Deep Learning-Based Acoustic Echo Cancellation for Surround Sound Systems
Surround sound systems that play back multi-channel audio signals through multiple loudspeakers can improve augmented reality, which has been widely used in many multimedia communication systems. It is common that a hand-free speech communication system suffers from the acoustic echo problem, and th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/3/1266 |
| _version_ | 1797625238730571776 |
|---|---|
| author | Guoteng Li Chengshi Zheng Yuxuan Ke Xiaodong Li |
| author_facet | Guoteng Li Chengshi Zheng Yuxuan Ke Xiaodong Li |
| author_sort | Guoteng Li |
| collection | DOAJ |
| description | Surround sound systems that play back multi-channel audio signals through multiple loudspeakers can improve augmented reality, which has been widely used in many multimedia communication systems. It is common that a hand-free speech communication system suffers from the acoustic echo problem, and the echo needs to be canceled or suppressed completely. This paper proposes a deep learning-based acoustic echo cancellation (AEC) method to recover the desired near-end speech from the microphone signals in surround sound systems. The ambisonics technique was adopted to record the surround sound for reproduction. To achieve a better generalization capability against different loudspeaker layouts, the compressed complex spectra of the first-order ambisonic signals (B-format) were sent to the neural network as the input features directly instead of using the ambisonic decoded signals (D-format). Experimental results on both simulated and real acoustic environments showed the effectiveness of the proposed algorithm in surround AEC, and outperformed other competing methods in terms of the speech quality and the amount of echo reduction. |
| first_indexed | 2024-03-11T09:53:44Z |
| format | Article |
| id | doaj.art-21c9b2b46da544d4b77a3a28db5299eb |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:53:44Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-21c9b2b46da544d4b77a3a28db5299eb2023-11-16T16:02:58ZengMDPI AGApplied Sciences2076-34172023-01-01133126610.3390/app13031266Deep Learning-Based Acoustic Echo Cancellation for Surround Sound SystemsGuoteng Li0Chengshi Zheng1Yuxuan Ke2Xiaodong Li3Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaSurround sound systems that play back multi-channel audio signals through multiple loudspeakers can improve augmented reality, which has been widely used in many multimedia communication systems. It is common that a hand-free speech communication system suffers from the acoustic echo problem, and the echo needs to be canceled or suppressed completely. This paper proposes a deep learning-based acoustic echo cancellation (AEC) method to recover the desired near-end speech from the microphone signals in surround sound systems. The ambisonics technique was adopted to record the surround sound for reproduction. To achieve a better generalization capability against different loudspeaker layouts, the compressed complex spectra of the first-order ambisonic signals (B-format) were sent to the neural network as the input features directly instead of using the ambisonic decoded signals (D-format). Experimental results on both simulated and real acoustic environments showed the effectiveness of the proposed algorithm in surround AEC, and outperformed other competing methods in terms of the speech quality and the amount of echo reduction.https://www.mdpi.com/2076-3417/13/3/1266acoustic echo cancellationsurround soundambisonics |
| spellingShingle | Guoteng Li Chengshi Zheng Yuxuan Ke Xiaodong Li Deep Learning-Based Acoustic Echo Cancellation for Surround Sound Systems Applied Sciences acoustic echo cancellation surround sound ambisonics |
| title | Deep Learning-Based Acoustic Echo Cancellation for Surround Sound Systems |
| title_full | Deep Learning-Based Acoustic Echo Cancellation for Surround Sound Systems |
| title_fullStr | Deep Learning-Based Acoustic Echo Cancellation for Surround Sound Systems |
| title_full_unstemmed | Deep Learning-Based Acoustic Echo Cancellation for Surround Sound Systems |
| title_short | Deep Learning-Based Acoustic Echo Cancellation for Surround Sound Systems |
| title_sort | deep learning based acoustic echo cancellation for surround sound systems |
| topic | acoustic echo cancellation surround sound ambisonics |
| url | https://www.mdpi.com/2076-3417/13/3/1266 |
| work_keys_str_mv | AT guotengli deeplearningbasedacousticechocancellationforsurroundsoundsystems AT chengshizheng deeplearningbasedacousticechocancellationforsurroundsoundsystems AT yuxuanke deeplearningbasedacousticechocancellationforsurroundsoundsystems AT xiaodongli deeplearningbasedacousticechocancellationforsurroundsoundsystems |