Real-time blind source separation system with applications to distant speech recognition

详细信息    查看全文

• 作者：Alberto E.A. Ferreira^a ; Diogo Alarcã ; o^b ; ^{diogo.alarcao@tecnico.ulisboa.pt" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Blind source separation ; Distant speech recognition ; DUET
• 刊名：Applied Acoustics
• 出版年：2016
• 出版时间：1 December 2016
• 年：2016
• 卷：113
• 期：Complete
• 页码：170-184
• 全文大小：2495 K

文摘

A real-time BSS system based on DUET was developed and implemented in order to assess its potential as the front-end for a DSR engine. The system uses only two closely-spaced standard omni-directional microphones and a computer soundcard and was developed for low reverberation environments with several human speakers and different noise sources.

sp010">A novel multi-source real-time audio streaming module was developed, with arbitrary statistics, movement tracking, continuity cues such as position and cross-correlation, a spurious peak classifier stage based on kurtosis, and spectral subtraction post-processing.

sp015">Two intrinsic error causes for the binaural attenuation and delay estimators were identified, due to FFT spectral leakage and to sibilants, which violate the taken for granted DUET assumptions. A comprehensive study on time windows was done and new window types proposed in order to minimize the DUET assumptions violations.

sp020">The implemented system correctly identifies the clusters in the binaural estimators’ space for the case of a real room with two human speakers, up to distances of 2 m from the two microphones, although for distances greater than 1 m the separation quality quickly degrades.