Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research.

EMRAI speech corpus dyadic audio analysis psychotherapy process measure random forest supervised speaker diarization

Journal

Frontiers in psychology
ISSN: 1664-1078
Titre abrégé: Front Psychol
Pays: Switzerland
ID NLM: 101550902

Informations de publication

Date de publication:
2020
Historique:
received: 10 02 2020
accepted: 23 06 2020
entrez: 28 8 2020
pubmed: 28 8 2020
medline: 28 8 2020
Statut: epublish

Résumé

Speaker diarization is the practice of determining who speaks when in audio recordings. Psychotherapy research often relies on labor intensive manual diarization. Unsupervised methods are available but yield higher error rates. We present a method for supervised speaker diarization based on random forests. It can be considered a compromise between commonly used labor-intensive manual coding and fully automated procedures. The method is validated using the EMRAI synthetic speech corpus and is made publicly available. It yields low diarization error rates (M: 5.61%, STD: 2.19). Supervised speaker diarization is a promising method for psychotherapy research and similar fields.

Identifiants

pubmed: 32849033
doi: 10.3389/fpsyg.2020.01726
pmc: PMC7399377
doi:

Types de publication

Journal Article

Langues

eng

Pagination

1726

Informations de copyright

Copyright © 2020 Fürer, Schenk, Roth, Steppan, Schmeck and Zimmermann.

Références

Psychotherapy (Chic). 2015 Mar;52(1):19-30
pubmed: 24866972
Sci Rep. 2019 Oct 11;9(1):14691
pubmed: 31604966
PLoS One. 2015 Dec 02;10(12):e0143055
pubmed: 26630392
J Consult Clin Psychol. 2011 Jun;79(3):284-95
pubmed: 21639608
Psychother Res. 2019 Aug;29(6):693-708
pubmed: 29409394
Contemp Clin Trials Commun. 2018 Oct 31;12:182-191
pubmed: 30511027
J Nerv Ment Dis. 2007 Feb;195(2):103-11
pubmed: 17299296
Personal Disord. 2020 Apr 23;:
pubmed: 32324008
PLoS One. 2017 Sep 21;12(9):e0185123
pubmed: 28934302
J Couns Psychol. 2014 Jan;61(1):146-53
pubmed: 24274679
Eur J Appl Physiol. 2010 Jul;109(4):779-86
pubmed: 20225081
Front Psychol. 2014 Sep 05;5:979
pubmed: 25249994
Front Psychol. 2015 Apr 09;6:379
pubmed: 25914657
J Med Internet Res. 2018 Oct 10;20(10):e10754
pubmed: 30305255
J Couns Psychol. 2020 Jul;67(4):536-549
pubmed: 32614233
Front Psychol. 2017 Nov 24;8:2053
pubmed: 29225589
Psychother Res. 2020 Mar;30(3):300-309
pubmed: 30913982
Front Psychol. 2020 Jan 10;10:2970
pubmed: 31998200
Psychother Res. 2020 Jun;30(5):591-603
pubmed: 32400306
Front Psychol. 2016 Jun 14;7:862
pubmed: 27378968
Behav Ther. 2015 May;46(3):296-303
pubmed: 25892166
J Pers. 2018 Apr;86(2):129-138
pubmed: 27977847

Auteurs

Lukas Fürer (L)

Clinic for Children and Adolescents, University Psychiatric Clinic, Basel, Switzerland.

Nathalie Schenk (N)

Clinic for Children and Adolescents, University Psychiatric Clinic, Basel, Switzerland.

Volker Roth (V)

Department of Mathematics and Computer Science, University of Basel, Basel, Switzerland.

Martin Steppan (M)

Clinic for Children and Adolescents, University Psychiatric Clinic, Basel, Switzerland.

Klaus Schmeck (K)

Clinic for Children and Adolescents, University Psychiatric Clinic, Basel, Switzerland.

Ronan Zimmermann (R)

Clinic for Children and Adolescents, University Psychiatric Clinic, Basel, Switzerland.
Division of Clinical Psychology and Psychotherapy, Faculty of Psychology, University of Basel, Basel, Switzerland.

Classifications MeSH