NDLI: Binary spectral masking for speech recognition systems

Content Provider	IEEE Xplore Digital Library
Author	de Souza Siqueira Versiani, T. Rodrigues, G.F. de Souza, A.C.S. de Matos Moreira, J. Yehia, H.C.
Copyright Year	2012
Description	Author affiliation: Federal University of São João del-Rey, Ouro Branco, Minas Gerais, Brazil (de Souza Siqueira Versiani, T.) \|\| Department of Telecommunications and Mechatronic Engineering, Federal University São João del-Rey, Ouro Branco, Minas Gerais, Brazil (de Souza, A.C.S.) \|\| Department of Telecommunications and Mechatronic Engineering, Federal University of São João del-Rey, Ouro Branco, Minas Gerais, Brazil (Rodrigues, G.F.) \|\| Department of Mathematic, Federal University of Minas Gerais, Belo Horizonte, Brazil (de Matos Moreira, J.) \|\| Department of Electronic Engineering, Federal University of Minas Gerais, Belo Horizonte, Brazil (Yehia, H.C.)
Abstract	The purpose of this paper is to examine the use of spectral masking techniques as a preprocessing step in speech recognition systems. The limits of these masking techniques for different levels of the signal-to-noise ratio are discussed. In general, speech recognition systems have low performance in noisy environments or in the presence of other speech signals. This work presents a blind source separation system based on ideal binary masks to deal with real situations in which speech signals are corrupted by noise, including other speech signals. The main contribution of this work is to analyze the performance limits of recognition systems using spectral masking. We obtain an increase of 18 % on the speech hit rate and an average gain of 10 dB in terms of noise level attenuation, when the speech signals were corrupted by other voice signals, with different signal-to-noise ratio of approximately 1, 10 and 20 dB.
Starting Page	432
Ending Page	436
File Size	1291623
Page Count	5
File Format	PDF
ISBN	9781467311175
e-ISBN	9781467311182
DOI	10.1109/TSP.2012.6256330
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2012-07-03
Publisher Place	Czech Republic
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Spectral masking Neural networks Speech recognition Independent component analysis White noise Speech Time frequency analysis Blind source separation Speech processing Signal to noise ratio
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Blind Source Separation Based on a Beamformer Array and Time Frequency Binary Masking

Underdetermined Convolutive Blind Source Separation via Time–Frequency Masking

Two-stage blind source separation based on ICA and binary masking for real-time robot audition system

Blind Separation of Noisy Mixed Speech Based on Independent Component Analysis and Neural Network

Applications of Wavelet to Independent Component Analysis

Two-Microphone Separation of Speech Mixtures

Speech source separation and noise reduction using a MMSE short-time spectral amplitude estimator

Overcomplete blind source separation by combining ICA and binary time-frequency masking (2005)

A Speech Enhancement System Using Binary Mask Approach and Spectral Subtraction Method

Binary spectral masking for speech recognition systems

Similar Documents

Blind Source Separation Based on a Beamformer Array and Time Frequency Binary Masking

Underdetermined Convolutive Blind Source Separation via Time–Frequency Masking

Two-stage blind source separation based on ICA and binary masking for real-time robot audition system

Blind Separation of Noisy Mixed Speech Based on Independent Component Analysis and Neural Network

Applications of Wavelet to Independent Component Analysis

Two-Microphone Separation of Speech Mixtures

Speech source separation and noise reduction using a MMSE short-time spectral amplitude estimator

Overcomplete blind source separation by combining ICA and binary time-frequency masking (2005)

A Speech Enhancement System Using Binary Mask Approach and Spectral Subtraction Method

Binary spectral masking for speech recognition systems