InforLorV4, Main, Exploration, bibRecord, 000372

Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR

Identifieur interne : 000372 ( Main/Exploration ); précédent : 000371; suivant : 000373

Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR

Auteurs : Felix Weninger [Allemagne] ; Hakan Erdogan [États-Unis] ; Shinji Watanabe [États-Unis] ; Emmanuel Vincent [France] ; Jonathan Le Roux [États-Unis] ; John R. Hershey [États-Unis] ; Björn Schuller [Royaume-Uni]

Source :

RBID : Hal:hal-01163493

Abstract

We evaluate some recent developments in recurrent neural network (RNN) based speech enhancement in the light of noise-robust automatic speech recognition (ASR). The proposed framework is based on Long Short-Term Memory (LSTM) RNNs which are discriminatively trained according to an optimal speech reconstruction objective. We demonstrate that LSTM speech enhancement, even when used ' na¨vely ' as front-end processing, delivers competitive results on the CHiME-2 speech recognition task. Furthermore, simple, feature-level fusion based extensions to the framework are proposed to improve the integration with the ASR back-end. These yield a best result of 13.76 % average word error rate, which is, to our knowledge, the best score to date.

Url:

https://hal.inria.fr/hal-01163493

Affiliations:

Links toward previous steps (curation, corpus...)

to stream Hal, to step Corpus: 004740
to stream Hal, to step Curation: 004740
to stream Hal, to step Checkpoint: 000348
to stream Main, to step Merge: 000372
to stream Main, to step Curation: 000372

