AlloVera: a multilingual allophone database - HAL-SHS - Sciences de l'Homme et de la Société Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

AlloVera: a multilingual allophone database

Résumé

We introduce a new resource, AlloVera, which provides mappings from 218 allophones to phonemes for 14 languages. Phonemes are contrastive phonological units, and allophones are their various concrete realizations, which are predictable from phonological context. While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription. AlloVera allows the training of speech recognition models that output phonetic transcriptions in the International Phonetic Alphabet (IPA), regardless of the input language. We show that a "universal" allophone model, Allosaurus, built with AlloVera, outperforms "universal" phonemic models and language-specific models on a speech-transcription task. We explore the implications of this technology (and related technologies) for the documentation of endangered and minority languages. We further explore other applications for which AlloVera will be suitable as it grows, including phonological typology.

Mots clés

Fichier principal
Vignette du fichier
MultilingualAllophoneResourceforNearUniversalASR.pdf (266.83 Ko) Télécharger le fichier
allovera.zip (30.55 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

halshs-02527046 , version 1 (31-03-2020)

Licence

Paternité - Pas d'utilisation commerciale - Partage selon les Conditions Initiales

Identifiants

  • HAL Id : halshs-02527046 , version 1

Citer

David R Mortensen, Xinjian Li, Patrick Littell, Alexis Michaud, Shruti Rijhwani, et al.. AlloVera: a multilingual allophone database. LREC 2020: 12th Language Resources and Evaluation Conference, European Language Resources Association, May 2020, Marseille, France. ⟨halshs-02527046⟩
277 Consultations
358 Téléchargements

Partager

Gmail Facebook X LinkedIn More