About: A Conditional Generative Model for Speech Enhancement

Not logged in : Login

(Sponging disallowed)

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

About: A Conditional Generative Model for Speech Enhancement Goto Sponge NotDistinct Permalink

An Entity of Type : bibo:AcademicArticle, within Data Space : linkeddata.uriburner.com:28898 associated with source document(s)

Attributes	Values
type	http://eprints.org/ontology/ArticleEPrint http://eprints.org/ontology/EPrint Article Academic Article
seeAlso	HTML Summary of #66126 A Conditional Generative Model for Speech Enhancement
sameAs	A Conditional Generative Model for Speech Enhancement
http://eprints.org/ontology/hasAccepted	A Conditional Generative Model for Speech Enhancement (PDF)
http://eprints.org/ontology/hasDocument	A Conditional Generative Model for Speech Enhancement (Other) A Conditional Generative Model for Speech Enhancement (Other) A Conditional Generative Model for Speech Enhancement (Other) A Conditional Generative Model for Speech Enhancement (Other) A Conditional Generative Model for Speech Enhancement (PDF) A Conditional Generative Model for Speech Enhancement (Other)
dc:hasVersion	A Conditional Generative Model for Speech Enhancement (PDF)
Title	A Conditional Generative Model for Speech Enhancement
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	2018-03-13
Creator	Yan Song Li-Rong Dai Zheng-xi Li I. McLoughlin
status	peer reviewed published
Publisher	Springer
abstract	Deep learning based speech enhancement approaches like Deep Neural Networks (DNN) and Long-Short Term Memory (LSTM) have already demonstrated superior results to classical methods. However these methods do not take full advantage of temporal context information. While DNN and LSTM consider temporal context in the noisy source speech, it does not do so for the estimated clean speech. Both DNN and LSTM also have a tendency to over-smooth spectra, which causes the enhanced speech to sound muffled. This paper proposes a novel architecture to address both issues, which we term a conditional generative model (CGM). By adopting an adversarial training scheme applied to a generator of deep dilated convolutional layers, CGM is designed to model the joint and symmetric conditions of both noisy and estimated clean spectra.We evaluate CGM against both DNN and LSTM in terms of Perceptual Evaluation of Speech Quality (PESQ) and Short-Time Objective Intelligibility (STOI) on TIMIT sentences corrupted by ITU-T P.501 and NOISEX-92 noise in a range of matched and mismatched noise conditions. Results show that both the CGM architecture and the adversarial training mechanism lead to better PESQ and STOI in all tested noise conditions. In addition to yielding significant improvements in PESQ and STOI, CGM and adversarial training both mitigate against over-smoothing.
Is Part Of	Circuits, Systems, and Signal Processing https://kar.kent.ac.uk/id/repository
Subject	T Technology
list of authors	https://kar.kent.ac.uk/id/eprint/66126#authors
volume	37
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 #66126 A Conditional Generative Model for Speech Enhancement

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, 14 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software