A mew ASR approach based on independent processing and recombination of partial frequency bands
作者： H. Bourlard , S. Dupont
DOI: 10.1109/ICSLP.1996.607145
关键词: Voice activity detection 、 Frequency band 、 Artificial neural network 、 Pattern recognition 、 Artificial intelligence 、 Time delay neural network 、 Hidden Markov model 、 Speaker recognition 、 Acoustic model 、 Speech recognition 、 Robustness (computer science) 、 Computer science
摘要: In the framework of hidden Markov models (HMM) or hybrid HMM/artificial neural network (ANN) systems, we present a new approach towards automatic speech recognition (ASR). The …
isca-speech.org
udel.edu 参考文章(6)
Herve Bourlard, Hynek Hermansky, Nelson Morgan, Stephane Dupont, Towards subband-based speech recognition european signal processing conference. pp. 1- 4 ,(1996) , 10.5281/ZENODO.36302
Louis D. Braida, Paul Duchnowski, A new structure for automatic speech recognition Ph.D. Thesis. ,(1993)
A.P. Varga, R.K. Moore, Hidden Markov model decomposition of speech and noise international conference on acoustics, speech, and signal processing. pp. 845- 848 ,(1990) , 10.1109/ICASSP.1990.115970
H. Hennansky, S. Tibrewala, M. Pavel, Towards ASR on partially corrupted speech international conference on spoken language processing. ,vol. 1, pp. 462- 465 ,(1996) , 10.1109/ICSLP.1996.607154
J.B. Allen, How do humans process and recognize speech IEEE Transactions on Speech and Audio Processing. ,vol. 2, pp. 567- 577 ,(1994) , 10.1109/89.326615
H. Hermansky, N. Morgan, RASTA processing of speech IEEE Transactions on Speech and Audio Processing. ,vol. 2, pp. 578- 589 ,(1994) , 10.1109/89.326616