Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifier

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kunze, Tarek, Métais, Marianne, Titeux, Hadrien, Elbert, Lucas, Coffey, Joseph, Dupoux, Emmanuel, Cristia, Alejandrina, Lavechin, Marvin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909765176655872
author Kunze, Tarek
Métais, Marianne
Titeux, Hadrien
Elbert, Lucas
Coffey, Joseph
Dupoux, Emmanuel
Cristia, Alejandrina
Lavechin, Marvin
author_facet Kunze, Tarek
Métais, Marianne
Titeux, Hadrien
Elbert, Lucas
Coffey, Joseph
Dupoux, Emmanuel
Cristia, Alejandrina
Lavechin, Marvin
contents Recordings gathered with child-worn devices promised to revolutionize both fundamental and applied speech sciences by allowing the effortless capture of children's naturalistic speech environment and language production. This promise hinges on speech technologies that can transform the sheer mounds of data thus collected into usable information. This paper demonstrates several obstacles blocking progress by summarizing three years' worth of experiments aimed at improving one fundamental task: Voice Type Classification. Our experiments suggest that improvements in representation features, architecture, and parameter search contribute to only marginal gains in performance. More progress is made by focusing on data relevance and quantity, which highlights the importance of collecting data with appropriate permissions to allow sharing.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11074
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifier
Kunze, Tarek
Métais, Marianne
Titeux, Hadrien
Elbert, Lucas
Coffey, Joseph
Dupoux, Emmanuel
Cristia, Alejandrina
Lavechin, Marvin
Audio and Speech Processing
Machine Learning
Sound
Recordings gathered with child-worn devices promised to revolutionize both fundamental and applied speech sciences by allowing the effortless capture of children's naturalistic speech environment and language production. This promise hinges on speech technologies that can transform the sheer mounds of data thus collected into usable information. This paper demonstrates several obstacles blocking progress by summarizing three years' worth of experiments aimed at improving one fundamental task: Voice Type Classification. Our experiments suggest that improvements in representation features, architecture, and parameter search contribute to only marginal gains in performance. More progress is made by focusing on data relevance and quantity, which highlights the importance of collecting data with appropriate permissions to allow sharing.
title Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifier
topic Audio and Speech Processing
Machine Learning
Sound
url https://arxiv.org/abs/2506.11074