Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFMG |
Texto Completo: | https://doi.org/10.20396/joss.v9i00.14957 http://hdl.handle.net/1843/58800 https://orcid.org/0000-0002-3446-313X https://orcid.org/0000-0001-6317-3548 |
Resumo: | Speech is segmented into intonational units marked by prosodic boundaries. This segmentation is claimed to have important consequences on syntax, information structure and cognition. This work aims both to investigate the phonetic-acoustic parameters that guide the production and perception of prosodic boundaries, and to develop models for automatic detection of prosodic boundaries in male monological spontaneous speech of Brazilian Portuguese. Two samples were segmented into intonational units by two groups of trained annotators. The boundaries perceived by the annotators were tagged as either terminal or non-terminal. A script was used to extract 111 phonetic-acoustic parameters along speech signal in a right and left windows around the boundary of each phonological word. The extracted parameters comprise measures of (1) Speech rate and rhythm; (2) Standardized segment duration; (3) Fundamental frequency; (4) Intensity; (5) Silent pause. The script considers as prosodic boundary positions at which at least 50% of the annotators indicated a boundary of the same type. A training of models composed by the parameters extracted by the script was developed; these models, were then improved heuristically. The models were developed from the two samples and from the whole data, both using non-balanced and balanced data. Linear Discriminant Analysis algorithm was adopted to produce the models. The models for terminal boundaries show a much higher performance than those for non-terminal ones. In this paper we: (i) show the methodological procedures; (ii) analyze the different models; (iii) discuss some strategies that could lead to an improvement of our results. |
id |
UFMG_f79a95637583ea111888b6a2a1b56b9a |
---|---|
oai_identifier_str |
oai:repositorio.ufmg.br:1843/58800 |
network_acronym_str |
UFMG |
network_name_str |
Repositório Institucional da UFMG |
repository_id_str |
|
spelling |
2023-09-19T21:34:29Z2023-09-19T21:34:29Z2020-09-099105128https://doi.org/10.20396/joss.v9i00.149572236-9740http://hdl.handle.net/1843/58800https://orcid.org/0000-0002-3446-313Xhttps://orcid.org/0000-0001-6317-3548Speech is segmented into intonational units marked by prosodic boundaries. This segmentation is claimed to have important consequences on syntax, information structure and cognition. This work aims both to investigate the phonetic-acoustic parameters that guide the production and perception of prosodic boundaries, and to develop models for automatic detection of prosodic boundaries in male monological spontaneous speech of Brazilian Portuguese. Two samples were segmented into intonational units by two groups of trained annotators. The boundaries perceived by the annotators were tagged as either terminal or non-terminal. A script was used to extract 111 phonetic-acoustic parameters along speech signal in a right and left windows around the boundary of each phonological word. The extracted parameters comprise measures of (1) Speech rate and rhythm; (2) Standardized segment duration; (3) Fundamental frequency; (4) Intensity; (5) Silent pause. The script considers as prosodic boundary positions at which at least 50% of the annotators indicated a boundary of the same type. A training of models composed by the parameters extracted by the script was developed; these models, were then improved heuristically. The models were developed from the two samples and from the whole data, both using non-balanced and balanced data. Linear Discriminant Analysis algorithm was adopted to produce the models. The models for terminal boundaries show a much higher performance than those for non-terminal ones. In this paper we: (i) show the methodological procedures; (ii) analyze the different models; (iii) discuss some strategies that could lead to an improvement of our results.engUniversidade Federal de Minas GeraisUFMGBrasilFALE - FACULDADE DE LETRASJournal of Speech SciencesAtos de fala (Linguística)Língua portuguesa - FonologiaProsodic boundariesAutomatic detectionSpontaneous speechModelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speechinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleTommaso RasoBárbara TeixeiraPlinio Barbosaapplication/pdfinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGLICENSELicense.txtLicense.txttext/plain; charset=utf-82042https://repositorio.ufmg.br/bitstream/1843/58800/1/License.txtfa505098d172de0bc8864fc1287ffe22MD51ORIGINALModelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech.pdfModelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech.pdfapplication/pdf1387973https://repositorio.ufmg.br/bitstream/1843/58800/2/Modelling%20automatic%20detection%20of%20prosodic%20boundaries%20for%20Brazilian%20Portuguese%20spontaneous%20speech.pdf06030354b763c7f31c3fe8c4417642abMD521843/588002023-09-19 18:34:29.389oai:repositorio.ufmg.br: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Repositório de PublicaçõesPUBhttps://repositorio.ufmg.br/oaiopendoar:2023-09-19T21:34:29Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false |
