Abstract | ||
---|---|---|
For decades, Hidden Markov Models (HMMs) have been the state-of-the-art technique for acoustic modeling despite their unrealistic independence assumptions and the very limited representational capacity of their hidden states. Conditional Restricted Boltzmann Machines (CRBMs) have recently proved to be very effective for modeling motion capture sequences and this paper investigates the application of this more powerful type of generative model to acoustic modeling. On the standard TIMIT corpus, one type of CRBM outperforms HMMs and is comparable with the best other methods, achieving a phone error rate (PER) of 26.7% on the TIMIT core test set. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICASSP.2010.5495651 | 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING |
Keywords | Field | DocType |
phone recognition, restricted Boltzmann machines, distributed representations | Data modeling,TIMIT,Boltzmann machine,Computer science,Artificial intelligence,Artificial neural network,Pattern recognition,Word error rate,Speech recognition,Hidden Markov model,Machine learning,Generative model,Test set | Conference |
ISSN | Citations | PageRank |
1520-6149 | 11 | 6.64 |
References | Authors | |
9 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Abdel-rahman Mohamed | 1 | 3772 | 266.13 |
geoffrey e hinton | 2 | 40435 | 4751.69 |