Deep Neural Network for Automatic Classification of Pathological Voice Signals

Computer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and clinical attention. This paper proposes an automatic diagnosis method of pathological voice based on deep neural network (DNN). Other two classification models (su...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of voice Vol. 36; no. 2; pp. 288.e15 - 288.e24
Main Authors:	Chen, Lili, Chen, Junjiang
Format:	Journal Article
Language:	English
Published:	United States Elsevier Inc 01.03.2022
Subjects:	Acoustics Automatic classification Deep neural network Humans Mel frequency cepstral coefficients Neural Networks, Computer Otolaryngology Pathological voice Stacked sparse autoencoder Support Vector Machine Voice Deep neural network Automatic classification Pathological voice Stacked sparse autoencoder Mel frequency cepstral coefficients
ISSN:	0892-1997, 1873-4588, 1873-4588
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Computer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and clinical attention. This paper proposes an automatic diagnosis method of pathological voice based on deep neural network (DNN). Other two classification models (support vector machines and random forests) were used to verify the effectiveness of DNN. In this paper, we extracted 12 Mel frequency cepstral coefficients of each voice sample as row features. The constructed DNN consists a two-layer stacked sparse autoencoders network and a softmax layer. The stacked sparse autoencoders layer can learn high-level features from raw Mel frequency cepstral coefficients features. Then, the softmax layer can diagnose pathological voice according to high-level features. The DNN and the other two comparison models used the same train set and test set for the experiment. Experimental results reveal that the value of sensitivity, specificity, precision, accuracy, and F1 score of the DNN can reach 97.8%, 99.4%, 99.4%, 98.6%, and 98.4%, respectively. The five indexes of DNN classification results are at least 6.2%, 5%, 5.6%, 5.7%, and 6.2% higher than the comparison models (support vector machine and random forest). The proposed DNN can learn advanced features from raw acoustic features, and distinguish pathological voice from healthy voice. To the extent of this preliminary study, future studies can further explore the application of DNN in other experiments and clinical practice
AbstractList	Computer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and clinical attention. This paper proposes an automatic diagnosis method of pathological voice based on deep neural network (DNN). Other two classification models (support vector machines and random forests) were used to verify the effectiveness of DNN.OBJECTIVESComputer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and clinical attention. This paper proposes an automatic diagnosis method of pathological voice based on deep neural network (DNN). Other two classification models (support vector machines and random forests) were used to verify the effectiveness of DNN.In this paper, we extracted 12 Mel frequency cepstral coefficients of each voice sample as row features. The constructed DNN consists a two-layer stacked sparse autoencoders network and a softmax layer. The stacked sparse autoencoders layer can learn high-level features from raw Mel frequency cepstral coefficients features. Then, the softmax layer can diagnose pathological voice according to high-level features. The DNN and the other two comparison models used the same train set and test set for the experiment.METHODSIn this paper, we extracted 12 Mel frequency cepstral coefficients of each voice sample as row features. The constructed DNN consists a two-layer stacked sparse autoencoders network and a softmax layer. The stacked sparse autoencoders layer can learn high-level features from raw Mel frequency cepstral coefficients features. Then, the softmax layer can diagnose pathological voice according to high-level features. The DNN and the other two comparison models used the same train set and test set for the experiment.Experimental results reveal that the value of sensitivity, specificity, precision, accuracy, and F1 score of the DNN can reach 97.8%, 99.4%, 99.4%, 98.6%, and 98.4%, respectively. The five indexes of DNN classification results are at least 6.2%, 5%, 5.6%, 5.7%, and 6.2% higher than the comparison models (support vector machine and random forest).RESULTSExperimental results reveal that the value of sensitivity, specificity, precision, accuracy, and F1 score of the DNN can reach 97.8%, 99.4%, 99.4%, 98.6%, and 98.4%, respectively. The five indexes of DNN classification results are at least 6.2%, 5%, 5.6%, 5.7%, and 6.2% higher than the comparison models (support vector machine and random forest).The proposed DNN can learn advanced features from raw acoustic features, and distinguish pathological voice from healthy voice. To the extent of this preliminary study, future studies can