An Utilizing of Spectral Mask to Enhance GSC Beamformer

The 11th Conference on Information Technology and its Applications; Topic: Network and Communications; pp.511-519.

Saved in:
Bibliographic Details
Main Authors: Pham, Tuan Anh, Dang, Dai Tho, Quan, Trong The, Nguyen, Ba Huy
Format: Bài viết
Language:English
Published: Da Nang Publishing House 2022
Subjects:
Online Access:http://elib.vku.udn.vn/handle/123456789/2319
Tags: Add Tag
No Tags, Be the first to tag this record!
Institutions: Trường Đại học Công nghệ Thông tin và Truyền thông Việt Hàn - Đại học Đà Nẵng
id oai:elib.vku.udn.vn:123456789-2319
record_format dspace
spelling oai:elib.vku.udn.vn:123456789-23192023-09-25T01:22:57Z An Utilizing of Spectral Mask to Enhance GSC Beamformer Pham, Tuan Anh Dang, Dai Tho Quan, Trong The Nguyen, Ba Huy Microphone array beamforming Generalized Sidelobe Canceller speech enhancement noise reduction the reference signal spectral mask The 11th Conference on Information Technology and its Applications; Topic: Network and Communications; pp.511-519. Speech source separation is always a complex problem when the recording situation has interference, unwanted noise, transport vehicle or third-party talker. Without any assumed information about source, it is very difficult to separate useful signal. Nowadays, there has been a several approaches to extract target directional speech. This technology, which use microphone array to utilize the microphone placement and speaker location, named beamformer. Generalized Sidelobe Canceller (GSC) Beamformer is one of the most popular method for remov- ing interfering noise and achieve desired signal with high speech quality. However, its performance is always degraded due to many reasons, such as the different microphone sensitivities, microphone mismatches, the error of the direction of arrival (DOA). In this paper, the author presented a spectral mask, which uses the instantaneous value of the signal-to-noise SNR for enhancing GSC's evaluation in presence of complicated noise. The developed spectral mask is based on the assumption of the amount of speech leakage is proportional with the ratio SNR, the higher SNR, the smaller spectral mask. The performed experiment was verified and confirmed of this approach through the numerical results of the SNR from 2.0 (dB) to 6.9 (dB). The proposed method, which provides us an efficient solution to deal realistic speech task with microphone array, can be integrated into multi-microphone system with arbitrary geometry or distribution of microphones. 2022-08-17T02:29:02Z 2022-08-17T02:29:02Z 2022-07 Working Paper 978-604-84-6711-1 http://elib.vku.udn.vn/handle/123456789/2319 en application/pdf Da Nang Publishing House
institution Trường Đại học Công nghệ Thông tin và Truyền thông Việt Hàn - Đại học Đà Nẵng
collection DSpace
language English
topic Microphone array
beamforming
Generalized Sidelobe Canceller
speech enhancement
noise reduction
the reference signal
spectral mask
spellingShingle Microphone array
beamforming
Generalized Sidelobe Canceller
speech enhancement
noise reduction
the reference signal
spectral mask
Pham, Tuan Anh
Dang, Dai Tho
Quan, Trong The
Nguyen, Ba Huy
An Utilizing of Spectral Mask to Enhance GSC Beamformer
description The 11th Conference on Information Technology and its Applications; Topic: Network and Communications; pp.511-519.
format Working Paper
author Pham, Tuan Anh
Dang, Dai Tho
Quan, Trong The
Nguyen, Ba Huy
author_facet Pham, Tuan Anh
Dang, Dai Tho
Quan, Trong The
Nguyen, Ba Huy
author_sort Pham, Tuan Anh
title An Utilizing of Spectral Mask to Enhance GSC Beamformer
title_short An Utilizing of Spectral Mask to Enhance GSC Beamformer
title_full An Utilizing of Spectral Mask to Enhance GSC Beamformer
title_fullStr An Utilizing of Spectral Mask to Enhance GSC Beamformer
title_full_unstemmed An Utilizing of Spectral Mask to Enhance GSC Beamformer
title_sort utilizing of spectral mask to enhance gsc beamformer
publisher Da Nang Publishing House
publishDate 2022
url http://elib.vku.udn.vn/handle/123456789/2319
_version_ 1849201113244368896