Title | ||
---|---|---|
Model composition by lagrange polynomial approximation for robust speech recognition in noisy environment |
Abstract | ||
---|---|---|
This paper presents a technique for estimating HMM model parameters for noisy speech from given clean speech HMM and noise HMM. The model parameters are estimated by approximating the non-linear function gov- erning the relationship between speech and noise, by a Lagrange polynomial, and thus enabling the distribution of corrupted speech parameters to have a closed form. The method is computationally efficient, and the experi- mental results showed significant improvement in recog- nition performance of noisy speech with this approach. Typically, word accuracy increased from 9.2% with clean model to 82.8% with the model composed by the pro- posed method as compared to 45.4% with the model com- posed by PMC Log-normal approximation, on an isolated word recognition task for exhibition hall noise added at 10 dB SNR. |
Year | Venue | Keywords |
---|---|---|
2004 | INTERSPEECH | word recognition |
Field | DocType | Citations |
Lagrange polynomial,Pattern recognition,Computer science,Model composition,Word recognition,Speech recognition,Artificial intelligence,Hidden Markov model,Word accuracy | Conference | 2 |
PageRank | References | Authors |
0.35 | 9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chandra Kant Raut | 1 | 21 | 2.30 |
Takuya Nishimoto | 2 | 227 | 28.95 |
Shigeki Sagayama | 3 | 1217 | 137.97 |