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... |
Year | DOI | Venue |
---|---|---|
1997 | 10.1109/ICASSP.1997.596172 | ICASSP |
Keywords | Field | DocType |
subband-based speech recognition,hidden markov model,neural nets,speech recognition,dynamic programming,automatic speech recognition,hidden markov models,artificial neural network,speech,critical bands,artificial neural networks,robustness | Pattern recognition,Frequency band,Computer science,Voice activity detection,Speech recognition,Robustness (computer science),Speaker recognition,Time delay neural network,Artificial intelligence,Artificial neural network,Hidden Markov model,Acoustic model | Conference |
ISBN | Citations | PageRank |
0-8186-7919-0 | 39 | 4.35 |
References | Authors | |
4 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Herve Bourlard | 1 | 152 | 37.75 |
S. DuPont | 2 | 39 | 4.35 |