Task domain independent speech keyword detection system
A multiple scale acoustic modeling framework for task-domain independent keyword spotting was proposed.A large-scale phoneme set was obtained automatically through decision-tree based phoneme clustering,and a large-scale phoneme acoustic context dependent background model was trained accordingly thr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2006-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/74666266/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841537324346769408 |
|---|---|
| author | HAN Jiang LIU Xiao-xing YAN Yong-hong ZHANG Peng-yuan |
| author_facet | HAN Jiang LIU Xiao-xing YAN Yong-hong ZHANG Peng-yuan |
| author_sort | HAN Jiang |
| collection | DOAJ |
| description | A multiple scale acoustic modeling framework for task-domain independent keyword spotting was proposed.A large-scale phoneme set was obtained automatically through decision-tree based phoneme clustering,and a large-scale phoneme acoustic context dependent background model was trained accordingly through using standard HMM training framework.The modeling accuracy for filler speech is improved.Under the framework,an efficient searching space construction through using shared HMM state was also described.Experimental results showed that in average absolute 6.9% improvement of keyword recognition accuracy could be obtained.Furthermore an acoustic context neighbor algorithm to measure acoustic confidence and a method of computing candidate keyword likelihood based on proposed multiple-scale acoustic model were proposed and a fusing method based on FLDA was adopted.The effectiveness of acoustic confidence measure is improved significantly.Experimental results showed that absolute 3.0% reduction of equal error rate could be obtained. |
| format | Article |
| id | doaj-art-659314b904e0486f8356606ad56e94db |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2006-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-659314b904e0486f8356606ad56e94db2025-01-14T08:39:39ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2006-01-0113714174666266Task domain independent speech keyword detection systemHAN JiangLIU Xiao-xingYAN Yong-hongZHANG Peng-yuanA multiple scale acoustic modeling framework for task-domain independent keyword spotting was proposed.A large-scale phoneme set was obtained automatically through decision-tree based phoneme clustering,and a large-scale phoneme acoustic context dependent background model was trained accordingly through using standard HMM training framework.The modeling accuracy for filler speech is improved.Under the framework,an efficient searching space construction through using shared HMM state was also described.Experimental results showed that in average absolute 6.9% improvement of keyword recognition accuracy could be obtained.Furthermore an acoustic context neighbor algorithm to measure acoustic confidence and a method of computing candidate keyword likelihood based on proposed multiple-scale acoustic model were proposed and a fusing method based on FLDA was adopted.The effectiveness of acoustic confidence measure is improved significantly.Experimental results showed that absolute 3.0% reduction of equal error rate could be obtained.http://www.joconline.com.cn/zh/article/74666266/acoustic confidence measuremultiple scale acoustic modelingsearching space |
| spellingShingle | HAN Jiang LIU Xiao-xing YAN Yong-hong ZHANG Peng-yuan Task domain independent speech keyword detection system Tongxin xuebao acoustic confidence measure multiple scale acoustic modeling searching space |
| title | Task domain independent speech keyword detection system |
| title_full | Task domain independent speech keyword detection system |
| title_fullStr | Task domain independent speech keyword detection system |
| title_full_unstemmed | Task domain independent speech keyword detection system |
| title_short | Task domain independent speech keyword detection system |
| title_sort | task domain independent speech keyword detection system |
| topic | acoustic confidence measure multiple scale acoustic modeling searching space |
| url | http://www.joconline.com.cn/zh/article/74666266/ |
| work_keys_str_mv | AT hanjiang taskdomainindependentspeechkeyworddetectionsystem AT liuxiaoxing taskdomainindependentspeechkeyworddetectionsystem AT yanyonghong taskdomainindependentspeechkeyworddetectionsystem AT zhangpengyuan taskdomainindependentspeechkeyworddetectionsystem |