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR</title>
<author><name sortKey="Weninger, Felix" sort="Weninger, Felix" uniqKey="Weninger F" first="Felix" last="Weninger">Felix Weninger</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-139341" status="INCOMING"><orgName>Technische Universität München</orgName>
<desc><address><country key="DE"></country>
</address>
</desc>
<listRelation><relation active="#struct-301140" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-301140" type="direct"><org type="institution" xml:id="struct-301140" status="VALID"><orgName>Technische Universität München [München]</orgName>
<orgName type="acronym">TUM</orgName>
<desc><address><addrLine>Arcisstraße 21, 80333 München</addrLine>
<country key="DE"></country>
</address>
<ref type="url">http://www.tum.de/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>Allemagne</country>
</affiliation>
</author>
<author><name sortKey="Erdogan, Hakan" sort="Erdogan, Hakan" uniqKey="Erdogan H" first="Hakan" last="Erdogan">Hakan Erdogan</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-89592" status="VALID"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<orgName type="acronym">MERL</orgName>
<desc><address><addrLine>Mitsubishi Electric Research Laboratories Cambridge MA 02139</addrLine>
<country key="US"></country>
</address>
<ref type="url">http://www.merl.com/</ref>
</desc>
<listRelation><relation active="#struct-322337" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-322337" type="direct"><org type="institution" xml:id="struct-322337" status="INCOMING"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Watanabe, Shinji" sort="Watanabe, Shinji" uniqKey="Watanabe S" first="Shinji" last="Watanabe">Shinji Watanabe</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-89592" status="VALID"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<orgName type="acronym">MERL</orgName>
<desc><address><addrLine>Mitsubishi Electric Research Laboratories Cambridge MA 02139</addrLine>
<country key="US"></country>
</address>
<ref type="url">http://www.merl.com/</ref>
</desc>
<listRelation><relation active="#struct-322337" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-322337" type="direct"><org type="institution" xml:id="struct-322337" status="INCOMING"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Vincent, Emmanuel" sort="Vincent, Emmanuel" uniqKey="Vincent E" first="Emmanuel" last="Vincent">Emmanuel Vincent</name>
<affiliation wicri:level="1"><hal:affiliation type="researchteam" xml:id="struct-420403" status="VALID"><idno type="RNSR">201421147E</idno>
<orgName>Speech Modeling for Facilitating Oral-Based Communication</orgName>
<orgName type="acronym">MULTISPEECH</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/multispeech</ref>
</desc>
<listRelation><relation active="#struct-129671" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno>
<orgName>INRIA Nancy - Grand Est</orgName>
<desc><address><addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/nancy</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="ISNI">0000000122597504</idno>
<idno type="IdRef">02636817X</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">Nancy</settlement>
<settlement type="city">Metz</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="university">Université de Lorraine</orgName>
</affiliation>
</author>
<author><name sortKey="Le Roux, Jonathan" sort="Le Roux, Jonathan" uniqKey="Le Roux J" first="Jonathan" last="Le Roux">Jonathan Le Roux</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-89592" status="VALID"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<orgName type="acronym">MERL</orgName>
<desc><address><addrLine>Mitsubishi Electric Research Laboratories Cambridge MA 02139</addrLine>
<country key="US"></country>
</address>
<ref type="url">http://www.merl.com/</ref>
</desc>
<listRelation><relation active="#struct-322337" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-322337" type="direct"><org type="institution" xml:id="struct-322337" status="INCOMING"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Hershey, John R" sort="Hershey, John R" uniqKey="Hershey J" first="John R." last="Hershey">John R. Hershey</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-89592" status="VALID"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<orgName type="acronym">MERL</orgName>
<desc><address><addrLine>Mitsubishi Electric Research Laboratories Cambridge MA 02139</addrLine>
<country key="US"></country>
</address>
<ref type="url">http://www.merl.com/</ref>
</desc>
<listRelation><relation active="#struct-322337" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-322337" type="direct"><org type="institution" xml:id="struct-322337" status="INCOMING"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Schuller, Bjorn" sort="Schuller, Bjorn" uniqKey="Schuller B" first="Björn" last="Schuller">Björn Schuller</name>
<affiliation wicri:level="1"><hal:affiliation type="institution" xml:id="struct-69530" status="VALID"><orgName>Imperial College London</orgName>
<desc><address><addrLine>Imperial College London, South Kensington Campus, London SW7 2AZ</addrLine>
<country key="GB"></country>
</address>
<ref type="url">http://www3.imperial.ac.uk/</ref>
</desc>
</hal:affiliation>
<country>Royaume-Uni</country>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:hal-01163493</idno>
<idno type="halId">hal-01163493</idno>
<idno type="halUri">https://hal.inria.fr/hal-01163493</idno>
<idno type="url">https://hal.inria.fr/hal-01163493</idno>
<date when="2015-08-25">2015-08-25</date>
<idno type="wicri:Area/Hal/Corpus">004740</idno>
<idno type="wicri:Area/Hal/Curation">004740</idno>
<idno type="wicri:Area/Hal/Checkpoint">000348</idno>
