Recognition of speech or speech-like sounds using associative memory
作者： Atsuo Tanaka , Fumio Togawa
DOI:
关键词:
摘要: Spoken words are recognized in a sequence of steps: first finding candidate the form mono-syllabic sequences; then associating (correcting) each to more speech-like sounds, comparing with pre-stored dictionary for final recognition.
lens.org 参考文章(5)
Hiroaki Sakoe, Speaker recognizer in which a significant part of a preselected one of input and reference patterns is pattern matched to a time normalized part of the other Journal of the Acoustical Society of America. ,vol. 82, pp. 1474- 1474 ,(1981) , 10.1121/1.395173
Hiroaki Sakoe, System for recognizing words continuously spoken according to a format Journal of the Acoustical Society of America. ,vol. 79, pp. 591- 591 ,(1979) , 10.1121/1.393497
Kaoru Nakano, Associatron-A Model of Associative Memory systems man and cybernetics. ,vol. 2, pp. 380- 388 ,(1972) , 10.1109/TSMC.1972.4309133
Stephen E. Levinson, Frank C. Pirz, Syntactic continuous speech recognizer The Journal of the Acoustical Society of America. ,vol. 78, pp. 1930- 1930 ,(1985) , 10.1121/1.392680