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

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 f...

Descripción completa

Detalles Bibliográficos
Autores principales: Fürer, Lukas, Schenk, Nathalie, Roth, Volker, Steppan, Martin, Schmeck, Klaus, Zimmermann, Ronan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Psychology
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7399377/
https://www.ncbi.nlm.nih.gov/pubmed/32849033
http://dx.doi.org/10.3389/fpsyg.2020.01726
_version_ 1783566135011049472
author Fürer, Lukas
Schenk, Nathalie
Roth, Volker
Steppan, Martin
Schmeck, Klaus
Zimmermann, Ronan
author_facet Fürer, Lukas
Schenk, Nathalie
Roth, Volker
Steppan, Martin
Schmeck, Klaus
Zimmermann, Ronan
author_sort Fürer, Lukas
collection PubMed
description 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.
format Online
Article
Text
id pubmed-7399377
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-73993772020-08-25 Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research Fürer, Lukas Schenk, Nathalie Roth, Volker Steppan, Martin Schmeck, Klaus Zimmermann, Ronan Front Psychol Psychology 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. Frontiers Media S.A. 2020-07-28 /pmc/articles/PMC7399377/ /pubmed/32849033 http://dx.doi.org/10.3389/fpsyg.2020.01726 Text en Copyright © 2020 Fürer, Schenk, Roth, Steppan, Schmeck and Zimmermann. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Psychology
Fürer, Lukas
Schenk, Nathalie
Roth, Volker
Steppan, Martin
Schmeck, Klaus
Zimmermann, Ronan
Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research
title Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research
title_full Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research
title_fullStr Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research
title_full_unstemmed Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research
title_short Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research
title_sort supervised speaker diarization using random forests: a tool for psychotherapy process research
topic Psychology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7399377/
https://www.ncbi.nlm.nih.gov/pubmed/32849033
http://dx.doi.org/10.3389/fpsyg.2020.01726
work_keys_str_mv AT furerlukas supervisedspeakerdiarizationusingrandomforestsatoolforpsychotherapyprocessresearch
AT schenknathalie supervisedspeakerdiarizationusingrandomforestsatoolforpsychotherapyprocessresearch
AT rothvolker supervisedspeakerdiarizationusingrandomforestsatoolforpsychotherapyprocessresearch
AT steppanmartin supervisedspeakerdiarizationusingrandomforestsatoolforpsychotherapyprocessresearch
AT schmeckklaus supervisedspeakerdiarizationusingrandomforestsatoolforpsychotherapyprocessresearch
AT zimmermannronan supervisedspeakerdiarizationusingrandomforestsatoolforpsychotherapyprocessresearch

Ejemplares similares