<idno type="wicri:explorRef" wicri:stream="Hal" wicri:step="Checkpoint">000348</idno>
<idno type="wicri:Area/Main/Merge">000372</idno>
<idno type="wicri:Area/Main/Curation">000372</idno>
<idno type="wicri:Area/Main/Exploration">000372</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR</title>
<author><name sortKey="Weninger, Felix" sort="Weninger, Felix" uniqKey="Weninger F" first="Felix" last="Weninger">Felix Weninger</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-139341" status="INCOMING"><orgName>Technische Universität München</orgName>
<desc><address><country key="DE"></country>
</address>
</desc>
<listRelation><relation active="#struct-301140" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-301140" type="direct"><org type="institution" xml:id="struct-301140" status="VALID"><orgName>Technische Universität München [München]</orgName>
<orgName type="acronym">TUM</orgName>
<desc><address><addrLine>Arcisstraße 21, 80333 München</addrLine>
<country key="DE"></country>
</address>
<ref type="url">http://www.tum.de/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>Allemagne</country>
</affiliation>
</author>
<author><name sortKey="Erdogan, Hakan" sort="Erdogan, Hakan" uniqKey="Erdogan H" first="Hakan" last="Erdogan">Hakan Erdogan</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-89592" status="VALID"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<orgName type="acronym">MERL</orgName>
<desc><address><addrLine>Mitsubishi Electric Research Laboratories Cambridge MA 02139</addrLine>
<country key="US"></country>
</address>
<ref type="url">http://www.merl.com/</ref>
</desc>
<listRelation><relation active="#struct-322337" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-322337" type="direct"><org type="institution" xml:id="struct-322337" status="INCOMING"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Watanabe, Shinji" sort="Watanabe, Shinji" uniqKey="Watanabe S" first="Shinji" last="Watanabe">Shinji Watanabe</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-89592" status="VALID"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<orgName type="acronym">MERL</orgName>
<desc><address><addrLine>Mitsubishi Electric Research Laboratories Cambridge MA 02139</addrLine>
<country key="US"></country>
</address>
<ref type="url">http://www.merl.com/</ref>
</desc>
<listRelation><relation active="#struct-322337" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-322337" type="direct"><org type="institution" xml:id="struct-322337" status="INCOMING"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Vincent, Emmanuel" sort="Vincent, Emmanuel" uniqKey="Vincent E" first="Emmanuel" last="Vincent">Emmanuel Vincent</name>
<affiliation wicri:level="1"><hal:affiliation type="researchteam" xml:id="struct-420403" status="VALID"><idno type="RNSR">201421147E</idno>
<orgName>Speech Modeling for Facilitating Oral-Based Communication</orgName>
<orgName type="acronym">MULTISPEECH</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/equipes/multispeech</ref>
</desc>
<listRelation><relation active="#struct-129671" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-423086" type="direct"></relation>
<relation active="#struct-206040" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
<tutelles><tutelle active="#struct-129671" type="direct"><org type="laboratory" xml:id="struct-129671" status="VALID"><idno type="RNSR">198618246Y</idno>
<orgName>INRIA Nancy - Grand Est</orgName>
<desc><address><addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/nancy</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-300009" type="indirect"><org type="institution" xml:id="struct-300009" status="VALID"><orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
<orgName type="acronym">Inria</orgName>
<desc><address><addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.inria.fr/en/</ref>
</desc>
</org>
</tutelle>
<tutelle active="#struct-423086" type="direct"><org type="department" xml:id="struct-423086" status="VALID"><orgName>Department of Natural Language Processing & Knowledge Discovery</orgName>
<orgName type="acronym">LORIA - NLPKD</orgName>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr/la-recherche-en/departements/Knowledge-and-Language-Management</ref>
</desc>
<listRelation><relation active="#struct-206040" type="direct"></relation>
<relation active="#struct-300009" type="indirect"></relation>
<relation active="#struct-413289" type="indirect"></relation>
<relation name="UMR7503" active="#struct-441569" type="indirect"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-206040" type="indirect"><org type="laboratory" xml:id="struct-206040" status="VALID"><idno type="IdRef">067077927</idno>
<idno type="RNSR">198912571S</idno>
<idno type="IdUnivLorraine">[UL]RSI--</idno>
<orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
<orgName type="acronym">LORIA</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.loria.fr</ref>
</desc>
<listRelation><relation active="#struct-300009" type="direct"></relation>
<relation active="#struct-413289" type="direct"></relation>
<relation name="UMR7503" active="#struct-441569" type="direct"></relation>
</listRelation>
</org>
</tutelle>
<tutelle active="#struct-413289" type="indirect"><org type="institution" xml:id="struct-413289" status="VALID"><idno type="IdRef">157040569</idno>
<idno type="IdUnivLorraine">[UL]100--</idno>
<orgName>Université de Lorraine</orgName>
<orgName type="acronym">UL</orgName>
<date type="start">2012-01-01</date>
<desc><address><addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lorraine.fr/</ref>
</desc>
</org>
</tutelle>
<tutelle name="UMR7503" active="#struct-441569" type="indirect"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="ISNI">0000000122597504</idno>
