Phonetic lessons from automatic phonemic transcription: preliminary reflections on Na (Sino-Tibetan) and Tsuut’ina (Dene) data

Abstract : Automatic phonemic transcription tools now reach high levels of accuracy on a single speaker with relatively small amounts of training data: on the order of 100 to 250 minutes of transcribed speech. Beyond its practical usefulness for language documentation, use of automatic transcription also yields some insights for phoneticians. The present report illustrates this by going into qualitative error analysis on two test cases, Yongning Na (Sino-Tibetan) and Tsuut’ina (Dene). Among other benefits, error analysis allows for a renewed exploration of phonetic detail: examining the output of phonemic transcription software compared with spectrographic and aural evidence. From a methodological point of view, the present report is intended as a case study in Computational Language Documentation: an interdisciplinary approach that associates fieldworkers (“diversity linguists”) and computer scientists with phoneticians/phonologists.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://halshs.archives-ouvertes.fr/halshs-02059313
Contributor : Alexis Michaud <>
Submitted on : Friday, March 29, 2019 - 10:03:32 AM
Last modification on : Wednesday, May 15, 2019 - 2:59:32 AM

File

ICPhS2019_PhoneticLessons_Na_T...
Files produced by the author(s)

Licence


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

Identifiers

  • HAL Id : halshs-02059313, version 2

Données associées

Citation

Alexis Michaud, Oliver Adams, Christopher Cox, Séverine Guillaume. Phonetic lessons from automatic phonemic transcription: preliminary reflections on Na (Sino-Tibetan) and Tsuut’ina (Dene) data. 2019. ⟨halshs-02059313v2⟩

Share

Metrics

Record views

41

Files downloads

80