Speech recognition system

• US 5,355,432 A
• Filed: 08/12/1992
• Issued: 10/11/1994
• Est. Priority Date: 08/30/1991
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Tanaka, Miyuki, Kato, Yasuhiko, Watari, Masao
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): KIM, RICHARD
• Application Number:
  US07/928,448
• Time in Patent Office: 790 Days
• Field of Search: 381/41, 381/43, 395/2.43
• US Class Current: 704/234
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates

Abstract

A speech recognition system includes an acoustic analyzer which produces a time sequence of acoustic parameters from an input speech signal in an utterance boundary thereof, and estimates a trajectory in a parameter space from the time sequence of acoustic parameters. The trajectory is re-sampled in the parameter space at predetermined constant intervals sequentially each time the acoustic parameters are produced by the acoustic analyzing means, thereby producing an input utterance pattern. The input utterance pattern is matched with reference speech patterns to recognize the input speech signal. The speech recognition system also has an utterance boundary detector for detecting the utterance boundary of the input speech signal. The trajectory is re-sampled while the utterance boundary is being detected by the utterance boundary detector.

Claims

1. A speech recognition system comprising:

acoustic analyzing means for producing a time sequence of acoustic parameters from an input speech signal in an utterance boundary thereof, and estimating a trajectory in a parameter space from said time sequence of acoustic parameters;

processing means for re-sampling said trajectory in said parameter space at predetermined constant intervals sequentially each time said acoustic parameters are produced by said acoustic analyzing means, thereby producing an input utterance pattern; and

matching means for matching said input utterance pattern with reference speech patterns to recognize the input speech signal.

2. A speech recognition system according to claim 1, further including utterance boundary detecting means for detecting said utterance boundary of the input speech signal, said processing means comprising means for re-sampling said trajectory while said utterance boundary is being detected by said utterance boundary detecting means.