A hybrid design of beamformers for voice control devices

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 enhanci...

Full description

Bibliographic Details
Main Authors: Yiu, K., Chan, Kit Yan, Grbić, N., Nordholm, Sven
Format: Journal Article
Published: Yokohama Publishers 2012
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/34974
_version_ 1848754369763213312
author Yiu, K.
Chan, Kit Yan
Grbić, N.
Nordholm, Sven
author_facet Yiu, K.
Chan, Kit Yan
Grbić, N.
Nordholm, Sven
author_sort Yiu, K.
building Curtin Institutional Repository
collection Online Access
description 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.
first_indexed 2025-11-14T08:39:19Z
format Journal Article
id curtin-20.500.11937-34974
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:39:19Z
publishDate 2012
publisher Yokohama Publishers
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-349742017-01-30T13:46:52Z A hybrid design of beamformers for voice control devices Yiu, K. Chan, Kit Yan Grbić, N. Nordholm, Sven speech recognition microphone array multi-channel filter beamformer signal enhancement noise reduction 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. 2012 Journal Article http://hdl.handle.net/20.500.11937/34974 Yokohama Publishers restricted
spellingShingle speech recognition
microphone array
multi-channel filter
beamformer
signal enhancement
noise reduction
Yiu, K.
Chan, Kit Yan
Grbić, N.
Nordholm, Sven
A hybrid design of beamformers for voice control devices
title A hybrid design of beamformers for voice control devices
title_full A hybrid design of beamformers for voice control devices
title_fullStr A hybrid design of beamformers for voice control devices
title_full_unstemmed A hybrid design of beamformers for voice control devices
title_short A hybrid design of beamformers for voice control devices
title_sort hybrid design of beamformers for voice control devices
topic speech recognition
microphone array
multi-channel filter
beamformer
signal enhancement
noise reduction
url http://hdl.handle.net/20.500.11937/34974