Deep learning microphone array speech enhancement for multiple speaker separation
With the increase of human-computer voice interaction scenes in recent years, using microphone array speech enhancement to improve speech quality has become one of the research hotspots. Different from the ambient noise, the interfering speaker′s speech and the target speaker are the same speech sig...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | Chinese |
| Published: |
National Computer System Engineering Research Institute of China
2022-05-01
|
| Series: | Dianzi Jishu Yingyong |
| Subjects: | |
| Online Access: | http://www.chinaaet.com/article/3000149429 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839639514241302528 |
|---|---|
| author | Zhang Jiayang Tong Feng Chen Dongsheng Huang Huixiang |
| author_facet | Zhang Jiayang Tong Feng Chen Dongsheng Huang Huixiang |
| author_sort | Zhang Jiayang |
| collection | DOAJ |
| description | With the increase of human-computer voice interaction scenes in recent years, using microphone array speech enhancement to improve speech quality has become one of the research hotspots. Different from the ambient noise, the interfering speaker′s speech and the target speaker are the same speech signal in the multiple speaker separation scene, showing similar time-frequency characteristics, which poses a higher challenge to the traditional microphone array speech enhancement technology. For the multiple speaker separation scenario, the spatial response cost function of microphone array is constructed and optimized based on deep learning network. The desired spatial transmission characteristics of microphone array are designed through deep learning model training, so as to improve the separation effect by improving the beamforming performance. Simulation and experimental results show that this method effectively improves the performance of multiple speaker separation. |
| format | Article |
| id | doaj-art-2f4345c44e4d4e6f9c38a5fac0087d16 |
| institution | Matheson Library |
| issn | 0258-7998 |
| language | zho |
| publishDate | 2022-05-01 |
| publisher | National Computer System Engineering Research Institute of China |
| record_format | Article |
| series | Dianzi Jishu Yingyong |
| spelling | doaj-art-2f4345c44e4d4e6f9c38a5fac0087d162025-07-04T08:29:17ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982022-05-01485313610.16157/j.issn.0258-7998.2124043000149429Deep learning microphone array speech enhancement for multiple speaker separationZhang Jiayang0Tong Feng1Chen Dongsheng2Huang Huixiang3Key Laboratory of Underwater Acoustic Communication and Marine Information Technology Ministry of Education， Xiamen University，Xiamen 361005，ChinaKey Laboratory of Underwater Acoustic Communication and Marine Information Technology Ministry of Education， Xiamen University，Xiamen 361005，ChinaKey Laboratory of Underwater Acoustic Communication and Marine Information Technology Ministry of Education， Xiamen University，Xiamen 361005，ChinaKey Laboratory of Underwater Acoustic Communication and Marine Information Technology Ministry of Education， Xiamen University，Xiamen 361005，ChinaWith the increase of human-computer voice interaction scenes in recent years, using microphone array speech enhancement to improve speech quality has become one of the research hotspots. Different from the ambient noise, the interfering speaker′s speech and the target speaker are the same speech signal in the multiple speaker separation scene, showing similar time-frequency characteristics, which poses a higher challenge to the traditional microphone array speech enhancement technology. For the multiple speaker separation scenario, the spatial response cost function of microphone array is constructed and optimized based on deep learning network. The desired spatial transmission characteristics of microphone array are designed through deep learning model training, so as to improve the separation effect by improving the beamforming performance. Simulation and experimental results show that this method effectively improves the performance of multiple speaker separation.http://www.chinaaet.com/article/3000149429deep learningmicrophone arraybeamforminglstm |
| spellingShingle | Zhang Jiayang Tong Feng Chen Dongsheng Huang Huixiang Deep learning microphone array speech enhancement for multiple speaker separation Dianzi Jishu Yingyong deep learning microphone array beamforming lstm |
| title | Deep learning microphone array speech enhancement for multiple speaker separation |
| title_full | Deep learning microphone array speech enhancement for multiple speaker separation |
| title_fullStr | Deep learning microphone array speech enhancement for multiple speaker separation |
| title_full_unstemmed | Deep learning microphone array speech enhancement for multiple speaker separation |
| title_short | Deep learning microphone array speech enhancement for multiple speaker separation |
| title_sort | deep learning microphone array speech enhancement for multiple speaker separation |
| topic | deep learning microphone array beamforming lstm |
| url | http://www.chinaaet.com/article/3000149429 |
| work_keys_str_mv | AT zhangjiayang deeplearningmicrophonearrayspeechenhancementformultiplespeakerseparation AT tongfeng deeplearningmicrophonearrayspeechenhancementformultiplespeakerseparation AT chendongsheng deeplearningmicrophonearrayspeechenhancementformultiplespeakerseparation AT huanghuixiang deeplearningmicrophonearrayspeechenhancementformultiplespeakerseparation |