Abstract | ||
---|---|---|
In the framework of hidden Markov models (HMM) or hybrid HMM/Artificial Neural Network (ANN) systems, we present a new approach towards speech recognition. The general idea is to split the whole frequency band (represented in terms of critical bands) into a few sub-bands on which different recognizers are independently applied and then recombined at a certain speech unit level to yield global scores and a global recognition decision. The preliminary results presented in this paper show that such an approach, even using quite simple recombination strategies, can yield at least comparable performance on clean speech while providing significantly better robustness in the case of speech corrupted by narrowband noise. |
Year | Venue | Keywords |
---|---|---|
1996 | EUSIPCO | signal to noise ratio,histograms,speech,speech recognition,hidden markov models |
Field | DocType | ISBN |
Speech processing,Narrowband,Pattern recognition,Voice activity detection,Computer science,Signal-to-noise ratio,Speech recognition,Robustness (computer science),Speaker recognition,Artificial intelligence,Artificial neural network,Hidden Markov model | Conference | 978-888-6179-83-6 |
Citations | PageRank | References |
21 | 7.59 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Herve Bourlard | 1 | 152 | 37.75 |
Stephane Dupont | 2 | 324 | 43.20 |
Hynek Hermansky | 3 | 3298 | 510.27 |
Nelson Morgan | 4 | 3048 | 533.52 |