Generating word hypotheses in continuous speech
作者： G. Schukat-Talamazzini , H. Niemann
DOI: 10.1109/ICASSP.1986.1168946
关键词:
摘要: This paper addresses the problem of generating word hypotheses in continuous German speech. It uses an extension well-known hidden Markow models order to model more accurately properties phonetic labeling stage. A powerful scoring function is derived. Experimental results are presented which were computed speaker independently.
sci-hub.se 参考文章(5)
Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, A Maximum Likelihood Approach to Continuous Speech Recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-5, pp. 179- 190 ,(1983) , 10.1109/TPAMI.1983.4767370
Dennis H. Klatt, Review of the ARPA speech understanding project Journal of the Acoustical Society of America. ,vol. 62, pp. 554- 575 ,(1990) , 10.1121/1.2003088
J. S. Bridle, M. D. Brown, R. M. Chamberlain, An Algorithm for Connected Word Recognition Automatic Speech Analysis and Recognition. ,vol. 7, pp. 191- 204 ,(1982) , 10.1007/978-94-009-7879-9_11
K. Sugawara, M. Nishimura, K. Toshioka, M. Okochi, T. Kaneko, Isolated word recognition using hidden Markov models international conference on acoustics, speech, and signal processing. ,vol. 10, pp. 1- 4 ,(1985) , 10.1109/ICASSP.1985.1168452
P. Regel, A module for acoustic-phonetic transcription of fluently spoken German speech IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 30, pp. 440- 450 ,(1982) , 10.1109/TASSP.1982.1163909