Name
Title | ||
|---|---|---|
Multi-environment model adaptation based on vector Taylor series for robust speech recognition |
Abstract | ||
|---|---|---|
In this paper, we propose a multi-environment model adaptation method based on vector Taylor series (VTS) for robust speech recognition. In the training phase, the clean speech is contaminated with noise at different signal-to-noise ratio (SNR) levels to produce several types of noisy training speech and each type is used to obtain a noisy hidden Markov model (HMM) set. In the recognition phase, the HMM set which best matches the testing environment is selected, and further adjusted to reduce the environmental mismatch by the VTS-based model adaptation method. In the proposed method, the VTS approximation based on noisy training speech is given and the testing noise parameters are estimated from the noisy testing speech using the expectation-maximization (EM) algorithm. The experimental results indicate that the proposed multi-environment model adaptation method can significantly improve the performance of speech recognizers and outperforms the traditional model adaptation method and the linear regression-based multi-environment method. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1016/j.patcog.2010.03.023 | Pattern Recognition |
Keywords | Field | DocType |
traditional model adaptation method,vts-based model adaptation method,noisy testing speech,speech recognizers,linear regression-based multi-environment method,noisy training speech,vector taylor series,robust speech recognition,multi-environment model adaptation method,clean speech,multi-environment model adaptation,expectation maximization,em algorithm,speech recognition,hidden markov model,linear regression,signal to noise ratio | Speech processing,Pattern recognition,Regression analysis,Expectation–maximization algorithm,Signal-to-noise ratio,Speech recognition,Artificial intelligence,Hidden Markov model,Machine learning,Mathematics,Linear regression,Taylor series | Journal |
Volume | Issue | ISSN |
43 | 9 | Pattern Recognition |
Citations | PageRank | References |
1 | 0.35 | 20 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yong Lü | 1 | 1 | 0.35 |
| Haiyang Wu | 2 | 1 | 0.35 |
| Lin Zhou | 3 | 26 | 6.36 |
| Zhenyang Wu | 4 | 154 | 17.52 |