A front-end speech enhancement system for robust automotive speech recognition

Haikun Wang, Zhongfu Ye, 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

This paper presents a front-end speech enhancement approach to robust speech recognition in automotive environments. It combines model-based voice activity detection (VAD), relative transfer function (RTF) based generalized sidelobe cancelation, and single-channel post filtering to enhance the speech signal of interest, thereby improving the robustness of speech recognition. First, we choose four typical driving scenarios, which include most of the noise types in automobiles to record training data. The recorded data are then used to train Gaussian mixture models (GMMs) for both speech and noise. The trained GMMs are subsequently used to estimate the speech presence probability on a frame-by-frame basis. This speech presence probability is then served as the basic information for RTF estimation, adaptive beamforming, and post-filtering.Experiments are conducted in real automotive environments and the results show that the developed method can significantly improve the performance of both VAD and automatic speech recognition (ASR).

源语言英语
主期刊名2018 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
1-5
页数5
ISBN(电子版)9781538656273
DOI
出版状态已出版 - 2 7月 2018
活动11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Taipei, 中国台湾
期限: 26 11月 201829 11月 2018

出版系列

姓名2018 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018 - Proceedings

会议

会议11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018
国家/地区中国台湾
Taipei
时期26/11/1829/11/18

指纹

探究 'A front-end speech enhancement system for robust automotive speech recognition' 的科研主题。它们共同构成独一无二的指纹。

引用此