Robustness of auditory Teager Energy Cepstrum Coefficients for classification of pathological and normal voices in noisy environments.
Identifieur interne : 000616 ( PubMed/Corpus ); précédent : 000615; suivant : 000617Robustness of auditory Teager Energy Cepstrum Coefficients for classification of pathological and normal voices in noisy environments.
Auteurs : Lotfi Salhi ; Adnane CherifSource :
- TheScientificWorldJournal [ 1537-744X ] ; 2013.
English descriptors
- KwdEn :
- Adult (MeSH), Aged (MeSH), Aged, 80 and over (MeSH), Algorithms (MeSH), Diagnosis, Computer-Assisted (methods), Female (MeSH), Humans (MeSH), Male (MeSH), Middle Aged (MeSH), Noise (MeSH), Pattern Recognition, Automated (methods), Reproducibility of Results (MeSH), Sensitivity and Specificity (MeSH), Sound Spectrography (methods), Speech Recognition Software (MeSH), Voice Disorders (diagnosis), Voice Disorders (physiopathology), Voice Quality (MeSH).
- MESH :
- diagnosis : Voice Disorders.
- methods : Diagnosis, Computer-Assisted, Pattern Recognition, Automated, Sound Spectrography.
- physiopathology : Voice Disorders.
- Adult, Aged, Aged, 80 and over, Algorithms, Female, Humans, Male, Middle Aged, Noise, Reproducibility of Results, Sensitivity and Specificity, Speech Recognition Software, Voice Quality.
Abstract
This paper focuses on a robust feature extraction algorithm for automatic classification of pathological and normal voices in noisy environments. The proposed algorithm is based on human auditory processing and the nonlinear Teager-Kaiser energy operator. The robust features which labeled Teager Energy Cepstrum Coefficients (TECCs) are computed in three steps. Firstly, each speech signal frame is passed through a Gammatone or Mel scale triangular filter bank. Then, the absolute value of the Teager energy operator of the short-time spectrum is calculated. Finally, the discrete cosine transform of the log-filtered Teager Energy spectrum is applied. This feature is proposed to identify the pathological voices using a developed neural system of multilayer perceptron (MLP). We evaluate the developed method using mixed voice database composed of recorded voice samples from normophonic or dysphonic speakers. In order to show the robustness of the proposed feature in detection of pathological voices at different White Gaussian noise levels, we compare its performance with results for clean environments. The experimental results show that TECCs computed from Gammatone filter bank are more robust in noisy environments than other extracted features, while their performance is practically similar to clean environments.
DOI: 10.1155/2013/435729
PubMed: 23818821
PubMed Central: PMC3681261
Links to Exploration step
pubmed:23818821Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Robustness of auditory Teager Energy Cepstrum Coefficients for classification of pathological and normal voices in noisy environments.</title><author><name sortKey="Salhi, Lotfi" sort="Salhi, Lotfi" uniqKey="Salhi L" first="Lotfi" last="Salhi">Lotfi Salhi</name><affiliation><nlm:affiliation>Signal Processing Laboratory, Physics Department, Sciences Faculty of Tunis, University of Tunis ElManar, 1060 Tunis, Tunisia. lotfi.salhi@laposte.net</nlm:affiliation></affiliation></author><author><name sortKey="Cherif, Adnane" sort="Cherif, Adnane" uniqKey="Cherif A" first="Adnane" last="Cherif">Adnane Cherif</name></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2013">2013</date><idno type="RBID">pubmed:23818821</idno><idno type="pmid">23818821</idno><idno type="doi">10.1155/2013/435729</idno><idno type="pmc">PMC3681261</idno><idno type="wicri:Area/PubMed/Corpus">000616</idno><idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000616</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Robustness of auditory Teager Energy Cepstrum Coefficients for classification of pathological and normal voices in noisy environments.</title><author><name sortKey="Salhi, Lotfi" sort="Salhi, Lotfi" uniqKey="Salhi L" first="Lotfi" last="Salhi">Lotfi Salhi</name><affiliation><nlm:affiliation>Signal Processing Laboratory, Physics Department, Sciences Faculty of Tunis, University of Tunis ElManar, 1060 Tunis, Tunisia. lotfi.salhi@laposte.net</nlm:affiliation></affiliation></author><author><name sortKey="Cherif, Adnane" sort="Cherif, Adnane" uniqKey="Cherif A" first="Adnane" last="Cherif">Adnane Cherif</name></author></analytic><series><title level="j">TheScientificWorldJournal</title><idno type="eISSN">1537-744X</idno><imprint><date when="2013" type="published">2013</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Adult (MeSH)</term><term>Aged (MeSH)</term><term>Aged, 80 and over (MeSH)</term><term>Algorithms (MeSH)</term><term>Diagnosis, Computer-Assisted (methods)</term><term>Female (MeSH)</term><term>Humans (MeSH)</term><term>Male (MeSH)</term><term>Middle Aged (MeSH)</term><term>Noise (MeSH)</term><term>Pattern Recognition, Automated (methods)</term><term>Reproducibility of Results (MeSH)</term><term>Sensitivity and Specificity (MeSH)</term><term>Sound Spectrography (methods)</term><term>Speech Recognition Software (MeSH)</term><term>Voice Disorders (diagnosis)</term><term>Voice Disorders (physiopathology)</term><term>Voice Quality (MeSH)</term></keywords><keywords scheme="MESH" qualifier="diagnosis" xml:lang="en"><term>Voice Disorders</term></keywords><keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Diagnosis, Computer-Assisted</term><term>Pattern Recognition, Automated</term><term>Sound Spectrography</term></keywords><keywords scheme="MESH" qualifier="physiopathology" xml:lang="en"><term>Voice Disorders</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Adult</term><term>Aged</term><term>Aged, 80 and over</term><term>Algorithms</term><term>Female</term><term>Humans</term><term>Male</term><term>Middle Aged</term><term>Noise</term><term>Reproducibility of Results</term><term>Sensitivity and Specificity</term><term>Speech Recognition Software</term><term>Voice Quality</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This paper focuses on a robust feature extraction algorithm for automatic classification of pathological and normal voices in noisy environments. The proposed algorithm is based on human auditory processing and the nonlinear Teager-Kaiser energy operator. The robust features which labeled Teager Energy Cepstrum Coefficients (TECCs) are computed in three steps. Firstly, each speech signal frame is passed through a Gammatone or Mel scale triangular filter bank. Then, the absolute value of the Teager energy operator of the short-time spectrum is calculated. Finally, the discrete cosine transform of the log-filtered Teager Energy spectrum is applied. This feature is proposed to identify the pathological voices using a developed neural system of multilayer perceptron (MLP). We evaluate the developed method using mixed voice database composed of recorded voice samples from normophonic or dysphonic speakers. In order to show the robustness of the proposed feature in detection of pathological voices at different White Gaussian noise levels, we compare its performance with results for clean environments. The experimental results show that TECCs computed from Gammatone filter bank are more robust in noisy environments than other extracted features, while their performance is practically similar to clean environments. </div></front></TEI><pubmed><MedlineCitation Status="MEDLINE" Owner="NLM"><PMID Version="1">23818821</PMID><DateCompleted><Year>2013</Year><Month>09</Month><Day>30</Day></DateCompleted><DateRevised><Year>2018</Year><Month>11</Month><Day>13</Day></DateRevised><Article PubModel="Electronic-Print"><Journal><ISSN IssnType="Electronic">1537-744X</ISSN><JournalIssue CitedMedium="Internet"><Volume>2013</Volume><PubDate><Year>2013</Year></PubDate></JournalIssue><Title>TheScientificWorldJournal</Title><ISOAbbreviation>ScientificWorldJournal</ISOAbbreviation></Journal><ArticleTitle>Robustness of auditory Teager Energy Cepstrum Coefficients for classification of pathological and normal voices in noisy environments.</ArticleTitle><Pagination><MedlinePgn>435729</MedlinePgn></Pagination><ELocationID EIdType="doi" ValidYN="Y">10.1155/2013/435729</ELocationID><Abstract><AbstractText>This paper focuses on a robust feature extraction algorithm for automatic classification of pathological and normal voices in noisy environments. The proposed algorithm is based on human auditory processing and the nonlinear Teager-Kaiser energy operator. The robust features which labeled Teager Energy Cepstrum Coefficients (TECCs) are computed in three steps. Firstly, each speech signal frame is passed through a Gammatone or Mel scale triangular filter bank. Then, the absolute value of the Teager energy operator of the short-time spectrum is calculated. Finally, the discrete cosine transform of the log-filtered Teager Energy spectrum is applied. This feature is proposed to identify the pathological voices using a developed neural system of multilayer perceptron (MLP). We evaluate the developed method using mixed voice database composed of recorded voice samples from normophonic or dysphonic speakers. In order to show the robustness of the proposed feature in detection of pathological voices at different White Gaussian noise levels, we compare its performance with results for clean environments. The experimental results show that TECCs computed from Gammatone filter bank are more robust in noisy environments than other extracted features, while their performance is practically similar to clean