Model-based voice activity detection in wireless acoustic sensor networks

Yingke Zhao, Jesper Kjær Nielsen, Mads Græsbøll Christensen, Jingdong Chen

科研成果: 书/报告/会议事项章节会议稿件同行评审

2 引用 (Scopus)

摘要

One of the major challenges in wireless acoustic sensor networks (WASN) based speech enhancement is robust and accurate voice activity detection (VAD). VAD is widely used in speech enhancement, speech coding, speech recognition, etc. In speech enhancement applications, VAD plays an important role, since noise statistics can be updated during non-speech frames to ensure efficient noise reduction and tolerable speech distortion. Although significant efforts have been made in single channel VAD, few solutions can be found in the multichannel case, especially in WASN. In this paper, we introduce a distributed VAD by using model-based noise power spectral density (PSD) estimation. For each node in the network, the speech PSD and noise PSD are first estimated, then a distributed detection is made by applying the generalized likelihood ratio test (GLRT). The proposed global GLRT based VAD has a quite general form. Indeed, we can judge whether the speech is present or absent by using the current time frame and frequency band observation or by taking into account the neighbouring frames and bands. Finally, the distributed GLRT result is obtained by using a distributed consensus method, such as random gossip, i.e., the whole detection system does not need any fusion center. With the model-based noise estimation method, the proposed distributed VAD performs robustly under non-stationary noise conditions, such as babble noise. As shown in experiments, the proposed method outperforms traditional multichannel VAD methods in terms of detection accuracy.

源语言英语
主期刊名2018 26th European Signal Processing Conference, EUSIPCO 2018
出版商European Signal Processing Conference, EUSIPCO
425-429
页数5
ISBN(电子版)9789082797015
DOI
出版状态已出版 - 29 11月 2018
活动26th European Signal Processing Conference, EUSIPCO 2018 - Rome, 意大利
期限: 3 9月 20187 9月 2018

出版系列

姓名European Signal Processing Conference
2018-September
ISSN(印刷版)2219-5491

会议

会议26th European Signal Processing Conference, EUSIPCO 2018
国家/地区意大利
Rome
时期3/09/187/09/18

指纹

探究 'Model-based voice activity detection in wireless acoustic sensor networks' 的科研主题。它们共同构成独一无二的指纹。

引用此