dc.title.pt_BR.fl_str_mv |
Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech |
title |
Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech |
spellingShingle |
Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech Tommaso Raso Prosodic boundaries Automatic detection Spontaneous speech Atos de fala (Linguística) Língua portuguesa - Fonologia |
title_short |
Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech |
title_full |
Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech |
title_fullStr |
Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech |
title_full_unstemmed |
Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech |
title_sort |
Modelling automatic detection of prosodic boundaries for Brazilian Portuguese spontaneous speech |
author |
Tommaso Raso |
author_facet |
Tommaso Raso Bárbara Teixeira Plinio Barbosa |
author_role |
author |
author2 |
Bárbara Teixeira Plinio Barbosa |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Tommaso Raso Bárbara Teixeira Plinio Barbosa |
dc.subject.por.fl_str_mv |
Prosodic boundaries Automatic detection Spontaneous speech |
topic |
Prosodic boundaries Automatic detection Spontaneous speech Atos de fala (Linguística) Língua portuguesa - Fonologia |
dc.subject.other.pt_BR.fl_str_mv |
Atos de fala (Linguística) Língua portuguesa - Fonologia |
description |
Speech is segmented into intonational units marked by prosodic boundaries. This segmentation is claimed to have important consequences on syntax, information structure and cognition. This work aims both to investigate the phonetic-acoustic parameters that guide the production and perception of prosodic boundaries, and to develop models for automatic detection of prosodic boundaries in male monological spontaneous speech of Brazilian Portuguese. Two samples were segmented into intonational units by two groups of trained annotators. The boundaries perceived by the annotators were tagged as either terminal or non-terminal. A script was used to extract 111 phonetic-acoustic parameters along speech signal in a right and left windows around the boundary of each phonological word. The extracted parameters comprise measures of (1) Speech rate and rhythm; (2) Standardized segment duration; (3) Fundamental frequency; (4) Intensity; (5) Silent pause. The script considers as prosodic boundary positions at which at least 50% of the annotators indicated a boundary of the same type. A training of models composed by the parameters extracted by the script was developed; these models, were then improved heuristically. The models were developed from the two samples and from the whole data, both using non-balanced and balanced data. Linear Discriminant Analysis algorithm was adopted to produce the models. The models for terminal boundaries show a much higher performance than those for non-terminal ones. In this paper we: (i) show the methodological procedures; (ii) analyze the different models; (iii) discuss some strategies that could lead to an improvement of our results. |
publishDate |
2020 |
dc.date.issued.fl_str_mv |
2020-09-09 |
dc.date.accessioned.fl_str_mv |
2023-09-19T21:34:29Z |
dc.date.available.fl_str_mv |
2023-09-19T21:34:29Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/1843/58800 |
dc.identifier.doi.pt_BR.fl_str_mv |
https://doi.org/10.20396/joss.v9i00.14957 |
dc.identifier.issn.pt_BR.fl_str_mv |
2236-9740 |
dc.identifier.orcid.pt_BR.fl_str_mv |
https://orcid.org/0000-0002-3446-313X https://orcid.org/0000-0001-6317-3548 |
url |
https://doi.org/10.20396/joss.v9i00.14957 http://hdl.handle.net/1843/58800 https://orcid.org/0000-0002-3446-313X https://orcid.org/0000-0001-6317-3548 |
identifier_str_mv |
2236-9740 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Journal of Speech Sciences |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.publisher.initials.fl_str_mv |
UFMG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
FALE - FACULDADE DE LETRAS |
publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFMG instname:Universidade Federal de Minas Gerais (UFMG) instacron:UFMG |
instname_str |
Universidade Federal de Minas Gerais (UFMG) |
instacron_str |
UFMG |
institution |
UFMG |
reponame_str |
Repositório Institucional da UFMG |
collection |
Repositório Institucional da UFMG |
bitstream.url.fl_str_mv |
https://repositorio.ufmg.br/bitstream/1843/58800/1/License.txt https://repositorio.ufmg.br/bitstream/1843/58800/2/Modelling%20automatic%20detection%20of%20prosodic%20boundaries%20for%20Brazilian%20Portuguese%20spontaneous%20speech.pdf |
bitstream.checksum.fl_str_mv |
fa505098d172de0bc8864fc1287ffe22 06030354b763c7f31c3fe8c4417642ab |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG) |
repository.mail.fl_str_mv |
|
_version_ |
1803589566227021824 |