further explore the application of DNN in other experiments and clinical practice.CONCLUSIONSThe proposed DNN can learn advanced features from raw acoustic features, and distinguish pathological voice from healthy voice. To the extent of this preliminary study, future studies can further explore the application of DNN in other experiments and clinical practice. Computer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and clinical attention. This paper proposes an automatic diagnosis method of pathological voice based on deep neural network (DNN). Other two classification models (support vector machines and random forests) were used to verify the effectiveness of DNN. In this paper, we extracted 12 Mel frequency cepstral coefficients of each voice sample as row features. The constructed DNN consists a two-layer stacked sparse autoencoders network and a softmax layer. The stacked sparse autoencoders layer can learn high-level features from raw Mel frequency cepstral coefficients features. Then, the softmax layer can diagnose pathological voice according to high-level features. The DNN and the other two comparison models used the same train set and test set for the experiment. Experimental results reveal that the value of sensitivity, specificity, precision, accuracy, and F1 score of the DNN can reach 97.8%, 99.4%, 99.4%, 98.6%, and 98.4%, respectively. The five indexes of DNN classification results are at least 6.2%, 5%, 5.6%, 5.7%, and 6.2% higher than the comparison models (support vector machine and random forest). The proposed DNN can learn advanced features from raw acoustic features, and distinguish pathological voice from healthy voice. To the extent of this preliminary study, future studies can further explore the application of DNN in other experiments and clinical practice. SummaryObjectivesComputer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and clinical attention. This paper proposes an automatic diagnosis method of pathological voice based on deep neural network (DNN). Other two classification models (support vector machines and random forests) were used to verify the effectiveness of DNN. MethodsIn this paper, we extracted 12 Mel frequency cepstral coefficients of each voice sample as row features. The constructed DNN consists a two-layer stacked sparse autoencoders network and a softmax layer. The stacked sparse autoencoders layer can learn high-level features from raw Mel frequency cepstral coefficients features. Then, the softmax layer can diagnose pathological voice according to high-level features. The DNN and the other two comparison models used the same train set and test set for the experiment. ResultsExperimental results reveal that the value of sensitivity, specificity, precision, accuracy, and F1 score of the DNN can reach 97.8%, 99.4%, 99.4%, 98.6%, and 98.4%, respectively. The five indexes of DNN classification results are at least 6.2%, 5%, 5.6%, 5.7%, and 6.2% higher than the comparison models (support vector machine and random forest). ConclusionsThe proposed DNN can learn advanced features from raw acoustic features, and distinguish pathological voice from healthy voice. To the extent of this preliminary study, future studies can further explore the application of DNN in other experiments and clinical practice Computer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and clinical attention. This paper proposes an automatic diagnosis method of pathological voice based on deep neural network (DNN). Other two classification models (support vector machines and random forests) were used to verify the effectiveness of DNN. In this paper, we extracted 12 Mel frequency cepstral coefficients of each voice sample as row features. The constructed DNN consists a two-layer stacked sparse autoencoders network and a softmax layer. The stacked sparse autoencoders layer can learn high-level features from raw Mel frequency cepstral coefficients features. Then, the softmax layer can diagnose pathological voice according to high-level features. The DNN and the other two comparison models used the same train set and test set for the experiment. Experimental results reveal that the value of sensitivity, specificity, precision, accuracy, and F1 score of the DNN can reach 97.8%, 99.4%, 99.4%, 98.6%, and 98.4%, respectively. The five indexes of DNN classification results are at least 6.2%, 5%, 5.6%, 5.7%, and 6.2% higher than the comparison models (support vector machine and random forest). The proposed DNN can learn advanced features from raw acoustic features, and distinguish pathological voice from healthy voice. To the extent of this preliminary study, future studies can further explore the application of DNN in other experiments and clinical practice
Author	Chen, Junjiang Chen, Lili
Author_xml	– sequence: 1 givenname: Lili surname: Chen fullname: Chen, Lili email: clili522@cqjtu.edu.cn organization: School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing, China – sequence: 2 givenname: Junjiang surname: Chen fullname: Chen, Junjiang organization: School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32660846$$D View this record in MEDLINE/PubMed
