In a speech recognition arrangement, a speech pattern is recognized as one of a plurality of reference patterns for which acoustic feature signal templates are stored. Each template includes a time frame (e.g., 10 millisecond) sequence of spectral features e.g., LPC and nonspectral e.g., acoustic energy...http://www.google.es/patents/US4519094?utm_source=gb-gplus-sharePatente US4519094 - LPC Word recognizer utilizing energy features