Name
Abstract | ||
|---|---|---|
In this paper, we investigate the use of the proposed non-parametric exemplar-based acoustic modeling for the NIST Open Keyword Search 2015 Evaluation. Specifically, kernel-density model is used to replace GMM in HMM/GMM (Hidden Markov Model / Gaussian Mixture Model) or DNN in HMM/DNN (Hidden Markov Model / Deep Neural Network) acoustic model to predict the emission probability of HMM states. To get further improvement, likelihood score generated by the kernel-density model is discriminatively tuned by the score tuning module realized by a neural network. Various configurations for score tuning module have been examined to show that simple neural network with 1 hidden layer is sufficient to fine tune the likelihood score generated by the kernel-density model. With this architecture, our exemplar-based model outperforms the 9-layer-DNN acoustic model significantly for both the speech recognition and keyword search tasks. In addition, our proposed exemplar-based system provides complementary information to other systems and we can further benefit from system combination. |
Year | Venue | Field |
|---|---|---|
2015 | Asia-Pacific Signal and Information Processing Association Annual Summit and Conference | Kernel (linear algebra),Pattern recognition,Computer science,Markov model,Keyword search,Speech recognition,NIST,Artificial intelligence,Artificial neural network,Hidden Markov model,Mixture model,Acoustic model |
DocType | ISSN | Citations |
Conference | 2309-9402 | 0 |
PageRank | References | Authors |
0.34 | 18 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Van Hai Do | 1 | 18 | 4.09 |
| Xiong Xiao | 2 | 281 | 34.97 |
| haihua xu | 3 | 26 | 2.72 |
| Eng Siong Chng | 4 | 970 | 106.33 |
| Haizhou Li | 5 | 3678 | 334.61 |