Noise-robust linear prediction analysis of speech based on super-Gaussian excitation
To overcome the problem that the performance of the traditional linear prediction (LP) analysis of speech dete-riorates significantly in the presence of background noise,a novel algorithm for robust LP analysis of speech based on super-Gaussian excitation was proposed.The excitation noise of LP was...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2013-05-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2013.05.007/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539855730868224 |
|---|---|
| author | Bin ZHOU Xia ZOU Xiong-wei ZHANG Gai-hua ZHAO |
| author_facet | Bin ZHOU Xia ZOU Xiong-wei ZHANG Gai-hua ZHAO |
| author_sort | Bin ZHOU |
| collection | DOAJ |
| description | To overcome the problem that the performance of the traditional linear prediction (LP) analysis of speech dete-riorates significantly in the presence of background noise,a novel algorithm for robust LP analysis of speech based on super-Gaussian excitation was proposed.The excitation noise of LP was modeled as a Student-t distribution,which was shown to be super-Gaussian.Then a novel probabilistic graphical model for robust LP analysis of speech was built by in-corporating the effect of additive noise explicitly.Furthermore,variational Bayesian inference was adopted to approxi-mate the intractable posterior distributions of the model parameters,based on which the LP coefficients of the noisy speech were estimated iteratively.The experimental results show that the developed algorithm performs well in terms of LP coefficients estimation of speech and is much more robust to ambient noise than several other algorithms. |
| format | Article |
| id | doaj-art-fac547115e6d4b7f9afc3c1509dc9f4b |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2013-05-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-fac547115e6d4b7f9afc3c1509dc9f4b2025-01-14T06:35:15ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2013-05-0134526159672041Noise-robust linear prediction analysis of speech based on super-Gaussian excitationBin ZHOUXia ZOUXiong-wei ZHANGGai-hua ZHAOTo overcome the problem that the performance of the traditional linear prediction (LP) analysis of speech dete-riorates significantly in the presence of background noise,a novel algorithm for robust LP analysis of speech based on super-Gaussian excitation was proposed.The excitation noise of LP was modeled as a Student-t distribution,which was shown to be super-Gaussian.Then a novel probabilistic graphical model for robust LP analysis of speech was built by in-corporating the effect of additive noise explicitly.Furthermore,variational Bayesian inference was adopted to approxi-mate the intractable posterior distributions of the model parameters,based on which the LP coefficients of the noisy speech were estimated iteratively.The experimental results show that the developed algorithm performs well in terms of LP coefficients estimation of speech and is much more robust to ambient noise than several other algorithms.http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2013.05.007/linear prediction of speechnoise-robustsuper-Gaussian excitationvariational Bayes |
| spellingShingle | Bin ZHOU Xia ZOU Xiong-wei ZHANG Gai-hua ZHAO Noise-robust linear prediction analysis of speech based on super-Gaussian excitation Tongxin xuebao linear prediction of speech noise-robust super-Gaussian excitation variational Bayes |
| title | Noise-robust linear prediction analysis of speech based on super-Gaussian excitation |
| title_full | Noise-robust linear prediction analysis of speech based on super-Gaussian excitation |
| title_fullStr | Noise-robust linear prediction analysis of speech based on super-Gaussian excitation |
| title_full_unstemmed | Noise-robust linear prediction analysis of speech based on super-Gaussian excitation |
| title_short | Noise-robust linear prediction analysis of speech based on super-Gaussian excitation |
| title_sort | noise robust linear prediction analysis of speech based on super gaussian excitation |
| topic | linear prediction of speech noise-robust super-Gaussian excitation variational Bayes |
| url | http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2013.05.007/ |
| work_keys_str_mv | AT binzhou noiserobustlinearpredictionanalysisofspeechbasedonsupergaussianexcitation AT xiazou noiserobustlinearpredictionanalysisofspeechbasedonsupergaussianexcitation AT xiongweizhang noiserobustlinearpredictionanalysisofspeechbasedonsupergaussianexcitation AT gaihuazhao noiserobustlinearpredictionanalysisofspeechbasedonsupergaussianexcitation |