Name
Abstract | ||
|---|---|---|
This paper applies relevance feedback technique in spoken language recognition task, in which we consider a test utterance as a test query. Assuming that we have a labeled multilingual corpus, we exploit the retrieved utterances from such a reference corpus to automatically augment the test query. Note that successful spoken language recognition relies on sufficient query data. The proposed method is especially effective for short query by expanding the query at a low cost. Experiments show that unsupervised relevance feedback reduces the relative equal-error-rate by 16.2%, 4.9% and 10.2% on NIST LRE 1996, 2003 and 2005 databases respectively for 3-second trials. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/ICASSP.2007.367206 | ICASSP (4) |
Keywords | Field | DocType |
vector space model,speech recognition,spoken language recognition,labeled multilingual corpus,testing,test utterance,relevance feedback,relative equal-error-rate,feedback,support vector machines,databases,nist,natural languages,information retrieval | Query language,Relevance feedback,Computer science,Web query classification,Utterance,Artificial intelligence,Natural language processing,Spoken language,RDF query language,Query expansion,Pattern recognition,Speech recognition,Natural language | Conference |
Volume | ISSN | ISBN |
4 | 1520-6149 E-ISBN : 1-4244-0728-1 | 1-4244-0728-1 |
Citations | PageRank | References |
1 | 0.35 | 4 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rong Tong | 1 | 108 | 11.33 |
| Haizhou Li | 2 | 3678 | 334.61 |
| Bin Ma | 3 | 600 | 47.26 |
| Eng Siong Chng | 4 | 970 | 106.33 |
| Siu-Yeung Cho | 5 | 465 | 39.83 |