Subband-based speech recognition
- 22 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1251-1254
- https://doi.org/10.1109/icassp.1997.596172
Abstract
In the framework of Hidden Markov Models (HMM) or hybridHMM/Artificial Neural Network (ANN) systems, wepresent a new approach towards automatic speech recognition(ASR). The general idea is to divide up the full frequencyband (represented in terms of critical bands) intoseveral subbands, compute phone probabilities for each subbandon the basis of subband acoustic features, performdynamic programming independently for each band, andmerge the subband recognizers (recombining the...Keywords
This publication has 6 references indexed in Scilit:
- A mew ASR approach based on independent processing and recombination of partial frequency bandsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Towards ASR on partially corrupted speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Hidden Markov model decomposition of speech and noisePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Analysis of linear prediction, coding, and spectral estimation from subbandsIEEE Transactions on Information Theory, 1996
- RASTA processing of speechIEEE Transactions on Speech and Audio Processing, 1994
- How do humans process and recognize speech?IEEE Transactions on Speech and Audio Processing, 1994