A Hybrid Design Of Beamformers For Voice Control Devices

Document type: Journal Articles
Article type: Original article
Peer reviewed: Yes
Author(s): K. F. C Yiu, K. Y Chan, Nedelko Grbic, Sven Nordholm
Title: A Hybrid Design Of Beamformers For Voice Control Devices
Journal: Pacific Journal of Optimization
Year: 2012
Volume: 8
Issue: 3
Pagination: 533-544
ISSN: 1348-9151
Publisher: Yokohama publishing
ISI number: 000307426100010
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: In this paper, a new approach to designing beamformers for voice control device is proposed. It is well-known that under a strong near-field noise with low signal-to-noise ratios (SNR), the performance of speech recognition is deteriorated significantly. However, designing the beamformer for enhancing speech recognition is a slow process and might not be adapted easily to the changing noise environment. In order to lower the complexity of the design, we intend to exploit the combination of existing optimal beamformer designs, which can be implemented in parallel. These include the least-squares technique and the signal-to-noise ratio maximization technique. We show here that for a given pre-trained speech recognizer and for a finite set of speech commands, neither method has a satisfactory performance in speech recognition accuracy under very low SNRs. However, since the two techniques have different characteristics in speech distortion and noise suppression, we show that it is possible to enhance the speech recognition accuracy by combining these two optimal designs.
Subject: Signal Processing\General
Signal Processing\Beamforming
Keywords: beamformer, microphone array, multi-channel filter, signal enhancement, speech recognition, noise reduction