Parallel processing of distributed beamforming and multichannel linear prediction for speech denoising and deverberation in wireless acoustic sensor networks

EURASIP Journal on Audio, Speech, and Music Processing

Methodology

Yuxuan Ke¹  Zhe Han²  Xiaodong Li²  Chengshi Zheng² 

[1] Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, 100190, Beijing, China;Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, 100190, Beijing, China;University of Chinese Academy of Sciences, 100049, Beijing, China;

关键词: Wireless acoustic sensor networks;    Speech enhancement;    Microphone arrays;   

DOI  :  10.1186/s13636-023-00287-6

 received in 2022-02-25, accepted in 2023-04-21,  发布年份 2023

来源: Springer

【 摘 要 】

More and more smart home devices with microphones come into our life in these years; it is highly desirable to connect these microphones as wireless acoustic sensor networks (WASNs) so that these devices can be better controlled in an enclosure. For indoor applications, both environmental noise and room reverberation may severely degrade speech quality, and thus both of them need to be removed to improve users’ experience. For this goal, this paper proposes a parallel processing framework of distributed beamforming and multichannel linear prediction (DB-BFMCLP), which consists of generalized sidelobe canceler and multichannel linear prediction for simultaneous speech dereverberation and noise reduction in WASNs. By sharing a common desired response vector, the proposed DB-BFMCLP can provide a significant reduction in communication bandwidth without sacrificing performance. The convergence guarantee of the DB-BFMCLP to its centralized implementation is derived mathematically. Simulation results verify the superiority of the proposed method to the existing related methods in noisy and reverberant scenarios.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

