NDLI: Block-online multi-channel speech enhancement using deep neural network-supported relative transfer function estimates

Content Provider	IET Digital Library
Author	Malek, Jiri Koldovský, Zbynĕk Bohac, Marek
Abstract	This work addresses the problem of block-online processing for multi-channel speech enhancement. Such processing is vital in scenarios with moving speakers and/or when short utterances are processed, e.g. in voice assistant applications. We consider several variants of a system that performs beamforming supported by deep neural network-based voice activity detection followed by post-filtering. The speaker is targeted through estimating relative transfer functions between microphones. Each block of the input signals is processed independently to make the method applicable in highly dynamic environments. Due to short processed blocks, the statistics required by the beamformer are estimated less precisely. The influence of this inaccuracy is studied and compared to batch processing regime, when recordings are treated as one block. The experimental evaluation is performed on large datasets of CHiME-4 and another dataset featuring moving target speaker. The experiments are evaluated in terms of objective and perceptual criteria. Moreover, word error rate (WER) of a speech recognition system is evaluated, for which the method serves as a front-end. The results indicate that the proposed method is robust for short length of the processed block. Significant improvements in terms of the criteria and WER are observed even for the block length of 250 ms.
Starting Page	124
Ending Page	133
Page Count	10
ISSN	17519675
Volume Number	14
e-ISSN	17519683
Issue Number	Issue 3, May (2020)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-spr/14/3
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-spr.2019.0304
Journal	IET Signal Processing
Publisher Date	2019-12-19
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Array Signal Processing Baseline Automatic Speech Recognition System Batch Processing Block Length Block-online Multichannel Speech Enhancement Block-online Processing Deep Neural Network-based Voice Activity Detection Deep Neural Network-supported Relative Transfer Function Estimate Enhancement Method Highly Dynamic Environments Neural Computing Technique Neural Nets Perceptual Evaluation Processed Block Processing Regime Relative Transfer Function Short Utterances Speech Enhancement Speech Processing Technique Speech Quality Speech Recognition Speech Recognition And Synthesis Time 250.0 Ms Transfer Function Voice Assistant Scenario
Content Type	Text
Resource Type	Article
Subject	Signal Processing Electrical and Electronic Engineering

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

Speech Magnitude Spectrum Reconstruction from MFCCs Using Deep Neural Network

Deep neural network-based linear predictive parameter estimations for speech enhancement

Improving speech enhancement by focusing on smaller values using relative loss

Distributed multichannel speech enhancement based on perceptually-motivated Bayesian estimators of the spectral amplitude

Learning deep features to recognise speech emotion using merged deep CNN

Multichannel speech enhancement using convolutive transfer function approximation in reverberant environments

Ideal neighbourhood mask for speech enhancement

Artificial bandwidth extension using deep neural network-based spectral envelope estimation and enhanced excitation estimation

Experiments on far-field multichannel speech processing in smart homes.

Block-online multi-channel speech enhancement using deep neural network-supported relative transfer function estimates

Similar Documents

Speech Magnitude Spectrum Reconstruction from MFCCs Using Deep Neural Network

Deep neural network-based linear predictive parameter estimations for speech enhancement

Improving speech enhancement by focusing on smaller values using relative loss

Distributed multichannel speech enhancement based on perceptually-motivated Bayesian estimators of the spectral amplitude

Learning deep features to recognise speech emotion using merged deep CNN

Multichannel speech enhancement using convolutive transfer function approximation in reverberant environments

Ideal neighbourhood mask for speech enhancement

Artificial bandwidth extension using deep neural network-based spectral envelope estimation and enhanced excitation estimation

Experiments on far-field multichannel speech processing in smart homes.

Block-online multi-channel speech enhancement using deep neural network-supported relative transfer function estimates