Alpha-Jacobian environmental adaptation
Identifieur interne : 006B63 ( Main/Merge ); précédent : 006B62; suivant : 006B64Alpha-Jacobian environmental adaptation
Auteurs : Christophe Cerisara ; Luca Rigazio ; Jean-Claude JunquaSource :
- Speech Communication ; 2004.
English descriptors
Abstract
The robustness of automatic speech recognition systems to noise is still a problem, especially for small footprint systems. This paper addresses the problem of noise robustness using model compensation methods. Such algorithms are already available, but their complexity is usually high. An often referenced method for achieving noise robustness is Parallel Model Combination (PMC). Several algorithms have been proposed to develop more computationally efficient methods than PMC. For example, Jacobian adaptation approximates PMC with a linear transformation function in the cepstral domain. However, the Jacobian approximation is valid only for test environments that are close to the training conditions whereas, in real test conditions, the mismatch between the test and training environments is usually large. In this paper, we propose two methods, respectively called static and dynamic alpha-Jacobian adaptation (or alpha-JAC), to compute new linear approximations of PMC for realistic test environments. We further extend both algorithms to compensate for additive and convolutional noise and we derive the corresponding non-linear algorithm that is approximated. All these algorithms are experimentally compared in important mismatch conditions. As compared to Jacobian adaptation, improvements are observed with both static and dynamic alpha-Jacobian adaptation.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 003F53
- to stream Crin, to step Curation: 003F53
- to stream Crin, to step Checkpoint: 000688
Links to Exploration step
CRIN:cerisara04aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="429">Alpha-Jacobian environmental adaptation</title></titleStmt><publicationStmt><idno type="RBID">CRIN:cerisara04a</idno><date when="2004" year="2004">2004</date><idno type="wicri:Area/Crin/Corpus">003F53</idno><idno type="wicri:Area/Crin/Curation">003F53</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003F53</idno><idno type="wicri:Area/Crin/Checkpoint">000688</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">000688</idno><idno type="wicri:Area/Main/Merge">006B63</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Alpha-Jacobian environmental adaptation</title><author><name sortKey="Cerisara, Christophe" sort="Cerisara, Christophe" uniqKey="Cerisara C" first="Christophe" last="Cerisara">Christophe Cerisara</name></author><author><name sortKey="Rigazio, Luca" sort="Rigazio, Luca" uniqKey="Rigazio L" first="Luca" last="Rigazio">Luca Rigazio</name></author><author><name sortKey="Junqua, Jean Claude" sort="Junqua, Jean Claude" uniqKey="Junqua J" first="Jean-Claude" last="Junqua">Jean-Claude Junqua</name></author></analytic><series><title level="j">Speech Communication</title><imprint><date when="2004" type="published">2004</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>automatic speech recognition</term><term>jacobian adaptation</term><term>model compensation</term><term>noise robustness</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="5641">The robustness of automatic speech recognition systems to noise is still a problem, especially for small footprint systems. This paper addresses the problem of noise robustness using model compensation methods. Such algorithms are already available, but their complexity is usually high. An often referenced method for achieving noise robustness is Parallel Model Combination (PMC). Several algorithms have been proposed to develop more computationally efficient methods than PMC. For example, Jacobian adaptation approximates PMC with a linear transformation function in the cepstral domain. However, the Jacobian approximation is valid only for test environments that are close to the training conditions whereas, in real test conditions, the mismatch between the test and training environments is usually large. In this paper, we propose two methods, respectively called static and dynamic alpha-Jacobian adaptation (or alpha-JAC), to compute new linear approximations of PMC for realistic test environments. We further extend both algorithms to compensate for additive and convolutional noise and we derive the corresponding non-linear algorithm that is approximated. All these algorithms are experimentally compared in important mismatch conditions. As compared to Jacobian adaptation, improvements are observed with both static and dynamic alpha-Jacobian adaptation.</div></front></TEI></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 006B63 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 006B63 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Merge
|type= RBID
|clé= CRIN:cerisara04a
|texte= Alpha-Jacobian environmental adaptation
}}
| This area was generated with Dilib version V0.6.33. |  |