Towards Unsupervised Subject-Independent Speech-Based Relapse Detection in Patients with Psychosis using Variational Autoencoders

Generative models, such as Variational Autoen-coders, are being increasingly utilized for various acoustic modeling tasks, such as anomaly detection from audio signals. Motivated by this, in this work we propose a Convolutional Variational Autoencoder (CVAE), in order to detect and predict the appea...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 30th European Signal Processing Conference (EUSIPCO) s. 175 - 179
Hlavní autori: Garoufis, C., Zlatintsi, A., Filntisis, P. P., Efthymiou, N., Kalisperakis, E., Karantinos, T., Garyfalli, V., Lazaridi, M., Smyrnis, N., Maragos, P.
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: EUSIPCO 29.08.2022
Predmet:
Aggregates
Anomaly Detection
Convolution
Europe
Interviews
Mental disorders
Predictive models
Protocols
Psychotic Disorders
Relapse Prediction
Spontaneous Speech
Vari-ational Autoencoder
ISSN:2076-1465
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Generative models, such as Variational Autoen-coders, are being increasingly utilized for various acoustic modeling tasks, such as anomaly detection from audio signals. Motivated by this, in this work we propose a Convolutional Variational Autoencoder (CVAE), in order to detect and predict the appearance of relapses in patients with psychotic disorders, such as schizophrenia and bipolar disorder. The proposed system utilizes speech segments of patients, isolated from interviews conducted with their clinicians containing spontaneous speech, and represented as log-mel spectrograms. The results from the analysis of each segment are then aggregated in a per-interview basis. We explore the performance of our system in both a personalized and a universal (patient-independent) setup. Evaluation of our method in data from 13 patients and 375 interviews, with a total duration of 30509 sec of isolated speech, indicate that the CVAE achieves similar results to a Convolutional Autoencoder (CAE) baseline in a personalized setup. Further-more, the proposed model significantly outperforms the CAE baseline when considering a universal relapse detection setup.
AbstractList Generative models, such as Variational Autoen-coders, are being increasingly utilized for various acoustic modeling tasks, such as anomaly detection from audio signals. Motivated by this, in this work we propose a Convolutional Variational Autoencoder (CVAE), in order to detect and predict the appearance of relapses in patients with psychotic disorders, such as schizophrenia and bipolar disorder. The proposed system utilizes speech segments of patients, isolated from interviews conducted with their clinicians containing spontaneous speech, and represented as log-mel spectrograms. The results from the analysis of each segment are then aggregated in a per-interview basis. We explore the performance of our system in both a personalized and a universal (patient-independent) setup. Evaluation of our method in data from 13 patients and 375 interviews, with a total duration of 30509 sec of isolated speech, indicate that the CVAE achieves similar results to a Convolutional Autoencoder (CAE) baseline in a personalized setup. Further-more, the proposed model significantly outperforms the CAE baseline when considering a universal relapse detection setup.
Author Zlatintsi, A.
Kalisperakis, E.
Filntisis, P. P.
Smyrnis, N.
Maragos, P.
Garoufis, C.
Garyfalli, V.
Lazaridi, M.
Karantinos, T.
Efthymiou, N.
Author_xml – sequence: 1
  givenname: C.
  surname: Garoufis
  fullname: Garoufis, C.
  email: cgaroufis@mail.ntua.gr
  organization: School of ECE, National Technical University of Athens,Athens,Greece,15773
– sequence: 2
  givenname: A.
  surname: Zlatintsi
  fullname: Zlatintsi, A.
  email: nzlat@cs.ntua.gr
  organization: School of ECE, National Technical University of Athens,Athens,Greece,15773
– sequence: 3
  givenname: P. P.
  surname: Filntisis
  fullname: Filntisis, P. P.
  email: filby@central.ntua.gr
  organization: School of ECE, National Technical University of Athens,Athens,Greece,15773
– sequence: 4
  givenname: N.
  surname: Efthymiou
  fullname: Efthymiou, N.
  email: nefthymiou@central.ntua.gr
  organization: School of ECE, National Technical University of Athens,Athens,Greece,15773
– sequence: 5
  givenname: E.
  surname: Kalisperakis
  fullname: Kalisperakis, E.
  organization: Laboratory of Cognitive Neuroscience, University Mental Health Research Institute,Athens,Greece
– sequence: 6
  givenname: T.
  surname: Karantinos
  fullname: Karantinos, T.
  organization: Laboratory of Cognitive Neuroscience, University Mental Health Research Institute,Athens,Greece
– sequence: 7
  givenname: V.
  surname: Garyfalli
  fullname: Garyfalli, V.
  organization: Laboratory of Cognitive Neuroscience, University Mental Health Research Institute,Athens,Greece
– sequence: 8
  givenname: M.
  surname: Lazaridi
  fullname: Lazaridi, M.
  organization: Laboratory of Cognitive Neuroscience, University Mental Health Research Institute,Athens,Greece
– sequence: 9
  givenname: N.
  surname: Smyrnis
  fullname: Smyrnis, N.
  email: smyrnis@med.uoa.gr
  organization: Laboratory of Cognitive Neuroscience, University Mental Health Research Institute,Athens,Greece
– sequence: 10
  givenname: P.
  surname: Maragos
  fullname: Maragos, P.
