About: Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation

Not logged in : Login

(Sponging disallowed)

Facets (new session)
Description
Metadata
Settings
- Rule:
- Inverse Functional Properties:
- "Same As":

About: Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation Goto Sponge NotDistinct Permalink

An Entity of Type : bibo:AcademicArticle, within Data Space : demo.openlinksw.com associated with source document(s)

Attributes	Values
type	http://eprints.org/ontology/ConferenceItemEPrint http://eprints.org/ontology/EPrint Article Academic Article
seeAlso	HTML Summary of #67161 Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation
sameAs	Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation
http://eprints.org/ontology/hasAccepted	Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation (PDF)
http://eprints.org/ontology/hasDocument	Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation (PDF) Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation (Other) Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation (Other) Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation (Other) Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation (Other) Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation (Other)
dc:hasVersion	Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation (PDF)
Title	Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation
described by	https://demo.openlinksw.com/about/id/entity/https/www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/export_kar_RDFN3.n3 https://demo.openlinksw.com/about/id/entity/https/raw.githubusercontent.com/annajordanous/CO644Files/main/export_kar_RDFN3.n3
Date	2018-09-13
Creator	Li-Rong Dai Zengxi Li Yan Song I. McLoughlin
status	peer reviewed published
Publisher	IEEE
abstract	Deep learning based approaches have achieved promising performance in speaker-dependent single-channel multi-speaker speech separation.However, partly due to the label permutation problem, they may encounter difficulties in speaker-independent conditions. Recent methods address this problem by some assignment operations. Different from them, we propose a novel source-aware context network, which explicitly inputs speech sources as well as mixture signal. By exploiting the temporal dependency and continuity of the same source signal, the permutation order of outputs can be easily determined without any additional post-processing. Furthermore, a Multi-time-step Prediction Training strategy is proposed to address the mismatch between training and inference stages. Experimental results on benchmark WSJ0-2mix dataset revealed that our network achieved comparable or better results than state-of-the-art methods in both closed-set and open-set conditions, in terms of Signal-to-Distortion Ratio (SDR) improvement.
Is Part Of	https://kar.kent.ac.uk/id/repository
Subject	T Technology
list of authors	https://kar.kent.ac.uk/id/eprint/67161#authors
presented at	2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
is topic of	https://www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/export_kar_RDFN3.n3 https://raw.githubusercontent.com/annajordanous/CO644Files/main/export_kar_RDFN3.n3
is primary topic of	HTML Summary of #67161 Source-Aware Context Network for Single-Channel Multi-speaker Speech Separation

Faceted Search & Find service v1.17_git144 as of Jul 26 2024

Alternative Linked Data Documents: iSPARQL | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 08.03.3331 as of Aug 25 2024, on Linux (x86_64-ubuntu_noble-linux-glibc2.38-64), Single-Server Edition (378 GB total memory, 31 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software