Please use this identifier to cite or link to this item:
Title: A Spectral Mask - Based on Method for Applying into Generalized Sidelobe Canceller Beamformer
Authors: Nguyen, Ba Huy
Pham, Tuan Anh
Quan, Trong The
Keywords: Generalized Sidelobe Canceller
microphone array
noise reduction
the speech quality
the signal-to-noise ratio
beamforming technique
Issue Date: Jul-2023
Publisher: Springer Nature
Abstract: The problem of signal processing is extracting the desired target speaker while suppressing the annoying background noise in complex recording situation, where exists third-party talker, transport vehicle or interference, noise. Speech quality or speech intelligibility are the major characteristics, which confirm the effectiveness of processed method. In speech applications, such as hearing-aids, hands-free telephony, teleconferencing, acoustic instruments, microphone array (MA) is applied for increasing the speech quality. MA uses the spatial response, the priori information about direction - of - arrival (DOA) of interest signal, the properties of recording environment to obtain speech components and remove noise. Generalized Sidelobe Canceller (GSC) is one of the most widely exploited in microphone array beamforming, due to its convenience and effective noise reduction. However, in several situations, the performance of GSC beamformer is often degraded, because of the imprecise DOA. In this paper, the authors suggested an additive spectral mask for improving the evaluation of GSC beamformer. The resulting experiment proves the received advantage of the author’s proposed algorithm to increase in the term of the signal-to-noise ratio (SNR).
Description: Lecture Notes in Networks and Systems (LNNS, volume 734); CITA: Conference on Information Technology and its Applications; pp: 332-341.
ISBN: 978-3-031-36886-8
Appears in Collections:CITA 2023 (International)

Files in This Item:

 Sign in to read

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.