<idno type="IdRef">02636817X</idno>
<orgName>Centre National de la Recherche Scientifique</orgName>
<orgName type="acronym">CNRS</orgName>
<date type="start">1939-10-19</date>
<desc><address><country key="FR"></country>
</address>
<ref type="url">http://www.cnrs.fr/</ref>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">Nancy</settlement>
<settlement type="city">Metz</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="university">Université de Lorraine</orgName>
</affiliation>
</author>
<author><name sortKey="Le Roux, Jonathan" sort="Le Roux, Jonathan" uniqKey="Le Roux J" first="Jonathan" last="Le Roux">Jonathan Le Roux</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-89592" status="VALID"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<orgName type="acronym">MERL</orgName>
<desc><address><addrLine>Mitsubishi Electric Research Laboratories Cambridge MA 02139</addrLine>
<country key="US"></country>
</address>
<ref type="url">http://www.merl.com/</ref>
</desc>
<listRelation><relation active="#struct-322337" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-322337" type="direct"><org type="institution" xml:id="struct-322337" status="INCOMING"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Hershey, John R" sort="Hershey, John R" uniqKey="Hershey J" first="John R." last="Hershey">John R. Hershey</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-89592" status="VALID"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<orgName type="acronym">MERL</orgName>
<desc><address><addrLine>Mitsubishi Electric Research Laboratories Cambridge MA 02139</addrLine>
<country key="US"></country>
</address>
<ref type="url">http://www.merl.com/</ref>
</desc>
<listRelation><relation active="#struct-322337" type="direct"></relation>
</listRelation>
<tutelles><tutelle active="#struct-322337" type="direct"><org type="institution" xml:id="struct-322337" status="INCOMING"><orgName>Mitsubishi Electric Research Laboratories</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Schuller, Bjorn" sort="Schuller, Bjorn" uniqKey="Schuller B" first="Björn" last="Schuller">Björn Schuller</name>
<affiliation wicri:level="1"><hal:affiliation type="institution" xml:id="struct-69530" status="VALID"><orgName>Imperial College London</orgName>
<desc><address><addrLine>Imperial College London, South Kensington Campus, London SW7 2AZ</addrLine>
<country key="GB"></country>
</address>
<ref type="url">http://www3.imperial.ac.uk/</ref>
</desc>
</hal:affiliation>
<country>Royaume-Uni</country>
</affiliation>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">We evaluate some recent developments in recurrent neural network (RNN) based speech enhancement in the light of noise-robust automatic speech recognition (ASR). The proposed framework is based on Long Short-Term Memory (LSTM) RNNs which are discriminatively trained according to an optimal speech reconstruction objective. We demonstrate that LSTM speech enhancement, even when used ' na¨vely ' as front-end processing, delivers competitive results on the CHiME-2 speech recognition task. Furthermore, simple, feature-level fusion based extensions to the framework are proposed to improve the integration with the ASR back-end. These yield a best result of 13.76 % average word error rate, which is, to our knowledge, the best score to date.</div>
</front>
</TEI>
<affiliations><list><country><li>Allemagne</li>
<li>France</li>
<li>Royaume-Uni</li>
<li>États-Unis</li>
</country>
<region><li>Grand Est</li>
<li>Lorraine (région)</li>
</region>
<settlement><li>Metz</li>
<li>Nancy</li>
</settlement>
<orgName><li>Université de Lorraine</li>
</orgName>
</list>
<tree><country name="Allemagne"><noRegion><name sortKey="Weninger, Felix" sort="Weninger, Felix" uniqKey="Weninger F" first="Felix" last="Weninger">Felix Weninger</name>
</noRegion>
</country>
<country name="États-Unis"><noRegion><name sortKey="Erdogan, Hakan" sort="Erdogan, Hakan" uniqKey="Erdogan H" first="Hakan" last="Erdogan">Hakan Erdogan</name>
</noRegion>
<name sortKey="Hershey, John R" sort="Hershey, John R" uniqKey="Hershey J" first="John R." last="Hershey">John R. Hershey</name>
<name sortKey="Le Roux, Jonathan" sort="Le Roux, Jonathan" uniqKey="Le Roux J" first="Jonathan" last="Le Roux">Jonathan Le Roux</name>
<name sortKey="Watanabe, Shinji" sort="Watanabe, Shinji" uniqKey="Watanabe S" first="Shinji" last="Watanabe">Shinji Watanabe</name>
</country>
<country name="France"><region name="Grand Est"><name sortKey="Vincent, Emmanuel" sort="Vincent, Emmanuel" uniqKey="Vincent E" first="Emmanuel" last="Vincent">Emmanuel Vincent</name>
</region>
</country>
<country name="Royaume-Uni"><noRegion><name sortKey="Schuller, Bjorn" sort="Schuller, Bjorn" uniqKey="Schuller B" first="Björn" last="Schuller">Björn Schuller</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000372 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000372 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    InforLorV4
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     Hal:hal-01163493
   |texte=   Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR
}}

This area was generated with Dilib version V0.6.33.
Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022

	Serveur d'exploration sur la recherche en informatique en Lorraine
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur la recherche en informatique en Lorraine

Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR

Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR

Source :

Abstract

Links toward previous steps (curation, corpus...)

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri