Can large language models replace human in speech analysis?

Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2023-2024. Tutor: Santi Seguí Mesquida i Carolina Martínez Pérez

Detalhes bibliográficos
Autor: Gareta Casas, Pol
Formato: tesis de maestría
Fecha de publicación:2024
País:España
Recursos:Universidad de Barcelona
Repositorio:Dipòsit Digital de la UB
OAI Identifier:oai:diposit.ub.edu:2445/212885
Acesso em linha:https://hdl.handle.net/2445/212885
Access Level:acceso abierto
Palavra-chave:Tractament del llenguatge natural (Informàtica)
Lingüística computacional
Intel·ligència artificial
Treballs de fi de màster
Natural language processing (Computer science)
Computational linguistics
Artificial intelligence
Master's thesis
id ES_70d3dd71a2dbc4349fcc3b9fbc622f9e
oai_identifier_str oai:diposit.ub.edu:2445/212885
network_acronym_str ES
network_name_str España
repository_id_str
spelling Can large language models replace human in speech analysis?Gareta Casas, PolTractament del llenguatge natural (Informàtica)Lingüística computacionalIntel·ligència artificialTreballs de fi de màsterNatural language processing (Computer science)Computational linguisticsArtificial intelligenceMaster's thesisTreballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2023-2024. Tutor: Santi Seguí Mesquida i Carolina Martínez Pérez[en] This thesis delves into the rapidly growing domain of Large Language Models (LLMs) and examines their relevance in the insurance sector, specifically focusing on their use in speech analysis to evaluate service quality. With the rapid escalation in the popularity of LLMs, we have the opportunity to analyze their practical use, focusing on Generali Seguros’ customer service operations. This research is based on a partnership with Generali Seguros, which provided valuable access to audio recordings of their customer service calls and the associated evaluation templates used for assessing their teleoperators. The core objective is to investigate the potential and real-world applications of LLMs in analyzing and evaluating the quality of service provided by Generali’s teleoperators. To facilitate this, the study utilizes a secure and confidential environment provided by AWS, selecting commercially available models for analysis. The approach begins with converting the audio calls into Spanish text through an audioto-text model, followed by improvements to this transcription method. Next, the study evaluates a baseline LLM that supports multiple languages and allows for fine tuning. A significant aspect of this research includes addressing the challenges inherent in LLMs, such as their tendency towards ’inventing’ responses and providing vague answers. Efforts to mitigate these issues involve both employing the baseline model in English —anticipating better performance due to its primarily English training—and implements strategies to enhance its effectiveness. Additionally, fine-tuning of the model is conducted, with the objective of specializing the model to required task. Despite efforts to enhance the LLM, a notable finding of this study is the model’s consistent failure to predict the minority group in the data, underscoring the limitations of current commercial models in fulfilling this specific evaluative function. The thesis concludes that, while LLMs show promise, they are yet to fully meet the demands of specialized tasks such as nuanced speech analysis in customer service settings. For transparency and further research, all codes used in this study are made available in a GitHub repository (Gareta, 2023).Seguí Mesquida, SantiMartínez Pérez, Carolina2024info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2445/212885Màster Oficial - Fonaments de la Ciència de Dadesreponame:Dipòsit Digital de la UBinstname:Universidad de BarcelonaIngléscc-by-nc-nd (c) Pol Gareta Casas, 2023codi: GPL (c) Pol Gareta Casas, 2023http://creativecommons.org/licenses/by-nc-nd/3.0/es/http://www.gnu.org/licenses/gpl-3.0.ca.htmlinfo:eu-repo/semantics/openAccessoai:diposit.ub.edu:2445/2128852026-05-27T06:46:51Z
dc.title.none.fl_str_mv Can large language models replace human in speech analysis?
title Can large language models replace human in speech analysis?
spellingShingle Can large language models replace human in speech analysis?
Gareta Casas, Pol
Tractament del llenguatge natural (Informàtica)
Lingüística computacional
Intel·ligència artificial
Treballs de fi de màster
Natural language processing (Computer science)
Computational linguistics
Artificial intelligence
Master's thesis
title_short Can large language models replace human in speech analysis?
title_full Can large language models replace human in speech analysis?
title_fullStr Can large language models replace human in speech analysis?
title_full_unstemmed Can large language models replace human in speech analysis?
title_sort Can large language models replace human in speech analysis?
dc.creator.none.fl_str_mv Gareta Casas, Pol
author Gareta Casas, Pol
author_facet Gareta Casas, Pol
author_role author
dc.contributor.none.fl_str_mv Seguí Mesquida, Santi
Martínez Pérez, Carolina
dc.subject.none.fl_str_mv Tractament del llenguatge natural (Informàtica)
Lingüística computacional
Intel·ligència artificial
Treballs de fi de màster
Natural language processing (Computer science)
Computational linguistics
Artificial intelligence
Master's thesis
topic Tractament del llenguatge natural (Informàtica)
Lingüística computacional
Intel·ligència artificial
Treballs de fi de màster
Natural language processing (Computer science)
Computational linguistics
Artificial intelligence
Master's thesis
description Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2023-2024. Tutor: Santi Seguí Mesquida i Carolina Martínez Pérez
publishDate 2024
dc.date.none.fl_str_mv 2024
dc.type.none.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2445/212885
url https://hdl.handle.net/2445/212885
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv cc-by-nc-nd (c) Pol Gareta Casas, 2023
codi: GPL (c) Pol Gareta Casas, 2023
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
http://www.gnu.org/licenses/gpl-3.0.ca.html
info:eu-repo/semantics/openAccess
rights_invalid_str_mv cc-by-nc-nd (c) Pol Gareta Casas, 2023
codi: GPL (c) Pol Gareta Casas, 2023
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
http://www.gnu.org/licenses/gpl-3.0.ca.html
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv Màster Oficial - Fonaments de la Ciència de Dades
reponame:Dipòsit Digital de la UB
instname:Universidad de Barcelona
instname_str Universidad de Barcelona
reponame_str Dipòsit Digital de la UB
collection Dipòsit Digital de la UB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869410608415244288
score 15,811543