ATR HMM-LR continuous speech recognition system
Toshiyuki Hanazawa, Kenji Kita, Satoshi Nakamura, Takeshi Kawabata, Kiyohiro Shikano · International Conference on Acoustics, Speech, and Signal Processing · 2002
An improvement of the hidden Markov model (HMM) LR continuous-speech recognizer using multiple codebooks, HMM state duration control and fuzzy vector quantization is described. The system recognizes Japanese phrases (Bunsetsu) according to a context-free grammar including 1035 words. In speaker-dependent conditions, a phrase recognition rate of 88.4% (99.0% for the top five candidates) was attained. The system was tested with speaker-adaptation based on a codebook mapping algorithm. An average speaker-adapted phrase recognition rate of 81.6% (98.8% for the top five candidates) was attained.>