Bind Subband Beamforming with Time-delay Constraints for Moving Source Speech Enhancement

Document type: Journal Articles
Article type: Original article
Peer reviewed: Yes
Author(s): Zohra Yermeche, Nedelko Grbic, Ingvar Claesson
Title: Bind Subband Beamforming with Time-delay Constraints for Moving Source Speech Enhancement
Journal: IEEE Transactions on Audio Speech and Language processing
Year: 2007
Volume: 15
Issue: 8
Pagination: 2360-2372 
ISSN: 1558-7916
Publisher: IEEE
ISI number: 000250282800016
Organization: Blekinge Institute of Technology
Department: School of Engineering - Dept. of Signal Processing (Sektionen för teknik – avd. för signalbehandling)
School of Engineering S- 372 25 Ronneby
+46 455 38 50 00
Language: English
Abstract: A new robust microphone array method to enhance speech signals generated by a moving person in a noisy environment is presented. This blind approach is based on a two-stage scheme. First, a subband time-delay estimation method is used to localize the dominant speech source. The second stage involves speech enhancement, based on the acquired spatial information, by means of a soft-constrained subband beamformer. The novelty of the proposed method involves considering the spatial spreading of the sound source as equivalent to a time-delay spreading, thus, allowing for the estimated intersensor time-delays to be directly used in the beamforming operations. In comparison to previous approaches, this new method requires no special array geometry, knowledge of the array manifold, or acquisition of calibration data to adapt the array weights. Furthermore, such a scheme allows for the beamformer to efficiently adapt to speaker movement. The robustness of the time-delay estimation of speech signals in high noise levels is improved by making use of the non-Gaussian nature of speech trough a subband Kurtosis-weighted structure. Evaluation in a real environment with a moving speaker shows promising results, with suppression levels of up to 16 dB for background noise and interfering (speech) signals, associated to a relatively small effect of speech distortion.
Subject: Signal Processing\Beamforming
Signal Processing\Speech Enhancement
Keywords: array signal processing, delay estimation, speech enhancement