BookMark	eNqVkk9v1DAQxS3Uim4L3wChHLkkHf-J4yCEVC1QkKoWqcDVip1JcZqNt3ZS1G-PwxYOlaqK08j2e2-s38wh2Rv9iIS8olBQoPK4L_pb7ywWDBgUUBbA6mdkRVXFc1EqtUdWoGqW07quDshhjD0AsPT6nBxwJiUoIVfk_APiNjvHOTRDKtMvH66zzofsZJ78ppmczdZDE6PrnE0nP2a-y742008_-Kt0NWQ_lk9kl-5qbIb4gux3qeDL-3pEvn_6-G39OT-7OP2yPjnLrahgymtZY2mlLMuaI1ctZVC3suS0YZUwnTHKSmVKahVSI9BQoZg0UrASuKkM8CPyZpe7Df5mxjjpjYsWh6EZ0c9RM6E4h0pwnqSv76Wz2WCrt8FtmnCn_zJIArET2OBjDNj9k1DQC2rd6x1qvaDWUOqEOtnePrBZN_1BNIXGDU-Z3-_MmCDdOgw6WoejxdYFtJNuvfvfADu4cRnINd5h7P0clnloqiPToC-XVVg2gQGHtCJLwLvHA57u_xvr7cQt
CitedBy_id	crossref_primary_10_3390_app12199748 crossref_primary_10_1016_j_health_2024_100369 crossref_primary_10_3233_JCM_237025 crossref_primary_10_1007_s00034_023_02551_8 crossref_primary_10_1016_j_compbiomed_2022_106517 crossref_primary_10_1038_s41598_025_03444_3 crossref_primary_10_3390_cancers14102366 crossref_primary_10_1016_j_compbiomed_2023_107566 crossref_primary_10_1016_j_jvoice_2024_09_002 crossref_primary_10_1002_lio2_1144 crossref_primary_10_1093_comjnl_bxae051 crossref_primary_10_1121_10_0016869 crossref_primary_10_1016_j_csl_2023_101552 crossref_primary_10_3390_data10010004 crossref_primary_10_1016_j_apacoust_2024_110438 crossref_primary_10_1002_ohn_636 crossref_primary_10_1186_s12938_025_01401_9 crossref_primary_10_1109_JTEHM_2023_3340345 crossref_primary_10_3390_app122111095 crossref_primary_10_1007_s10772_024_10134_4 crossref_primary_10_1080_10494820_2025_2488991 crossref_primary_10_1007_s00034_025_03032_w crossref_primary_10_1109_ACCESS_2024_3454825 crossref_primary_10_1109_JSEN_2021_3049277 crossref_primary_10_1080_10255842_2024_2410228
Cites_doi	10.1016/j.neucom.2018.05.040 10.1118/1.4896099 10.1016/j.neunet.2017.04.012 10.1016/j.neucom.2016.12.038 10.1016/j.neunet.2014.08.005 10.1016/j.bspc.2019.01.007 10.1016/j.compeleceng.2018.04.008 10.1016/j.compbiomed.2011.06.019 10.1016/j.jmr.2018.06.015 10.1016/j.jvoice.2009.08.002 10.1016/j.procs.2018.10.010 10.1016/j.jvoice.2010.04.009 10.1016/j.compbiomed.2018.05.027 10.1016/j.procs.2017.12.112 10.1016/j.compbiomed.2009.10.011 10.1016/j.jvoice.2014.05.006 10.1016/j.eswa.2018.08.050 10.1016/j.jvoice.2018.07.014 10.1109/TNSRE.2018.2805338 10.1016/j.neucom.2017.08.043 10.1016/j.patrec.2005.07.004 10.17743/jaes.2019.0004 10.1016/j.asoc.2014.03.036 10.1016/j.measurement.2016.04.007 10.1126/science.1127647 10.1016/j.ins.2016.01.082 10.1007/s11517-019-01949-4 10.1016/j.bspc.2014.02.001 10.1016/j.nicl.2018.01.032 10.1016/j.ins.2017.10.044
ContentType	Journal Article
Copyright	2020 The Voice Foundation The Voice Foundation Copyright © 2020 The Voice Foundation. Published by Elsevier Inc. All rights reserved.
Copyright_xml	– notice: 2020 The Voice Foundation – notice: The Voice Foundation – notice: Copyright © 2020 The Voice Foundation. Published by Elsevier Inc. All rights reserved.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1016/j.jvoice.2020.05.029
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic MEDLINE
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine Anatomy & Physiology
EISSN	1873-4588
EndPage	288.e24
ExternalDocumentID	32660846 10_1016_j_jvoice_2020_05_029 S0892199720301879 1_s2_0_S0892199720301879
Genre	Journal Article
GrantInformation_xml	– fundername: Social Undertakings and Livelihood Security of Chongqing grantid: cstc2017shmsA30016 – fundername: Graduate Education and Teaching Reform Research Project of Chongqing grantid: yjg182027
GroupedDBID	--- --K --M -RU -~X .1- .FO .GJ .~1 0R~ 186 1B1 1P~ 1RT 1~. 1~5 29L 4.4 457 4G. 53G 5RE 5VS 6PF 7-5 71M 85S 8P~ 9JM 9JO AAEDT AAEDW AAFJI AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAWTL AAXKI AAXUO AAYWO ABBQC ABFNM ABFRF ABIVO ABJNI ABMAC ABMMH ABMZM ABWVN ABXDB ACDAQ ACGFO ACGFS ACIEU ACLOT ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADMHG ADMUD ADNMO AEBSH AEFWE AEIPS AEKER AENEX AETEA AEUPX AEVXI AFFDN AFFNX AFJKZ AFPUW AFRHN AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX AOMHK APXCP ASPBG AVARZ AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV BPHCQ BVXVI CS3 DU5 EBS EFJIC EFKBS EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HEA HMK HMO HVGLF HZ~ H~9 IAO ICO IEA IER IHE IHR INH INR IOF IPO ITC J1W J5H KNOGT KOM LZ2 M27 M41 MO0 N9A O-L O9- OAUVE OG- OHT OR0 OZT P-8 P-9 P2P PC. PQQKQ PRBVW PROAC Q38 R2- ROL RPZ SAE SDF SDG SEL SES SEW SPCBC SSB SSH SSO SSZ T5K TAE TN5 TWZ UHS UKR UNMZH UPT WH7 WUQ YQT Z5R ZCG ZY4 ~G- ~HD 3V. A3D AACTN ABTAH AFCTW AFKWA AJOXV AJPXE AMFUW AVQMV BENPR DJMCT PKN RIG VQA AAIAV ABLVK ABYKQ AEVYS AJBFU AKYCK LCYCR 9DU AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
ID	FETCH-LOGICAL-c470t-969e5c665593e38d1209d6531a274bfbb8c68b51c8e1b4eb14826b642503b7b03
ISICitedReferencesCount	31
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000860525600017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0892-1997 1873-4588