  email: maragos@cs.ntua.gr
  organization: School of ECE, National Technical University of Athens,Athens,Greece,15773
BookMark eNot0MFPwjAUBvBqNFGQv8BL43342q7rekREJSGBCHglZX2TGuyWtZNw9D93RC7v-w6_fIfXI1e-8kjIA4MhF5rpx8l6OV2M51KCFkMOnA-1Bp2n7IL0NORcaQVaXZJbDipLWJrJGzIIwW2B55ArBtkt-V1VB9PYQNc-tDU2Py6gpct2-4VFTKbeYo3d8ZEua8RilzyZE3jHvakD0meMnXOVp87ThYmuk4EeXNzRRTgWuyq4QNvg_Cf9MI0zJ2r2dNTGCn1RWWzCHbkuzT7g4Jx9sn6ZrMZvyWz-Oh2PZoljIGNiclQi57w0lmthFCtBgTFapFuJqS21zIWxwLqWQpFZ4FJAplIJjAmdStEn9_-7DhE3deO-TXPcnD8m_gAjk2XI
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.23919/EUSIPCO55093.2022.9909841
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9082797097
9789082797091
EISSN 2076-1465
EndPage 179
ExternalDocumentID 9909841
Genre orig-research
GroupedDBID 6IE
6IL
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i105t-a8e73822fad293a71f070aa934b5e4df9583ad01df940c6d02530674501139453
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000918827600036&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:52:09 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i105t-a8e73822fad293a71f070aa934b5e4df9583ad01df940c6d02530674501139453
PageCount 5
ParticipantIDs ieee_primary_9909841
PublicationCentury 2000
PublicationDate 2022-Aug.-29
PublicationDateYYYYMMDD 2022-08-29
PublicationDate_xml – month: 08
  year: 2022
  text: 2022-Aug.-29
  day: 29
PublicationDecade 2020
PublicationTitle 2022 30th European Signal Processing Conference (EUSIPCO)
PublicationTitleAbbrev EUSIPCO
PublicationYear 2022
Publisher EUSIPCO
Publisher_xml – name: EUSIPCO
SSID ssib028087106
ssib025355106
Score 1.8272555
Snippet Generative models, such as Variational Autoen-coders, are being increasingly utilized for various acoustic modeling tasks, such as anomaly detection from audio...
SourceID ieee
SourceType Publisher
StartPage 175
SubjectTerms Aggregates
Anomaly Detection
Convolution
Europe
Interviews
Mental disorders
Predictive models
Protocols
Psychotic Disorders
Relapse Prediction
Spontaneous Speech
Vari-ational Autoencoder
Title Towards Unsupervised Subject-Independent Speech-Based Relapse Detection in Patients with Psychosis using Variational Autoencoders
URI https://ieeexplore.ieee.org/document/9909841
WOSCitedRecordID wos000918827600036&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZKxcAEqEW85YERt0lsx_EIpRWVUInUFnWr3NiBLmlUJ-z8c85JKCCxsFmWFUV31ncPf3eH0A2NNE2ZnxKhIERhNPWIjCglXLMV56EK_LTS9JOYTKLFQsYtdLurhTHGVOQz03PL6i1fb5LSpcr6gJwyclXqe0KIulbr6-4EHAznjxfDIPIgFPDCus9oQKUv-8P5dBwPnsEnlxQiwyDoNR_8NVmlMiyjw__90hHqflfo4Xhne45Ry2Qd9DGrOLAWzzNb5g4ErNEYoMHlWsh4N_C2wNPcmOSN3Ct3wPHhcmvwgykqXlaG1xmO636rFrtELa5h0q4tdjz5V_wCEXaTRcR3ZbFx3TAdI7qL5qPhbPBImhELZA2OVUFUZAQFHyFVGuy-En4KEKCUpKApw3QqeUSV9nxYMS8JtZMz2DfGARaoZJyeoHa2ycwpwl6gZMI5uH9MMg1Rd7IyoVj5Uodae9qcoY4T3zKvu2gsG8md_719gQ6chlz2NpCXqF1sS3OF9pP3Ym2315XqPwG406_A
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELaqggQToBbxxgMjaRM_kniE0qoVpURqi7pVbuxAljRqEnb-OeckFJBY2CzLiqI767uHv7tD6Ib6ikbMiSxPQojCaGRbwqfU4oqtOHclcaJS02NvMvEXCxE00O22FkZrXZLPdMcsy7d8tQ4LkyrrAnIK31Sp73DGiFNVa33dHsLBdP54MyS-DcGA7VadRgkVjuj259NR0HsGr1xQiA0J6dSf_DVbpTQtg4P__dQhan_X6OFga32OUEMnLfQxK1mwGZ4nWZEaGMi0wgAOJttijbYjb3M8TbUO36x7aQ4YRlyaafyg85KZleA4wUHVcTXDJlWLK6DM4gwbpvwrfoEYu84j4rsiX5t-mIYT3UbzQX_WG1r1kAUrBtcqt6SvPQpeQiQVWH7pORGAgJSCgq40U5HgPpXKdmDF7NBVRs5g4RgHYKCCcXqMmsk60ScI20SKkHNwAJlgCuLucKVdb-UI5SplK32KWkZ8y7Tqo7GsJXf29_Y12hvOnsbL8WjyeI72jbZMLpeIC9TMN4W-RLvhex5nm6vyGnwCB1CzBw
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=proceeding&rft.title=2022+30th+European+Signal+Processing+Conference+%28EUSIPCO%29&rft.atitle=Towards+Unsupervised+Subject-Independent+Speech-Based+Relapse+Detection+in+Patients+with+Psychosis+using+Variational+Autoencoders&rft.au=Garoufis%2C+C.&rft.au=Zlatintsi%2C+A.&rft.au=Filntisis%2C+P.+P.&rft.au=Efthymiou%2C+N.&rft.date=2022-08-29&rft.pub=EUSIPCO&rft.eissn=2076-1465&rft.spage=175&rft.epage=179&rft_id=info:doi/10.23919%2FEUSIPCO55093.2022.9909841&rft.externalDocID=9909841