Teamwork Quality Prediction Using Speech-Based Features

This paper describes a novel protocol for annotating teamwork quality and related variables, based only on the speech signal. Our protocol was designed to annotate a Spanish version of the Objects Games corpus, a publicly available corpus that contains dialogues of people playing a collaborative com...

Descripción completa

Detalles Bibliográficos
Autores principales: Meza, Martín, Gauder, Lara, Estienne, Lautaro, Barchi, Ricardo, Gravano, Agustín, Riera, Pablo, Ferrer, Luciana
Formato: Documento de conferencia publishedVersion
Lenguaje:Inglés
Publicado: SMM23, Workshop on Speech, Music and Mind 2023 2023
Materias:
Predicción tecnológica
Technological Prediction
Speech-Based Features
Protocols
Protocolos
Acceso en línea:https://repositorio.utdt.edu/handle/20.500.13098/12137
Aporte de:
Repositorio Digital Universidad Torcuato Di Tella de Universidad Torcuato Di Tella
id I57-R163-20.500.13098-12137
record_format dspace
spelling I57-R163-20.500.13098-121372023-11-17T07:00:18Z Teamwork Quality Prediction Using Speech-Based Features Meza, Martín Gauder, Lara Estienne, Lautaro Barchi, Ricardo Gravano, Agustín Riera, Pablo Ferrer, Luciana Predicción tecnológica Technological Prediction Speech-Based Features Protocols Protocolos This paper describes a novel protocol for annotating teamwork quality and related variables, based only on the speech signal. Our protocol was designed to annotate a Spanish version of the Objects Games corpus, a publicly available corpus that contains dialogues of people playing a collaborative computer game. The corpus was annotated by 4 raters, who achieved an Intra class Correlation Coefficient of 0.64 for the main teamwork quality metric. Using the resulting annotations, we developed a system for automatic prediction of the average teamwork quality across raters using features extracted from the conversations, reaching a coefficient of determination, R2 of 0.56. This result suggests that automatic prediction of teamwork quality from the speech signal of the teammates is a feasible task. 2023-11-16T15:15:07Z 2023-11-16T15:15:07Z 2023 info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion https://repositorio.utdt.edu/handle/20.500.13098/12137 eng info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by-sa/2.5/ar/ 5 p. application/pdf application/pdf SMM23, Workshop on Speech, Music and Mind 2023
institution Universidad Torcuato Di Tella
institution_str I-57
repository_str R-163
collection Repositorio Digital Universidad Torcuato Di Tella
language Inglés
orig_language_str_mv eng
topic Predicción tecnológica
Technological Prediction
Speech-Based Features
Protocols
Protocolos
spellingShingle Predicción tecnológica
Technological Prediction
Speech-Based Features
Protocols
Protocolos
Meza, Martín
Gauder, Lara
Estienne, Lautaro
Barchi, Ricardo
Gravano, Agustín
Riera, Pablo
Ferrer, Luciana
Teamwork Quality Prediction Using Speech-Based Features
topic_facet Predicción tecnológica
Technological Prediction
Speech-Based Features
Protocols
Protocolos
description This paper describes a novel protocol for annotating teamwork quality and related variables, based only on the speech signal. Our protocol was designed to annotate a Spanish version of the Objects Games corpus, a publicly available corpus that contains dialogues of people playing a collaborative computer game. The corpus was annotated by 4 raters, who achieved an Intra class Correlation Coefficient of 0.64 for the main teamwork quality metric. Using the resulting annotations, we developed a system for automatic prediction of the average teamwork quality across raters using features extracted from the conversations, reaching a coefficient of determination, R2 of 0.56. This result suggests that automatic prediction of teamwork quality from the speech signal of the teammates is a feasible task.
format Documento de conferencia
publishedVersion
author Meza, Martín
Gauder, Lara
Estienne, Lautaro
Barchi, Ricardo
Gravano, Agustín
Riera, Pablo
Ferrer, Luciana
author_facet Meza, Martín
Gauder, Lara
Estienne, Lautaro
Barchi, Ricardo
Gravano, Agustín
Riera, Pablo
Ferrer, Luciana
author_sort Meza, Martín
title Teamwork Quality Prediction Using Speech-Based Features
title_short Teamwork Quality Prediction Using Speech-Based Features
title_full Teamwork Quality Prediction Using Speech-Based Features
title_fullStr Teamwork Quality Prediction Using Speech-Based Features
title_full_unstemmed Teamwork Quality Prediction Using Speech-Based Features
title_sort teamwork quality prediction using speech-based features
publisher SMM23, Workshop on Speech, Music and Mind 2023
publishDate 2023
url https://repositorio.utdt.edu/handle/20.500.13098/12137
work_keys_str_mv AT mezamartin teamworkqualitypredictionusingspeechbasedfeatures
AT gauderlara teamworkqualitypredictionusingspeechbasedfeatures
AT estiennelautaro teamworkqualitypredictionusingspeechbasedfeatures
AT barchiricardo teamworkqualitypredictionusingspeechbasedfeatures
AT gravanoagustin teamworkqualitypredictionusingspeechbasedfeatures
AT rierapablo teamworkqualitypredictionusingspeechbasedfeatures
AT ferrerluciana teamworkqualitypredictionusingspeechbasedfeatures
_version_ 1808040728010424320

Ejemplares similares