42004_2023_897_Article_IEq31.gif

Fig. 4

40517_2023_256_Article_IEq132.gif

Fig. 21

42004_2023_897_Article_IEq24.gif

40517_2023_256_Article_IEq129.gif

40517_2023_256_Article_IEq128.gif

42004_2023_897_Article_IEq20.gif

42004_2023_897_Article_IEq18.gif

42004_2023_897_Article_IEq16.gif

Fig. 20

Fig. 2

Fig. 1

Fig. 1

41512_2023_147_Article_IEq110.gif

Fig. 19

Fig. 4

40517_2023_256_Article_IEq121.gif

Fig. 5

40517_2023_256_Article_IEq120.gif

Fig. 18

40517_2023_256_Article_IEq119.gif

Fig. 3

40517_2023_256_Article_IEq118.gif

Fig. 17

41512_2023_147_Article_IEq107.gif

40517_2023_256_Article_IEq116.gif

Fig. 16

40517_2023_256_Article_IEq115.gif

40517_2023_256_Article_IEq114.gif

Fig. 2

40517_2023_256_Article_IEq113.gif

Fig. 5

Fig. 14

Fig. 1

Fig. 1

Fig. 1

40517_2023_256_Article_IEq110.gif

Fig. 5

40517_2023_256_Article_IEq109.gif

Fig. 1

40517_2023_256_Article_IEq108.gif

Fig. 5

40517_2023_256_Article_IEq107.gif

Fig. 4

40517_2023_256_Article_IEq106.gif

40517_2023_256_Article_IEq105.gif

Fig. 2

40517_2023_256_Article_IEq103.gif

40517_2023_256_Article_IEq102.gif

Fig. 3

40517_2023_256_Article_IEq101.gif

Fig. 2

Fig. 10

40517_2023_256_Article_IEq99.gif

Fig. 3

40517_2023_256_Article_IEq98.gif

40854_2023_494_Article_IEq2.gif

Fig. 1

Fig. 2

41512_2023_147_Article_IEq89.gif

40517_2023_256_Article_IEq87.gif

40517_2023_256_Article_IEq86.gif

40517_2023_256_Article_IEq85.gif

Fig. 4

40517_2023_256_Article_IEq83.gif

Fig. 13

40517_2023_256_Article_IEq81.gif

Fig. 12

Fig. 2

Fig. 3

40517_2023_256_Article_IEq79.gif

Fig. 7

40517_2023_256_Article_IEq78.gif

Fig. 1

40517_2023_256_Article_IEq77.gif

Fig. 11

40517_2023_256_Article_IEq76.gif

Fig. 10

Fig. 1

40517_2023_256_Article_IEq74.gif

Fig. 9

40517_2023_256_Article_IEq73.gif

Fig. 9

Fig. 8

Fig. 5

Fig. 7

Fig. 3

Fig. 1

Fig. 6

Fig. 2

Fig. 1

Fig. 1

41512_2023_147_Article_IEq71.gif

Fig. 4

40517_2023_256_Article_IEq64.gif

40517_2023_256_Article_IEq62.gif

Fig. 1

Fig. 3

13731_2023_296_Article_IEq2.gif

40517_2023_256_Article_IEq60.gif

40517_2023_256_Article_IEq59.gif

Fig. 3

Fig. 4

40517_2023_256_Article_IEq55.gif

Fig. 3

Fig. 3

Fig. 2

40517_2023_256_Article_IEq53.gif

Fig. 2

40517_2023_256_Article_IEq52.gif

40517_2023_256_Article_IEq51.gif

Fig. 2

12888_2023_4880_Article_IEq1.gif

Fig. 1

Fig. 1

40517_2023_256_Article_IEq47.gif

Fig. 3

Fig. 7

Fig. 2

Fig. 6

Fig. 4

Fig. 1

40517_2023_256_Article_IEq39.gif

40517_2023_256_Article_IEq38.gif

12936_2023_4577_Article_IEq66.gif

40517_2023_256_Article_IEq35.gif

40517_2023_256_Article_IEq34.gif

Fig. 1

40517_2023_256_Article_IEq33.gif

Fig. 2

40517_2023_258_Article_IEq68.gif

40517_2023_258_Article_IEq138.gif

40517_2023_258_Article_IEq137.gif

Fig. 8

40517_2023_258_Article_IEq135.gif

Fig. 1

40517_2023_258_Article_IEq133.gif

40517_2023_258_Article_IEq132.gif

40517_2023_258_Article_IEq131.gif

40517_2023_258_Article_IEq130.gif

40517_2023_258_Article_IEq129.gif

40517_2023_258_Article_IEq128.gif

40517_2023_258_Article_IEq127.gif

40517_2023_258_Article_IEq126.gif

40517_2023_258_Article_IEq125.gif

Fig. 2

Fig. 1

41116_2023_36_Article_IEq818.gif

Fig. 1

41116_2023_36_Article_IEq789.gif

Fig. 2

41116_2023_36_Article_IEq768.gif

41116_2023_36_Article_IEq757.gif

41116_2023_36_Article_IEq754.gif

41116_2023_36_Article_IEq749.gif

41116_2023_36_Article_IEq747.gif

41116_2023_36_Article_IEq744.gif

41116_2023_36_Article_IEq737.gif

Fig. 1

41116_2023_36_Article_IEq734.gif

41116_2023_36_Article_IEq733.gif

41116_2023_36_Article_IEq731.gif

41116_2023_36_Article_IEq692.gif

41116_2023_36_Article_IEq689.gif

41116_2023_36_Article_IEq688.gif

41116_2023_36_Article_IEq667.gif

41116_2023_36_Article_IEq649.gif

41116_2023_36_Article_IEq615.gif

41116_2023_36_Article_IEq501.gif

Fig. 7

Fig. 2

41116_2023_36_Article_IEq497.gif

41116_2023_36_Article_IEq483.gif

Fig. 3

41116_2023_36_Article_IEq456.gif

41116_2023_36_Article_IEq438.gif

41116_2023_36_Article_IEq425.gif

41116_2023_36_Article_IEq408.gif

41116_2023_36_Article_IEq375.gif