摘要: A voice recognition system is disclosed which has incorporated therein information on the phonological effects syllables. The receives a signal and tentatively identifies syllable arrays provides collection of data syllables in arrays. are used to generate hypothetical from identified evaluated via arithmetic operations, taking into consideration context, speaker's habit dialect, thereby determining reliable representation input signal.
harvard.edu
aip.org
lens.org 参考文章(9)
Atsuo Tanaka, Fumio Togawa, Recognition of speech or speech-like sounds using associative memory ,(1982)
Daniel Kahn, Speech analysis syllabic segmenter Journal of the Acoustical Society of America. ,vol. 87, pp. 2801- 2801 ,(1983) , 10.1121/1.398999
Sadakazu Watanabe, Teruhiko Ukita, Speech recognition apparatus Journal of the Acoustical Society of America. ,vol. 85, pp. 1812- 1812 ,(1984) , 10.1121/1.399638
Nobuo Hataoka, Akira Ichikawa, Method for production of speech reference templates Journal of the Acoustical Society of America. ,vol. 87, pp. 468- 468 ,(1982) , 10.1121/1.399219
Yoichi Takebayashi, Hidenori Shinoda, Learning system of dictionary for speech recognition Journal of the Acoustical Society of America. ,vol. 88, pp. 1672- 1672 ,(1985) , 10.1121/1.400230
Matsumi Suzuki, Tetsuro Morino, Shozo Yokota, Speech recognition method and apparatus adapted to a plurality of different speakers ,(1975)
Matsumi Suzuki, Saburo Kitamoto, Tetsuro Morino, Voice verification system based on word pronunciation ,(1976)
Hiroshi Matsuura, Tsuneo Nitta, Monosyllable recognition apparatus ,(1983)
Kanou Hisao, HIGH-FREQUENCY HEATER ,(1983)