Head-related transfer function–reserved time-frequency masking for robust binaural sound source localization

CAAI Transactions on Intelligence Technology

article

Hong Liu¹  Peipei Yuan¹  Bing Yang¹  Ge Yang²  Yang Chen³ 

[1] Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University;School of Artificial Intelligence, Chongqing University of Technology;Yanka Kupala State University of Grodno

关键词: speech processing;    reverberation;    acoustic signal processing;    transfer functions;    deep learning (artificial intelligence);    convolutional neural nets;   

DOI  :  10.1049/cit2.12010

学科分类：数学（综合）

来源: Wiley

【 摘 要 】

Various time-frequency (T-F) masks are being applied to sound source localization tasks. Moreover, deep learning has dramatically advanced T-F mask estimation. However, existing masks are usually designed for speech separation tasks and are suitable only for single-channel signals. A novel complex-valued T-F mask is proposed that reserves the head-related transfer function (HRTF), customized for binaural sound source localization. In addition, because the convolutional neural network that is exploited to estimate the proposed mask takes binaural spectral information as the input and output, accurate binaural cues can be preserved. Compared with conventional T-F masks that emphasize single speech source–dominated T-F units, HRTF-reserved masks eliminate the speech component while keeping the direct propagation path. Thus, the estimated HRTF is capable of extracting more reliable localization features for the final direction of arrival estimation. Hence, binaural sound source localization guided by the proposed T-F mask is robust under noisy and reverberant acoustic environments. The experimental results demonstrate that the new T-F mask is superior to conventional T-F masks and lead to the better performance of sound source localization in adverse environments.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND