Speech Separation Using Convolutional Neural Network and Attention Mechanism
Speech information is the most important means of human communication, and it is crucial to separate the target voice from the mixed sound signals. This paper proposes a speech separation model based on convolutional neural networks and attention mechanism. The magnitude spectrum of the mixed speech...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Discrete Dynamics in Nature and Society |
| Online Access: | http://dx.doi.org/10.1155/2020/2196893 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832566232302223360 |
|---|---|
| author | Chun-Miao Yuan Xue-Mei Sun Hu Zhao |
| author_facet | Chun-Miao Yuan Xue-Mei Sun Hu Zhao |
| author_sort | Chun-Miao Yuan |
| collection | DOAJ |
| description | Speech information is the most important means of human communication, and it is crucial to separate the target voice from the mixed sound signals. This paper proposes a speech separation model based on convolutional neural networks and attention mechanism. The magnitude spectrum of the mixed speech signals, as the input, has its high dimensionality. By analyzing the characteristics of the convolutional neural network and attention mechanism, it can be found that the convolutional neural network can effectively extract low-dimensional features and mine the spatiotemporal structure information in the speech signals, and the attention mechanism can reduce the loss of sequence information. The accuracy of speech separation can be improved effectively by combining two mechanisms. Compared to the typical speech separation model DRNN-2 + discrim, this method achieves 0.27 dB GNSDR gain and 0.51 dB GSIR gain, which illustrates that the speech separation model proposed in this paper has achieved an ideal separation effect. |
| format | Article |
| id | doaj-art-c5b71d75a44b42daaa0de1388bf01d6b |
| institution | Kabale University |
| issn | 1026-0226 1607-887X |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Discrete Dynamics in Nature and Society |
| spelling | doaj-art-c5b71d75a44b42daaa0de1388bf01d6b2025-02-03T01:04:48ZengWileyDiscrete Dynamics in Nature and Society1026-02261607-887X2020-01-01202010.1155/2020/21968932196893Speech Separation Using Convolutional Neural Network and Attention MechanismChun-Miao Yuan0Xue-Mei Sun1Hu Zhao2School of Computer Science and Technology, TianGong University, Tianjin 300387, ChinaSchool of Computer Science and Technology, TianGong University, Tianjin 300387, ChinaSchool of Computer Science and Technology, TianGong University, Tianjin 300387, ChinaSpeech information is the most important means of human communication, and it is crucial to separate the target voice from the mixed sound signals. This paper proposes a speech separation model based on convolutional neural networks and attention mechanism. The magnitude spectrum of the mixed speech signals, as the input, has its high dimensionality. By analyzing the characteristics of the convolutional neural network and attention mechanism, it can be found that the convolutional neural network can effectively extract low-dimensional features and mine the spatiotemporal structure information in the speech signals, and the attention mechanism can reduce the loss of sequence information. The accuracy of speech separation can be improved effectively by combining two mechanisms. Compared to the typical speech separation model DRNN-2 + discrim, this method achieves 0.27 dB GNSDR gain and 0.51 dB GSIR gain, which illustrates that the speech separation model proposed in this paper has achieved an ideal separation effect.http://dx.doi.org/10.1155/2020/2196893 |
| spellingShingle | Chun-Miao Yuan Xue-Mei Sun Hu Zhao Speech Separation Using Convolutional Neural Network and Attention Mechanism Discrete Dynamics in Nature and Society |
| title | Speech Separation Using Convolutional Neural Network and Attention Mechanism |
| title_full | Speech Separation Using Convolutional Neural Network and Attention Mechanism |
| title_fullStr | Speech Separation Using Convolutional Neural Network and Attention Mechanism |
| title_full_unstemmed | Speech Separation Using Convolutional Neural Network and Attention Mechanism |
| title_short | Speech Separation Using Convolutional Neural Network and Attention Mechanism |
| title_sort | speech separation using convolutional neural network and attention mechanism |
| url | http://dx.doi.org/10.1155/2020/2196893 |
| work_keys_str_mv | AT chunmiaoyuan speechseparationusingconvolutionalneuralnetworkandattentionmechanism AT xuemeisun speechseparationusingconvolutionalneuralnetworkandattentionmechanism AT huzhao speechseparationusingconvolutionalneuralnetworkandattentionmechanism |