Phonemic transcription of low-resource tonal languages

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.
Document type :
Conference papers
Complete list of metadatas

https://halshs.archives-ouvertes.fr/halshs-01656683
Contributor : Alexis Michaud <>
Submitted on : Tuesday, December 5, 2017 - 9:33:39 PM
Last modification on : Wednesday, May 15, 2019 - 7:19:40 AM

File

Adams_et_al2017_PhonemicTransc...
Publisher files allowed on an open archive

Licence


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

Identifiers

  • HAL Id : halshs-01656683, version 1

Citation

Oliver Adams, Trevor Cohn, Graham Neubig, Alexis Michaud. Phonemic transcription of low-resource tonal languages. Australasian Language Technology Association Workshop 2017, Dec 2017, Brisbane, Australia. pp.53-60. ⟨halshs-01656683⟩

Share

Metrics

Record views

646

Files downloads

464