IngestDate	Thu Oct 02 05:09:11 EDT 2025 Thu Apr 03 07:09:05 EDT 2025 Sat Nov 29 07:12:51 EST 2025 Tue Nov 18 21:33:47 EST 2025 Fri Feb 23 02:41:02 EST 2024 Tue Feb 25 20:08:14 EST 2025 Tue Oct 14 19:36:08 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	2
Keywords	Deep neural network Automatic classification Pathological voice Stacked sparse autoencoder Mel frequency cepstral coefficients
Language	English
License	Copyright © 2020 The Voice Foundation. Published by Elsevier Inc. All rights reserved.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c470t-969e5c665593e38d1209d6531a274bfbb8c68b51c8e1b4eb14826b642503b7b03
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
PMID	32660846
PQID	2483307433
PQPubID	23479
ParticipantIDs	proquest_miscellaneous_2483307433 pubmed_primary_32660846 crossref_primary_10_1016_j_jvoice_2020_05_029 crossref_citationtrail_10_1016_j_jvoice_2020_05_029 elsevier_sciencedirect_doi_10_1016_j_jvoice_2020_05_029 elsevier_clinicalkeyesjournals_1_s2_0_S0892199720301879 elsevier_clinicalkey_doi_10_1016_j_jvoice_2020_05_029
PublicationCentury	2000
PublicationDate	2022-03-01
PublicationDateYYYYMMDD	2022-03-01
PublicationDate_xml	– month: 03 year: 2022 text: 2022-03-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Journal of voice
PublicationTitleAlternate	J Voice
PublicationYear	2022
Publisher	Elsevier Inc
Publisher_xml	– name: Elsevier Inc
References	Al-Noori, Duncan (bib0025) 2019; 67 Wang, Zhang, Yan (bib0016) 2011; 25 AL, LAN, L (bib0024) 2000; 101 Hegde, Shetty, Rai (bib0003) 2018; 33 Liu, Wang, Liu (bib0010) 2017; 234 Vaziri, Almasganj, Behroozmand (bib0015) 2010; 40 Chen, Zhou, Su (bib0021) 2018; 428 Lee, Chou, Han (bib0026) 2006; 27 Adem, Kilicarslan, Comert (bib0022) 2019; 115 Sanchez, Sidky, Pan (bib0009) 2014; 41 Sun, Shao, Zhao (bib0033) 2016; 89 Zeng, Zhang, Song (bib0031) 2018; 273 Muhammad, Melhem (bib0001) 2014; 11 Aichinger, Pernkopf, Schoentgen (bib0004) 2019; 50 Sainath, Kingsbury, Saon (bib0011) 2015; 64 Zorrilla, Zapirain, Izquierdo (bib0012) 2012; 1 Uloza, Verikas, Bacauskiene (bib0005) 2011; 25 Erfanian Saeedi, Almasganj, Torabinejad (bib0014) 2011; 41 Jothilakshmi (bib0007) 2014; 21 Delvaux, Pillot-Loiseau (bib0002) 2019 Hinton, Salakhutdinov (bib0018) 2006; 313 Maurya, Kumar, Agarwal (bib0017) 2018; 125 Cesari, Pietro, Marciano (bib0023) 2018; 68 Cordeiro, Ribeiro (bib0013) 2018; 138 Xu, Cao, Song (bib0030) 2018; 311 Praveen, Agrawal, Sundaram (bib0019) 2018; 99 He, Li, Holland (bib0029) 2018; 18 Wang, Qian, Feng (bib0034) 2018; 26 Yamauchi, Yokonishi, Imagawa (bib0006) 2015; 29 Hu, Yu (bib0028) 2019; 17 Al Rahhal, Bazi, AlHichri (bib0020) 2016; 345 Naeem, Hamzaid, Islam (bib0027) 2019; 57 Ayinde, Zurada (bib0032) 2017; 93 Qiao, Zhang, Pan (bib0008) 2018; 294 Aichinger (10.1016/j.jvoice.2020.05.029_bib0004) 2019; 50 Jothilakshmi (10.1016/j.jvoice.2020.05.029_bib0007) 2014; 21 Wang (10.1016/j.jvoice.2020.05.029_bib0016) 2011; 25 Wang (10.1016/j.jvoice.2020.05.029_bib0034) 2018; 26 Sanchez (10.1016/j.jvoice.2020.05.029_bib0009) 2014; 41 Ayinde (10.1016/j.jvoice.2020.05.029_bib0032) 2017; 93 Naeem (10.1016/j.jvoice.2020.05.029_bib0027) 2019; 57 Al Rahhal (10.1016/j.jvoice.2020.05.029_bib0020) 2016; 345 Maurya (10.1016/j.jvoice.2020.05.029_bib0017) 2018; 125 Al-Noori (10.1016/j.jvoice.2020.05.029_bib0025) 2019; 67 Muhammad (10.1016/j.jvoice.2020.05.029_bib0001) 2014; 11 Chen (10.1016/j.jvoice.2020.05.029_bib0021) 2018; 428 Zeng (10.1016/j.jvoice.2020.05.029_bib0031) 2018; 273 Xu (10.1016/j.jvoice.2020.05.029_bib0030) 2018; 311 Hinton (10.1016/j.jvoice.2020.05.029_bib0018) 2006; 313 Zorrilla (10.1016/j.jvoice.2020.05.029_bib0012) 2012; 1 Erfanian Saeedi (10.1016/j.jvoice.2020.05.029_bib0014) 2011; 41 Sainath (10.1016/j.jvoice.2020.05.029_bib0011) 2015; 64 AL (10.1016/j.jvoice.2020.05.029_bib0024) 2000; 101 Lee (10.1016/j.jvoice.2020.05.029_bib0026) 2006; 27 Hu (10.1016/j.jvoice.2020.05.029_bib0028) 2019; 17 Delvaux (10.1016/j.jvoice.2020.05.029_bib0002) 2019 Yamauchi (10.1016/j.jvoice.2020.05.029_bib0006) 2015; 29 Qiao (10.1016/j.jvoice.2020.05.029_bib0008) 2018; 294 Liu (10.1016/j.jvoice.2020.05.029_bib0010) 2017; 234 Vaziri (10.1016/j.jvoice.2020.05.029_bib0015) 2010; 40 Uloza (10.1016/j.jvoice.2020.05.029_bib0005) 2011; 25 Cesari (10.1016/j.jvoice.2020.05.029_bib0023) 2018; 68 He (10.1016/j.jvoice.2020.05.029_bib0029) 2018; 18 Sun (10.1016/j.jvoice.2020.05.029_bib0033) 2016; 89 Adem (10.1016/j.jvoice.2020.05.029_bib0022) 2019; 115 Cordeiro (10.1016/j.jvoice.2020.05.029_bib0013) 2018; 138 Praveen (10.1016/j.jvoice.2020.05.029_bib0019) 2018; 99 Hegde (10.1016/j.jvoice.2020.05.029_bib0003) 2018; 33
References_xml	– volume: 26 start-page: 629 year: 2018 end-page: 636 ident: bib0034 article-title: Design and preliminary evaluation of electrolarynx with F0 control based on capacitive touch technology publication-title: IEEE Trans Neural Syst Rehabil Eng – volume: 138 start-page: 64 year: 2018 end-page: 71 ident: bib0013 article-title: Spectral envelope first peak and periodic component in pathological voices: a spectral analysis publication-title: Proc Comput Sci – volume: 40 start-page: 54 year: 2010 end-page: 63 ident: bib0015 article-title: Pathological assessment of patients’ speech signals using nonlinear dynamical analysis publication-title: Comput Biol Med – volume: 99 start-page: 38 year: 2018 end-page: 52 ident: bib0019 article-title: Ischemic stroke lesion segmentation using stacked sparse autoencoder publication-title: Comput Biol Med – volume: 1 year: 2012 ident: bib0012 publication-title: Computer Aided Tool for Diagnosis of ENT Pathologies Using Digital Signal Processing of Speech and Stroboscopic Images – volume: 25 start-page: 38 year: 2011 end-page: 43 ident: bib0016 article-title: Discrimination between pathological and normal voices using GMM-SVM approach publication-title: J Voice – volume: 115 start-page: 557 year: 2019 end-page: 564 ident: bib0022 article-title: Classification and diagnosis of cervical cancer with softmax classification with stacked autoencoder publication-title: Expert Syst Appl – volume: 41 year: 2014 ident: bib0009 article-title: Task-based optimization of dedicated breast CT via Hotelling observer metrics publication-title: Med Phys – volume: 17 start-page: 1483 year: 2019 end-page: 1490 ident: bib0028 article-title: Diagnosis of mesothelioma with deep learning publication-title: Oncol Lett – volume: 89 start-page: 171 year: 2016 end-page: 178 ident: bib0033 article-title: A sparse auto-encoder-based deep neural network approach for induction motor faults classification publication-title: Measurement – volume: 29 start-page: 109 year: 2015 end-page: 119 ident: bib0006 article-title: Quantitative analysis of digital videokymography: a preliminary study on age- and gender-related difference of vocal fold vibration in normal speakers publication-title: J Voice – volume: 27 start-page: 93 year: 2006 end-page: 101 ident: bib0026 article-title: Automatic recognition of animal vocalizations using averaged MFCC and linear discriminant analysis publication-title: Pattern Recognit Lett – volume: 311 start-page: 1 year: 2018 end-page: 10 ident: bib0030 article-title: ircuit fault diagnosis of power rectifier using sparse autoencoder based deep neural network publication-title: Neurocomputing – volume: 25 start-page: 700 year: 2011 end-page: 708 ident: bib0005 article-title: Categorizing normal and pathological voices: automated and perceptual categorization publication-title: J Voice – volume: 428 start-page: 49 year: 2018 end-page: 61 ident: bib0021 article-title: Softmax regression based deep sparse autoencoder network for facial emotion recognition in human-robot interaction publication-title: Inf Sci – volume: 125 start-page: 880 year: 2018 end-page: 887 ident: bib0017 article-title: Speaker recognition for Hindi speech signal using MFCC-GMM approach publication-title: Proc Comput Sci – volume: 33 start-page: 947.e11 year: 2018 end-page: 947.e33 ident: bib0003 article-title: A survey on machine learning approaches for automatic detection of voice disorders publication-title: J Voice – volume: 234 start-page: 11 year: 2017 end-page: 26 ident: bib0010 article-title: A survey of deep neural network architectures and their applications publication-title: Neurocomputing – year: 2019 ident: bib0002 article-title: Perceptual judgment of voice quality in nondysphonic French speakers: effect of task-, speaker- and listener-related variables publication-title: J Voice – volume: 93 start-page: 99 year: 2017 end-page: 109 ident: bib0032 article-title: Nonredundant sparse feature extraction using autoencoders with receptive fields clustering publication-title: Neural Netw – volume: 21 start-page: 244 year: 2014 end-page: 249 ident: bib0007 article-title: Automatic system to detect the type of voice pathology publication-title: Appl Soft Comput – volume: 64 start-page: 39 year: 2015 end-page: 48 ident: bib0011 article-title: Deep convolutional neural networks for large-scale speech tasks publication-title: Neural Netw – volume: 57 start-page: 1199 year: 2019 end-page: 1211 ident: bib0027 article-title: Mechanomyography-based muscle fatigue detection during electrically elicited cycling in patients with spinal cord injury publication-title: Med Biol Eng Comput – volume: 41 start-page: 822 year: 2011 end-page: 828 ident: bib0014 article-title: Support vector wavelet adaptation for pathological voice assessment publication-title: Comput Biol Med – volume: 18 start-page: 290 year: 2018 end-page: 297 ident: bib0029 article-title: Early prediction of cognitive deficits in very preterm infants using functional connectome data in an artificial neural network framework publication-title: Neuroimage Clin – volume: 345 start-page: 340 year: 2016 end-page: 354 ident: bib0020 article-title: Deep learning approach for active classification of electrocardiogram signals publication-title: Inf Sci – volume: 11 start-page: 1 year: 2014 end-page: 9 ident: bib0001 article-title: Pathological voice detection and binary classification using MPEG-7 audio features publication-title: Biomed Signal Process Control – volume: 50 start-page: 158 year: 2019 end-page: 167 ident: bib0004 article-title: Detection of extra pulses in synthesized glottal area waveforms of dysphonic voices publication-title: Biomed Signal Process Control – volume: 67 start-page: 174 year: 2019 end-page: 189 ident: bib0025 article-title: Robust speaker recognition in noisy conditions by means of online training with noise profiles publication-title: J Audio Eng Soc – volume: 273 start-page: 643 year: 2018 end-page: 649 ident: bib0031 article-title: Facial expression recognition via learning deep sparse autoencoders publication-title: Neurocomputing – volume: 313 start-page: 504 year: 2006 end-page: 507 ident: bib0018 article-title: Reducing the dimensionality of data with neural networks publication-title: Science – volume: 294 start-page: 24 year: 2018 end-page: 34 ident: bib0008 article-title: Optimization-based image reconstruction from sparsely sampled data in electron paramagnetic resonance imaging publication-title: J Magn Reson – volume: 68 start-page: 310 year: 2018 end-page: 321 ident: bib0023 article-title: A new database of healthy and pathological voices publication-title: Comput Electr Eng – volume: 101 start-page: e215 year: 2000 end-page: e220 ident: bib0024 article-title: PhysioBank, PhysioToolkit, and PhysioNet. Components of a new research resource for complex physiologic signals publication-title: Circulation – volume: 311 start-page: 1 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0030 article-title: ircuit fault diagnosis of power rectifier using sparse autoencoder based deep neural network publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.05.040 – volume: 41 year: 2014 ident: 10.1016/j.jvoice.2020.05.029_bib0009 article-title: Task-based optimization of dedicated breast CT via Hotelling observer metrics publication-title: Med Phys doi: 10.1118/1.4896099 – volume: 17 start-page: 1483 year: 2019 ident: 10.1016/j.jvoice.2020.05.029_bib0028 article-title: Diagnosis of mesothelioma with deep learning publication-title: Oncol Lett – volume: 93 start-page: 99 year: 2017 ident: 10.1016/j.jvoice.2020.05.029_bib0032 article-title: Nonredundant sparse feature extraction using autoencoders with receptive fields clustering publication-title: Neural Netw doi: 10.1016/j.neunet.2017.04.012 – volume: 234 start-page: 11 year: 2017 ident: 10.1016/j.jvoice.2020.05.029_bib0010 article-title: A survey of deep neural network architectures and their applications publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.12.038 – volume: 101 start-page: e215 year: 2000 ident: 10.1016/j.jvoice.2020.05.029_bib0024 article-title: PhysioBank, PhysioToolkit, and PhysioNet. Components of a new research resource for complex physiologic signals publication-title: Circulation – volume: 64 start-page: 39 year: 2015 ident: 10.1016/j.jvoice.2020.05.029_bib0011 article-title: Deep convolutional neural networks for large-scale speech tasks publication-title: Neural Netw doi: 10.1016/j.neunet.2014.08.005 – volume: 50 start-page: 158 year: 2019 ident: 10.1016/j.jvoice.2020.05.029_bib0004 article-title: Detection of extra pulses in synthesized glottal area waveforms of dysphonic voices publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2019.01.007 – volume: 68 start-page: 310 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0023 article-title: A new database of healthy and pathological voices publication-title: Comput Electr Eng doi: 10.1016/j.compeleceng.2018.04.008 – volume: 41 start-page: 822 year: 2011 ident: 10.1016/j.jvoice.2020.05.029_bib0014 article-title: Support vector wavelet adaptation for pathological voice assessment publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2011.06.019 – volume: 294 start-page: 24 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0008 article-title: Optimization-based image reconstruction from sparsely sampled data in electron paramagnetic resonance imaging publication-title: J Magn Reson doi: 10.1016/j.jmr.2018.06.015 – volume: 25 start-page: 38 year: 2011 ident: 10.1016/j.jvoice.2020.05.029_bib0016 article-title: Discrimination between pathological and normal voices using GMM-SVM approach publication-title: J Voice doi: 10.1016/j.jvoice.2009.08.002 – volume: 1 year: 2012 ident: 10.1016/j.jvoice.2020.05.029_bib0012 – volume: 138 start-page: 64 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0013 article-title: Spectral envelope first peak and periodic component in pathological voices: a spectral analysis publication-title: Proc Comput Sci doi: 10.1016/j.procs.2018.10.010 – volume: 25 start-page: 700 year: 2011 ident: 10.1016/j.jvoice.2020.05.029_bib0005 article-title: Categorizing normal and pathological voices: automated and perceptual categorization publication-title: J Voice doi: 10.1016/j.jvoice.2010.04.009 – volume: 99 start-page: 38 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0019 article-title: Ischemic stroke lesion segmentation using stacked sparse autoencoder publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2018.05.027 – volume: 125 start-page: 880 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0017 article-title: Speaker recognition for Hindi speech signal using MFCC-GMM approach publication-title: Proc Comput Sci doi: 10.1016/j.procs.2017.12.112 – volume: 40 start-page: 54 year: 2010 ident: 10.1016/j.jvoice.2020.05.029_bib0015 article-title: Pathological assessment of patients’ speech signals using nonlinear dynamical analysis publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2009.10.011 – volume: 29 start-page: 109 year: 2015 ident: 10.1016/j.jvoice.2020.05.029_bib0006 article-title: Quantitative analysis of digital videokymography: a preliminary study on age- and gender-related difference of vocal fold vibration in normal speakers publication-title: J Voice doi: 10.1016/j.jvoice.2014.05.006 – volume: 115 start-page: 557 year: 2019 ident: 10.1016/j.jvoice.2020.05.029_bib0022 article-title: Classification and diagnosis of cervical cancer with softmax classification with stacked autoencoder publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2018.08.050 – year: 2019 ident: 10.1016/j.jvoice.2020.05.029_bib0002 article-title: Perceptual judgment of voice quality in nondysphonic French speakers: effect of task-, speaker- and listener-related variables publication-title: J Voice – volume: 33 start-page: 947.e11 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0003 article-title: A survey on machine learning approaches for automatic detection of voice disorders publication-title: J Voice doi: 10.1016/j.jvoice.2018.07.014 – volume: 26 start-page: 629 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0034 article-title: Design and preliminary evaluation of electrolarynx with F0 control based on capacitive touch technology publication-title: IEEE Trans Neural Syst Rehabil Eng doi: 10.1109/TNSRE.2018.2805338 – volume: 273 start-page: 643 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0031 article-title: Facial expression recognition via learning deep sparse autoencoders publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.08.043 – volume: 27 start-page: 93 year: 2006 ident: 10.1016/j.jvoice.2020.05.029_bib0026 article-title: Automatic recognition of animal vocalizations using averaged MFCC and linear discriminant analysis publication-title: Pattern Recognit Lett doi: 10.1016/j.patrec.2005.07.004 – volume: 67 start-page: 174 year: 2019 ident: 10.1016/j.jvoice.2020.05.029_bib0025 article-title: Robust speaker recognition in noisy conditions by means of online training with noise profiles publication-title: J Audio Eng Soc doi: 10.17743/jaes.2019.0004 – volume: 21 start-page: 244 year: 2014 ident: 10.1016/j.jvoice.2020.05.029_bib0007 article-title: Automatic system to detect the type of voice pathology publication-title: Appl Soft Comput doi: 10.1016/j.asoc.2014.03.036 – volume: 89 start-page: 171 year: 2016 ident: 10.1016/j.jvoice.2020.05.029_bib0033 article-title: A sparse auto-encoder-based deep neural network approach for induction motor faults classification publication-title: Measurement doi: 10.1016/j.measurement.2016.04.007 – volume: 313 start-page: 504 year: 2006 ident: 10.1016/j.jvoice.2020.05.029_bib0018 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – volume: 345 start-page: 340 year: 2016 ident: 10.1016/j.jvoice.2020.05.029_bib0020 article-title: Deep learning approach for active classification of electrocardiogram signals publication-title: Inf Sci doi: 10.1016/j.ins.2016.01.082 – volume: 57 start-page: 1199 year: 2019 ident: 10.1016/j.jvoice.2020.05.029_bib0027 article-title: Mechanomyography-based muscle fatigue detection during electrically elicited cycling in patients with spinal cord injury publication-title: Med Biol Eng Comput doi: 10.1007/s11517-019-01949-4 – volume: 11 start-page: 1 year: 2014 ident: 10.1016/j.jvoice.2020.05.029_bib0001 article-title: Pathological voice detection and binary classification using MPEG-7 audio features publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2014.02.001 – volume: 18 start-page: 290 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0029 article-title: Early prediction of cognitive deficits in very preterm infants using functional connectome data in an artificial neural network framework publication-title: Neuroimage Clin doi: 10.1016/j.nicl.2018.01.032 – volume: 428 start-page: 49 year: 2018 ident: 10.1016/j.jvoice.2020.05.029_bib0021 article-title: Softmax regression based deep sparse autoencoder network for facial emotion recognition in human-robot interaction publication-title: Inf Sci doi: 10.1016/j.ins.2017.10.044
SSID	ssj0002873
Score	2.4611309
Snippet	Computer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and clinical attention.... SummaryObjectivesComputer-aided pathological voice detection is efficient for initial screening of pathological voice, and has received high academic and...
