Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition
Original eigenphone speaker adaptation method performed well when the amount of adaptation data was suffi-cient.However,it suffered from server overfitting when insufficient amount of adaptation data was provided.A sparse group LASSO(SGL) constraint eigenphone speaker adaptation method was proposed....
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2015-09-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2015241/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539693151256576 |
|---|---|
| author | Dan QU Wen-lin ZHANG |
| author_facet | Dan QU Wen-lin ZHANG |
| author_sort | Dan QU |
| collection | DOAJ |
| description | Original eigenphone speaker adaptation method performed well when the amount of adaptation data was suffi-cient.However,it suffered from server overfitting when insufficient amount of adaptation data was provided.A sparse group LASSO(SGL) constraint eigenphone speaker adaptation method was proposed.Firstly,the principle of eigenphone speaker adaptation was introduced in case of hidden Markov model-Gaussian mixture model (HMM-GMM) based speech recognition system.Then,a sparse group LASSO was applied to estimation of the eigenphone matrix.The weight of the SGL norm was adjusted to control the complexity of the adaptation model.Finally,an accelerated proximal gradient method was adopted to solve the mathematic optimization.The method was compared with up-to-date norm algorithms.Experiments on an mandarin Chinese continuous speech recognition task show that,the performance of the SGL con-straint eigenphone method can improve remarkably the performance of the system than original eigenphone method,and is also superior to l<sub>1</sub>、l<sub>2</sub>-norm and elastic net constraint methods. |
| format | Article |
| id | doaj-art-dfbd35826d684af080a4585b24c681d4 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2015-09-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-dfbd35826d684af080a4585b24c681d42025-01-14T06:53:30ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2015-09-0136475459695277Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognitionDan QUWen-lin ZHANGOriginal eigenphone speaker adaptation method performed well when the amount of adaptation data was suffi-cient.However,it suffered from server overfitting when insufficient amount of adaptation data was provided.A sparse group LASSO(SGL) constraint eigenphone speaker adaptation method was proposed.Firstly,the principle of eigenphone speaker adaptation was introduced in case of hidden Markov model-Gaussian mixture model (HMM-GMM) based speech recognition system.Then,a sparse group LASSO was applied to estimation of the eigenphone matrix.The weight of the SGL norm was adjusted to control the complexity of the adaptation model.Finally,an accelerated proximal gradient method was adopted to solve the mathematic optimization.The method was compared with up-to-date norm algorithms.Experiments on an mandarin Chinese continuous speech recognition task show that,the performance of the SGL con-straint eigenphone method can improve remarkably the performance of the system than original eigenphone method,and is also superior to l<sub>1</sub>、l<sub>2</sub>-norm and elastic net constraint methods.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2015241/speaker adaptationeigenphonegroup sparse constraintsparse group LASSO constraintproximal gradient method |
| spellingShingle | Dan QU Wen-lin ZHANG Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition Tongxin xuebao speaker adaptation eigenphone group sparse constraint sparse group LASSO constraint proximal gradient method |
| title | Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition |
| title_full | Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition |
| title_fullStr | Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition |
| title_full_unstemmed | Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition |
| title_short | Sparse group LASSO constraint eigenphone speaker adaptation method for speech recognition |
| title_sort | sparse group lasso constraint eigenphone speaker adaptation method for speech recognition |
| topic | speaker adaptation eigenphone group sparse constraint sparse group LASSO constraint proximal gradient method |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2015241/ |
| work_keys_str_mv | AT danqu sparsegrouplassoconstrainteigenphonespeakeradaptationmethodforspeechrecognition AT wenlinzhang sparsegrouplassoconstrainteigenphonespeakeradaptationmethodforspeechrecognition |