the epo has been informed by wipo that ep was designated in this application
WWP Wipo information: published in national office

Ref document number: 1998905577

Country of ref document: EP