environments. </AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Salhi</LastName><ForeName>Lotfi</ForeName><Initials>L</Initials><AffiliationInfo><Affiliation>Signal Processing Laboratory, Physics Department, Sciences Faculty of Tunis, University of Tunis ElManar, 1060 Tunis, Tunisia. lotfi.salhi@laposte.net</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Cherif</LastName><ForeName>Adnane</ForeName><Initials>A</Initials></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2013</Year><Month>05</Month><Day>28</Day></ArticleDate></Article><MedlineJournalInfo><Country>United States</Country><MedlineTA>ScientificWorldJournal</MedlineTA><NlmUniqueID>101131163</NlmUniqueID><ISSNLinking>1537-744X</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><MeshHeadingList><MeshHeading><DescriptorName UI="D000328" MajorTopicYN="N">Adult</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D000368" MajorTopicYN="N">Aged</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D000369" MajorTopicYN="N">Aged, 80 and over</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D000465" MajorTopicYN="N">Algorithms</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D003936" MajorTopicYN="N">Diagnosis, Computer-Assisted</DescriptorName><QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D005260" MajorTopicYN="N">Female</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D006801" MajorTopicYN="N">Humans</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D008297" MajorTopicYN="N">Male</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D008875" MajorTopicYN="N">Middle Aged</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D009622" MajorTopicYN="Y">Noise</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D010363" MajorTopicYN="N">Pattern Recognition, Automated</DescriptorName><QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D015203" MajorTopicYN="N">Reproducibility of Results</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D012680" MajorTopicYN="N">Sensitivity and Specificity</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D013018" MajorTopicYN="N">Sound Spectrography</DescriptorName><QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D049250" MajorTopicYN="Y">Speech Recognition Software</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D014832" MajorTopicYN="N">Voice Disorders</DescriptorName><QualifierName UI="Q000175" MajorTopicYN="Y">diagnosis</QualifierName><QualifierName UI="Q000503" MajorTopicYN="Y">physiopathology</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D014833" MajorTopicYN="N">Voice Quality</DescriptorName></MeshHeading></MeshHeadingList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2013</Year><Month>03</Month><Day>31</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2013</Year><Month>05</Month><Day>08</Day></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2013</Year><Month>7</Month><Day>3</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2013</Year><Month>7</Month><Day>3</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2013</Year><Month>10</Month><Day>1</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>epublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">23818821</ArticleId><ArticleId IdType="doi">10.1155/2013/435729</ArticleId><ArticleId IdType="pmc">PMC3681261</ArticleId></ArticleIdList><ReferenceList><Reference><Citation>J Speech Lang Hear Res. 2000 Apr;43(2):469-85</Citation><ArticleIdList><ArticleId IdType="pubmed">10757697</ArticleId></ArticleIdList></Reference><Reference><Citation>J Voice. 2001 Dec;15(4):529-42</Citation><ArticleIdList><ArticleId IdType="pubmed">11792029</ArticleId></ArticleIdList></Reference><Reference><Citation>J Acoust Soc Am. 2005 Jan;117(1):328-37</Citation><ArticleIdList><ArticleId IdType="pubmed">15704425</ArticleId></ArticleIdList></Reference><Reference><Citation>IEEE Eng Med Biol Mag. 1997 Jul-Aug;16(4):74-82</Citation><ArticleIdList><ArticleId IdType="pubmed">9241523</ArticleId></ArticleIdList></Reference><Reference><Citation>Hear Res. 1990 Aug 1;47(1-2):103-38</Citation><ArticleIdList><ArticleId IdType="pubmed">2228789</ArticleId></ArticleIdList></Reference></ReferenceList></PubmedData></pubmed></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/MaghrebDataLibMedV2/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000616 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000616 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Sante
|area= MaghrebDataLibMedV2
|flux= PubMed
|étape= Corpus
|type= RBID
|clé= pubmed:23818821
|texte= Robustness of auditory Teager Energy Cepstrum Coefficients for classification of pathological and normal voices in noisy environments.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:23818821" \
| HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a MaghrebDataLibMedV2
| This area was generated with Dilib version V0.6.38. |  |