Phone Based Keyword Spotting for Transcribing Very Low Resource Languages - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Phone Based Keyword Spotting for Transcribing Very Low Resource Languages

Résumé

We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust speech recognition system. This work is grounded in a very low-resource language documentation scenario where only a few minutes of recording have been transcribed for a given language so far. Experiments on two oral languages show that a pretrained universal phone recognizer, fine-tuned with only a few minutes of target language speech, can be used for spoken term detection through searches in phone confusion networks with a lexicon expressed as a finite state automaton. Experimental results show that a phone recognition based approach provides better overall performances than Dynamic Time Warping when working with clean data, and highlight the benefits of each methods for two types of speech corpus.
Fichier principal
Vignette du fichier
2021.alta-1.8.pdf (303.37 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03931103 , version 1 (09-01-2023)

Identifiants

  • HAL Id : hal-03931103 , version 1

Citer

Éric Le Ferrand, Steven Bird, Laurent Besacier. Phone Based Keyword Spotting for Transcribing Very Low Resource Languages. Proceedingd of the 19th Workshop of the Australasian Language Technology Association (ALTA) 2021, Dec 2021, Virtual, Australia. pp.79-86. ⟨hal-03931103⟩
15 Consultations
37 Téléchargements

Partager

Gmail Facebook X LinkedIn More