TY - GEN
T1 - Multiple fixed beamformers with a spacial Wiener-form postfilter for far-field speech recognition
AU - Sun, Sining
AU - Zhou, Shuran
AU - Hwang, Mei Yuh
AU - Xie, Lei
AU - Li, Qin
AU - Lei, Xin
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Far-field speech recognition is becoming a hot topic in research and industrial applications. In this paper, in order to improve far-field speech recognition performance, we propose to use multiple fixed beamformers with a spacial Wiener-form postfilter (MFB-SWP) to suppress noise and interference. Our proposed method consists of two parts, beamforming and post-filter estimation. First, multiple fixed beamformers are designed and each of them aims at one specific direction. Next the target speech is estimated using the fixed beamformer aiming to the target direction, and the noise and interference signals are estimated using the remaining beamformers. After that, we calculate a spacial Wiener-form time-frequency and frame-level gains, as postfilter to further reduce the residual noise and interference. Compared with a single fixed beamformer, the proposed MFB-SWP method can suppress noise and interference significantly. It is also computationally more efficient comparing with other adaptive beamforming methods. Our experiments showed that proposed method achieved 16-50% relative character error rate (CER) reduction compared with using the single fixed beamformer only.
AB - Far-field speech recognition is becoming a hot topic in research and industrial applications. In this paper, in order to improve far-field speech recognition performance, we propose to use multiple fixed beamformers with a spacial Wiener-form postfilter (MFB-SWP) to suppress noise and interference. Our proposed method consists of two parts, beamforming and post-filter estimation. First, multiple fixed beamformers are designed and each of them aims at one specific direction. Next the target speech is estimated using the fixed beamformer aiming to the target direction, and the noise and interference signals are estimated using the remaining beamformers. After that, we calculate a spacial Wiener-form time-frequency and frame-level gains, as postfilter to further reduce the residual noise and interference. Compared with a single fixed beamformer, the proposed MFB-SWP method can suppress noise and interference significantly. It is also computationally more efficient comparing with other adaptive beamforming methods. Our experiments showed that proposed method achieved 16-50% relative character error rate (CER) reduction compared with using the single fixed beamformer only.
KW - Far-field speech recognition
KW - Fixed beamformer
KW - MFB-SWP
KW - Spacial Wiener postfilter
UR - http://www.scopus.com/inward/record.url?scp=85082384756&partnerID=8YFLogxK
U2 - 10.1109/APSIPAASC47483.2019.9023131
DO - 10.1109/APSIPAASC47483.2019.9023131
M3 - 会议稿件
AN - SCOPUS:85082384756
T3 - 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
SP - 633
EP - 637
BT - 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
Y2 - 18 November 2019 through 21 November 2019
ER -