Keyword spotting system for broadcast news
A two-step keyword spotting strategy was presented.This strategy allowed to change keyword list conven-iently.Different from the previous systems,search space was generated based on all Chinese syllables,not specifically for keywords.Phoneme recognition was performed without any lexical constraints....
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2007-01-01
|
| Series: | Tongxin xuebao |
| Online Access: | http://www.joconline.com.cn/thesisDetails?columnId=74658803&Fpath=home&index=0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | A two-step keyword spotting strategy was presented.This strategy allowed to change keyword list conven-iently.Different from the previous systems,search space was generated based on all Chinese syllables,not specifically for keywords.Phoneme recognition was performed without any lexical constraints.With 1-best phoneme sequence and keyword list,which generated keyword hypotheses.At last,two confidence measures were introduced adopted in the sys-tem: one based on acoustic model and the other based on phoneme lattice.For a decoded speech frame aligned to an HMM state,the acoustic confidence was calculated.The lattice confidence made use of phoneme lattices generated by a phoneme recognizer.These two confidence measures were combined using a weighting factor to obtain a hybrid confi-dence as they had different dynamic scales.Experiments show that the proposed algorithms significantly improve the system performance on the broadcast news task. |
|---|---|
| ISSN: | 1000-436X |