SourceID	proquest pubmed crossref elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	288.e15
SubjectTerms	Acoustics Automatic classification Deep neural network Humans Mel frequency cepstral coefficients Neural Networks, Computer Otolaryngology Pathological voice Stacked sparse autoencoder Support Vector Machine Voice
Title	Deep Neural Network for Automatic Classification of Pathological Voice Signals
URI	https://www.clinicalkey.com/#!/content/1-s2.0-S0892199720301879 https://www.clinicalkey.es/playcontent/1-s2.0-S0892199720301879 https://dx.doi.org/10.1016/j.jvoice.2020.05.029 https://www.ncbi.nlm.nih.gov/pubmed/32660846 https://www.proquest.com/docview/2483307433
Volume	36
WOSCitedRecordID	wos000860525600017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-4588 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002873 issn: 0892-1997 databaseCode: AIEXJ dateStart: 19950301 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3fb9MwELZYhxAvE2wwOmAyEuIFZUpiJ3YeqzEE06gmMaa-WXHiTKmmpFrSafz3nH8kbSnVBhIvUWTFcez7fL5zvjsj9D4v4jQGN8BLqFIeTXjmySzPvIgFqlCEKWbSNV2esfGYTybJuePPN-Y4AVZV_O4umf1XUUMZCFuHzv6FuPuXQgHcg9DhCmKH64ME_0mp2UedcwMGf2xJ3oZLOJq3tc3Pag7C1BSh3lw8T9uFFrysS52es7zSqZU3GK-3dbmAxLGL8Dgrr8vfy07n1RQQeLW8uwCOaU-vslteXdjLCivT50loGCp2EbGakzPi6bDXZdVqc5s4CIXLepLzI2XjON2ya0psOPWaVrcbDNOjqekcOPWhb9Ktur2S1XzZ3_XX6Y8LtbfHWbKFtkMWJXyAtkdfTyan_UINzqIhIHS96SIrDf1vva1Nlssmz8RYKBfP0I6TDh5ZSDxHj1S1i_ZGVQpy_4k_YEP2NX9RdtGTb45TsYfGGjDYAgY7wGAADO4Bg1cBg-sCLwMGG8BgB5gX6Mfnk4vjL547ZcPLKPNbL4kTFWVxDK4lUYTnOpg6j0E1pyGjspCSZzGXUZBxFUgKSzsFj1SC2xr5RDLpk5doUNWVeoVwHimZSqICX6ZU8VhGOQtpyrmirGBBMESkG0GRuRT0-iSUa9FxDafCjrvQ4y78SMC4D5HX15rZFCz3PB91whFdeDEsiALQdE899qd6qnGTuxGBaELhizWELdd0hqs1SB_Q5rsOPQL0uv5Zl1aqnjcipJwQbd-TIdq3sOp7Dy5X7IPjcPDP7b5GTxez_Q0atDdz9RY9zm7bsrk5RFtswg_ddPkF4kXRwQ
linkProvider	Elsevier
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+Neural+Network+for+Automatic+Classification+of+Pathological+Voice+Signals&rft.jtitle=Journal+of+voice&rft.au=Chen%2C+Lili&rft.au=Chen%2C+Junjiang&rft.date=2022-03-01&rft.pub=Elsevier+Inc&rft.issn=0892-1997&rft.eissn=1873-4588&rft.volume=36&rft.issue=2&rft.spage=288.e15&rft.epage=288.e24&rft_id=info:doi/10.1016%2Fj.jvoice.2020.05.029&rft.externalDocID=S0892199720301879
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0892-1997&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0892-1997&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0892-1997&client=summon