Linearized distortion model for robust speech recognition in noisy environments
The robustness of speech recognition system in noisy environments was investigated.The distortion model in Mel-frequency cepstral coefficient（MFCC） domain is highly non-linear and difficult to deal with.A new linear distortion model was proposed by replacing the logarithm operation with its piecewis...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2010-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/74646863/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841537732272193536 |
|---|---|
| author | HE Yong-jun1 HAN Ji-qing1 |
| author_facet | HE Yong-jun1 HAN Ji-qing1 |
| author_sort | HE Yong-jun1 |
| collection | DOAJ |
| description | The robustness of speech recognition system in noisy environments was investigated.The distortion model in Mel-frequency cepstral coefficient（MFCC） domain is highly non-linear and difficult to deal with.A new linear distortion model was proposed by replacing the logarithm operation with its piecewise linear interpolation function.Then the esti-mation of noise parameters and compensation of acoustic models were provided.The proposed method can avoid model error introduced by utilizing linearization methods based on vector Taylor series（VTS） expansion,and significantly im-prove the robustness of recognizer in noisy environments. |
| format | Article |
| id | doaj-art-73eca6eab91a40edbfd6a4a723f5c05e |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2010-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-73eca6eab91a40edbfd6a4a723f5c05e2025-01-14T08:24:38ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2010-01-013181474646863Linearized distortion model for robust speech recognition in noisy environmentsHE Yong-jun1HAN Ji-qing1The robustness of speech recognition system in noisy environments was investigated.The distortion model in Mel-frequency cepstral coefficient（MFCC） domain is highly non-linear and difficult to deal with.A new linear distortion model was proposed by replacing the logarithm operation with its piecewise linear interpolation function.Then the esti-mation of noise parameters and compensation of acoustic models were provided.The proposed method can avoid model error introduced by utilizing linearization methods based on vector Taylor series（VTS） expansion,and significantly im-prove the robustness of recognizer in noisy environments.http://www.joconline.com.cn/zh/article/74646863/speech recognitionrobustnessdistortion modellinearization |
| spellingShingle | HE Yong-jun1 HAN Ji-qing1 Linearized distortion model for robust speech recognition in noisy environments Tongxin xuebao speech recognition robustness distortion model linearization |
| title | Linearized distortion model for robust speech recognition in noisy environments |
| title_full | Linearized distortion model for robust speech recognition in noisy environments |
| title_fullStr | Linearized distortion model for robust speech recognition in noisy environments |
| title_full_unstemmed | Linearized distortion model for robust speech recognition in noisy environments |
| title_short | Linearized distortion model for robust speech recognition in noisy environments |
| title_sort | linearized distortion model for robust speech recognition in noisy environments |
| topic | speech recognition robustness distortion model linearization |
| url | http://www.joconline.com.cn/zh/article/74646863/ |
| work_keys_str_mv | AT heyongjun1 linearizeddistortionmodelforrobustspeechrecognitioninnoisyenvironments AT hanjiqing1 linearizeddistortionmodelforrobustspeechrecognitioninnoisyenvironments |