A New Auditory-Based Index to Evaluate the Blind Separation Performance of Acoustic Mixtures
Identifieur interne : 000219 ( Main/Exploration ); précédent : 000218; suivant : 000220A New Auditory-Based Index to Evaluate the Blind Separation Performance of Acoustic Mixtures
Auteurs : Juan Manuel Sanchis [Espagne] ; José Joaquín Rieta [Espagne] ; Francisco Castells [Espagne] ; José Millet [Espagne]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2004.
Abstract
Abstract: A new method to evaluate the performance of convolutive blind signal separation (BSS) algorithms in acoustic mixtures is presented. The method is able to compute the spectral level enhancement, in a frequency-band based fashion, between the estimated and the residual sources, thus combining two previously defined parameters in time and frequency domain: the signal to interference ratio and the spectral preservation index. The new index is able to compute the quality of separation performing the spectral computations over a set of logarithmically spaced frequency bands in a similar way as the human auditory system. Obtained results clearly verify that this methodology is a more realistic approach to evaluate the convolutive BSS results of acoustic mixtures.
Url:
DOI: 10.1007/978-3-540-30110-3_141
Affiliations:
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A New Auditory-Based Index to Evaluate the Blind Separation Performance of Acoustic Mixtures</title><author><name sortKey="Sanchis, Juan Manuel" sort="Sanchis, Juan Manuel" uniqKey="Sanchis J" first="Juan Manuel" last="Sanchis">Juan Manuel Sanchis</name></author><author><name sortKey="Rieta, Jose Joaquin" sort="Rieta, Jose Joaquin" uniqKey="Rieta J" first="José Joaquín" last="Rieta">José Joaquín Rieta</name></author><author><name sortKey="Castells, Francisco" sort="Castells, Francisco" uniqKey="Castells F" first="Francisco" last="Castells">Francisco Castells</name></author><author><name sortKey="Millet, Jose" sort="Millet, Jose" uniqKey="Millet J" first="José" last="Millet">José Millet</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:2AD1F485D07F14A62310E1ACD7B6B143466ECE51</idno><date when="2004" year="2004">2004</date><idno type="doi">10.1007/978-3-540-30110-3_141</idno><idno type="url">https://api.istex.fr/document/2AD1F485D07F14A62310E1ACD7B6B143466ECE51/fulltext/pdf</idno><idno type="wicri:Area/Main/Corpus">000827</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Corpus" wicri:corpus="ISTEX">000827</idno><idno type="wicri:Area/Main/Curation">000827</idno><idno type="wicri:Area/Main/Exploration">000219</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Exploration">000219</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A New Auditory-Based Index to Evaluate the Blind Separation Performance of Acoustic Mixtures</title><author><name sortKey="Sanchis, Juan Manuel" sort="Sanchis, Juan Manuel" uniqKey="Sanchis J" first="Juan Manuel" last="Sanchis">Juan Manuel Sanchis</name><affiliation wicri:level="1"><country xml:lang="fr">Espagne</country><wicri:regionArea>Universidad Politécnica de Valencia, 46730, Gandia</wicri:regionArea><wicri:noRegion>Gandia</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Espagne</country></affiliation></author><author><name sortKey="Rieta, Jose Joaquin" sort="Rieta, Jose Joaquin" uniqKey="Rieta J" first="José Joaquín" last="Rieta">José Joaquín Rieta</name><affiliation wicri:level="1"><country xml:lang="fr">Espagne</country><wicri:regionArea>Universidad Politécnica de Valencia, 46730, Gandia</wicri:regionArea><wicri:noRegion>Gandia</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Espagne</country></affiliation></author><author><name sortKey="Castells, Francisco" sort="Castells, Francisco" uniqKey="Castells F" first="Francisco" last="Castells">Francisco Castells</name><affiliation wicri:level="1"><country xml:lang="fr">Espagne</country><wicri:regionArea>Universidad Politécnica de Valencia, 46730, Gandia</wicri:regionArea><wicri:noRegion>Gandia</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Espagne</country></affiliation></author><author><name sortKey="Millet, Jose" sort="Millet, Jose" uniqKey="Millet J" first="José" last="Millet">José Millet</name><affiliation wicri:level="1"><country xml:lang="fr">Espagne</country><wicri:regionArea>Universidad Politécnica de Valencia, 46020, Valencia</wicri:regionArea><wicri:noRegion>Valencia</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Espagne</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2004</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">2AD1F485D07F14A62310E1ACD7B6B143466ECE51</idno><idno type="DOI">10.1007/978-3-540-30110-3_141</idno><idno type="ChapterID">141</idno><idno type="ChapterID">Chap141</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: A new method to evaluate the performance of convolutive blind signal separation (BSS) algorithms in acoustic mixtures is presented. The method is able to compute the spectral level enhancement, in a frequency-band based fashion, between the estimated and the residual sources, thus combining two previously defined parameters in time and frequency domain: the signal to interference ratio and the spectral preservation index. The new index is able to compute the quality of separation performing the spectral computations over a set of logarithmically spaced frequency bands in a similar way as the human auditory system. Obtained results clearly verify that this methodology is a more realistic approach to evaluate the convolutive BSS results of acoustic mixtures.</div></front></TEI><affiliations><list><country><li>Espagne</li></country></list><tree><country name="Espagne"><noRegion><name sortKey="Sanchis, Juan Manuel" sort="Sanchis, Juan Manuel" uniqKey="Sanchis J" first="Juan Manuel" last="Sanchis">Juan Manuel Sanchis</name></noRegion><name sortKey="Castells, Francisco" sort="Castells, Francisco" uniqKey="Castells F" first="Francisco" last="Castells">Francisco Castells</name><name sortKey="Castells, Francisco" sort="Castells, Francisco" uniqKey="Castells F" first="Francisco" last="Castells">Francisco Castells</name><name sortKey="Millet, Jose" sort="Millet, Jose" uniqKey="Millet J" first="José" last="Millet">José Millet</name><name sortKey="Millet, Jose" sort="Millet, Jose" uniqKey="Millet J" first="José" last="Millet">José Millet</name><name sortKey="Rieta, Jose Joaquin" sort="Rieta, Jose Joaquin" uniqKey="Rieta J" first="José Joaquín" last="Rieta">José Joaquín Rieta</name><name sortKey="Rieta, Jose Joaquin" sort="Rieta, Jose Joaquin" uniqKey="Rieta J" first="José Joaquín" last="Rieta">José Joaquín Rieta</name><name sortKey="Sanchis, Juan Manuel" sort="Sanchis, Juan Manuel" uniqKey="Sanchis J" first="Juan Manuel" last="Sanchis">Juan Manuel Sanchis</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/France/explor/AussoisV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000219 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000219 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/France
|area= AussoisV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:2AD1F485D07F14A62310E1ACD7B6B143466ECE51
|texte= A New Auditory-Based Index to Evaluate the Blind Separation Performance of Acoustic Mixtures
}}
| This area was generated with Dilib version V0.6.29. |  |