摘要 |
There is disclosed a speech recognition system and technique which is of the acoustic/phonetic type. It is made speaker-independent and capable of continuous speech recognition during fluent discourse by a combination of techniques which include, inter alia, using a so-called continuously-variable-duration hidden Markov model in identifying word segments and making all steps of the technique responsive to the durational information, and using a separate step for aligning the members of the candidate word arrays with the acoustic feature signals representative of the corresponding portion of the utterance, including using pairs of candidate phonetic segments in the alignment technique. |