Name
Abstract | ||
|---|---|---|
In this paper we report our approaches to accomplishing the very limited resource keyword search (KWS) task in the NIST Open Keyword Search 2015 (OpenKWS15) Evaluation. We devised the methods, first, to attain better acoustic modeling, multilingual and semi-supervised acoustic model training as well as the examplar-based acoustic model training; second, to address the overwhelming out-of-vocabulary (OOV) KWS issue. Finally, we proposed a neural network (NN) framework to fuse diversified component systems, yielding improved combination results. Experimental results demonstrated the effectiveness of these approaches. |
Year | Venue | Keywords |
|---|---|---|
2015 | Asia-Pacific Signal and Information Processing Association Annual Summit and Conference | speech recognition,low-resource,keyword search,multilingual training,semi-supervised training,system fusion |
Field | DocType | ISSN |
Computer science,Keyword search,Feature extraction,Speech recognition,NIST,Artificial neural network,Hidden Markov model,Fuse (electrical),Acoustic model | Conference | 2309-9402 |
Citations | PageRank | References |
2 | 0.36 | 24 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Van Tung Pham | 1 | 40 | 8.42 |
| Haihua Xu | 2 | 55 | 11.41 |
| Van Hai Do | 3 | 18 | 4.09 |
| Tze Yuang Chong | 4 | 9 | 3.59 |
| Xiong Xiao | 5 | 281 | 34.97 |
| Eng Siong Chng | 6 | 970 | 106.33 |
| Haizhou Li | 7 | 3678 | 334.61 |