Phonemic transcription of low-resource tonal languages

Oliver Adams 1 Trevor Cohn 1 Graham Neubig 2 Alexis Michaud 3, 4
1 Computing and Information Systems, The University of Melbourne, Australia
2 Language Technologies Institute, Carnegie Mellon University
3 LACITO - LACITO - Langues et civilisations à tradition orale - UMR 7107
4 LPP - LPP - Laboratoire de Phonétique et Phonologie - UMR 7018
Abstract : Transcription of speech is an important part of language documentation, and yet speech recognition technology has not been widely harnessed to aid linguists. We explore the use of a neural network architecture with the connectionist temporal classification loss function for phonemic and tonal transcription in a language documentation setting. In this framework, we explore jointly modelling phonemes and tones versus modelling them separately, and assess the importance of pitch information versus phonemic context for tonal prediction. Experiments on two tonal languages, Yongning Na and Eastern Chatino, show the changes in recognition performance as training data is scaled from 10 minutes to 150 minutes. We discuss the findings from incorporating this technology into the linguistic workflow for documenting Yongning Na, which show the method's promise in improving efficiency, minimizing typographical errors, and maintaining the transcription's faithfulness to the acoustic signal, while highlighting phonetic and phonemic facts for linguistic consideration.
Mots-clés : Traitement automatique de la parole Transcription automatique Transcription phonémique Documentation linguistique
Type de document :
Communication dans un congrès
Wong, Sze-Meng Jojo ; Haffari, Gholamreza. Australasian Language Technology Association Workshop 2017, Dec 2017, Brisbane, Australia. ISSN: 1834-7037, pp.53-60, 2017, Australasian Language Technology Association Workshop 2017: Proceedings of the workshop
Liste complète des métadonnées
https://halshs.archives-ouvertes.fr/halshs-01656683
Contributeur : Alexis Michaud <>
Soumis le : mardi 5 décembre 2017 - 21:33:39
Dernière modification le : mardi 27 mars 2018 - 14:16:07

Fichier

Adams_et_al2017_PhonemicTransc...
Fichiers éditeurs autorisés sur une archive ouverte

Licence

Distributed under a Creative Commons Paternité - Pas d'utilisation commerciale - Partage selon les Conditions Initiales 4.0 International License

Identifiants

  • HAL Id : halshs-01656683, version 1

Collections

UNIV-PARIS3 | LACITO | LPP | USPC

Citation

Oliver Adams, Trevor Cohn, Graham Neubig, Alexis Michaud. Phonemic transcription of low-resource tonal languages. Wong, Sze-Meng Jojo ; Haffari, Gholamreza. Australasian Language Technology Association Workshop 2017, Dec 2017, Brisbane, Australia. ISSN: 1834-7037, pp.53-60, 2017, Australasian Language Technology Association Workshop 2017: Proceedings of the workshop. 〈halshs-01656683〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

478

Téléchargements de fichiers

360

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD