Extracting Linguistic Knowledge from Speech: A Study of Stop Realization in 5 Romance Languages - Traitement du Langage Parlé Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Extracting Linguistic Knowledge from Speech: A Study of Stop Realization in 5 Romance Languages

Résumé

This paper builds upon recent work in leveraging the corpora and tools originally used to develop speech technologies for corpus-based linguistic studies. We address the non-canonical realization of consonants in connected speech and we focus on voicing alternation phenomena of stops in 5 standard varieties of Romance languages (French, Italian, Spanish, Portuguese, Romanian). For these languages, both large scale corpora and speech recognition systems were available for the study. We use forced alignment with pronunciation variants and machine learning techniques to examine to what extent such frequent phenomena characterize languages and what are the most triggering factors. The results confirm that voicing alternations occur in all Romance languages. Automatic classification underlines that surrounding contexts and segment duration are recurring contributing factors for modeling voicing alternation. The results of this study also demonstrate the new role that machine learning techniques such as classification algorithms can play in helping to extract linguistic knowledge from speech and to suggest interesting research directions.

Video
https://s3.eu-west-2.wasabisys.com/lrec2022/sessions/555.mp4
Fichier principal
Vignette du fichier
2022.lrec-1.348.pdf (537.31 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03706248 , version 1 (27-06-2022)

Identifiants

  • HAL Id : hal-03706248 , version 1

Citer

Yaru Wu, Mathilde Hutin, Ioana Vasilescu, Lori Lamel, Martine Adda-Decker. Extracting Linguistic Knowledge from Speech: A Study of Stop Realization in 5 Romance Languages. 13th Conference on Language Resources and Evaluation (LREC 2022), Jun 2022, Marseille, France. pp.3257-3263. ⟨hal-03706248⟩
147 Consultations
80 Téléchargements

Partager

Gmail Facebook X LinkedIn More