Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Evaluating phonemic transcription of low-resource tonal languages for language documentation

Abstract : Transcribing speech is an important part of language documentation, 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 up to 50 minutes for Chatino, and up to 224 minutes for Na. 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Cited literature [36 references]  Display  Hide  Download
Contributor : Alexis Michaud Connect in order to contact the contributor
Submitted on : Tuesday, February 20, 2018 - 7:59:13 AM
Last modification on : Tuesday, October 19, 2021 - 6:51:47 PM
Long-term archiving on: : Monday, May 21, 2018 - 12:26:47 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution - NonCommercial - ShareAlike 4.0 International License


  • HAL Id : halshs-01709648, version 2


Oliver Adams, Trevor Cohn, Graham Neubig, Hilaria Cruz, Steven Bird, et al.. Evaluating phonemic transcription of low-resource tonal languages for language documentation. 2018. ⟨halshs-01709648v2⟩



Record views


Files downloads