1 |
Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)
|
|
Guillaume, Séverine; Wisniewski, Guillaume; Macaire, Cécile; Jacques, Guillaume; Michaud, Alexis; Galliot, Benjamin; Coavoux, Maximin; Rossato, Solange; Nguyễn, Minh-Châu; Fily, Maxime
|
|
In: https://halshs.archives-ouvertes.fr/halshs-03647315 ; 2022 (2022)
|
|
Abstract:
Accepted for publication in Proceedings of ComputEL-5: Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages ; This is a report on results obtained in the development of speech recognition tools intended to support linguistic documentation efforts. The test case is an extensive fieldwork corpus of Japhug, an endangered language of the Trans-Himalayan (Sino-Tibetan) family. The goal is to reduce the transcription workload of field linguists. The method used is a deep learning approach based on the language-specific tuning of a generic pre-trained representation model, XLS-R, using a Transformer architecture. We note difficulties in implementation, in terms of learning stability. But this approach brings significant improvements nonetheless. The quality of phonemic transcription is improved over earlier experiments; and most significantly, the new approach allows for reaching the stage of automatic word recognition. Subjective evaluation of the tool by the author of the training data confirms the usefulness of this approach.
|
|
Keyword:
[SHS.LANGUE]Humanities and Social Sciences/Linguistics; Automatic Speech Recognition
|
|
URL: https://halshs.archives-ouvertes.fr/halshs-03647315/file/ComputEL_5_Japhug_ASR.pdf https://halshs.archives-ouvertes.fr/halshs-03647315/document https://halshs.archives-ouvertes.fr/halshs-03647315
|
|
BASE
|
|
Hide details
|
|
2 |
Fine-tuning pre-trained models for Automatic Speech Recognition: experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-03647315 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
L'intonation dans les langues tonales : des réflexions générales et deux études de cas
|
|
|
|
In: ISSN: 0071-190X ; EISSN: 1965-0477 ; Études de linguistique appliquée : revue de didactologie des langues-cultures ; https://halshs.archives-ouvertes.fr/halshs-03189736 ; Études de linguistique appliquée : revue de didactologie des langues-cultures, Klincksieck (Didier Erudition jusqu'en 2003), 2021, 199 (1) (2021)
|
|
BASE
|
|
Show details
|
|
4 |
L'intonation dans les langues tonales : des réflexions générales et deux études de cas
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-03189736 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
5 |
L'intonation dans les langues tonales : des réflexions générales et deux études de cas
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-03189736 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
6 |
A Literature Review of the Use of the Term Extensive Reading in Second Language Literature: Who Was the First to Use It? ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
L'intonation dans les langues tonales : des réflexions générales et deux études de cas
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-03189736 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
8 |
L'intonation dans les langues tonales : des réflexions générales et deux études de cas
|
|
|
|
In: ISSN: 0071-190X ; EISSN: 1965-0477 ; Études de linguistique appliquée : revue de didactologie des langues-cultures ; https://halshs.archives-ouvertes.fr/halshs-03189736 ; Études de linguistique appliquée : revue de didactologie des langues-cultures, Klincksieck (Didier Erudition jusqu'en 2003), 2021, 199 (1) (2021)
|
|
BASE
|
|
Show details
|
|
9 |
International Phonetic Alphabet (Vietnamese version) ; Alphabet Phonétique International (version vietnamienne) ; Bảng phiên âm quốc tế. Bản tiếng Việt
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-02469549 ; 2020 (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Voix de « ceux qui ne sont rien » en Asie du sud-est
|
|
|
|
In: ISSN: 0396-891X ; EISSN: 2266-1816 ; Cahiers de Littérature Orale ; https://halshs.archives-ouvertes.fr/halshs-02519293 ; Cahiers de Littérature Orale, Presses de l'Inalco, 2020 (2020)
|
|
BASE
|
|
Show details
|
|
11 |
International Phonetic Alphabet (Vietnamese version) ; Alphabet Phonétique International (version vietnamienne) ; Bảng phiên âm quốc tế. Bản tiếng Việt
|
|
|
|
In: https://halshs.archives-ouvertes.fr/halshs-02469549 ; 2020 (2020)
|
|
BASE
|
|
Show details
|
|
12 |
A glottalized tone in Muong (Vietic): a pilot study based on audio and electroglottographic recordings
|
|
|
|
In: ICPhS XIX (19th International Congress of Phonetic Sciences ) ; https://hal-univ-paris3.archives-ouvertes.fr/hal-02088021 ; ICPhS XIX (19th International Congress of Phonetic Sciences ), Melbourne, Australia. 2019 (2019)
|
|
BASE
|
|
Show details
|
|
13 |
A glottalized tone in Muong (Vietic): a pilot study based on audio and electroglottographic recordings
|
|
|
|
In: ICPhS XIX (19th International Congress of Phonetic Sciences ) ; https://hal-univ-paris3.archives-ouvertes.fr/hal-02088021 ; ICPhS XIX (19th International Congress of Phonetic Sciences ), Melbourne, Australia. 2019 (2019)
|
|
BASE
|
|
Show details
|
|
14 |
Z in company names: trendy clothing for a typical Vietnamese sound
|
|
|
|
In: Mon-Khmer Studies ; https://halshs.archives-ouvertes.fr/halshs-01413258 ; Mon-Khmer Studies, 2016, 45, pp.53-65 (2016)
|
|
BASE
|
|
Show details
|
|
15 |
Z in company names: trendy clothing for a typical Vietnamese sound
|
|
|
|
In: Mon-Khmer Studies ; https://halshs.archives-ouvertes.fr/halshs-01413258 ; Mon-Khmer Studies, 2016, 45, pp.53-65 (2016)
|
|
BASE
|
|
Show details
|
|
16 |
Phonetic insights into a simple level-tone system: ‘careful’ vs. ‘impatient’ realizations of Naxi High, Mid and Low tones
|
|
|
|
In: ICPhS XVIII (18th International Congress of Phonetic Sciences) ; https://halshs.archives-ouvertes.fr/halshs-01148765 ; ICPhS XVIII (18th International Congress of Phonetic Sciences), Aug 2015, Glasgow, United Kingdom (2015)
|
|
BASE
|
|
Show details
|
|
17 |
Strata of standardization: the Phong Nha dialect of Vietnamese (Quảng Bình Province) in historical perspective
|
|
|
|
In: ISSN: 0731-3500 ; Linguistics of the Tibeto-Burman Area ; https://halshs.archives-ouvertes.fr/halshs-01141389 ; Linguistics of the Tibeto-Burman Area, Dept. of Linguistics, University of California, 2015, 38 (1), pp.124-162. ⟨10.1075/ltba.38.1.04mic⟩ ; https://benjamins.com/#catalog/journals/ltba/main (2015)
|
|
BASE
|
|
Show details
|
|
18 |
Strata of standardization: the Phong Nha dialect of Vietnamese (Quảng Bình Province) in historical perspective
|
|
|
|
In: ISSN: 0731-3500 ; Linguistics of the Tibeto-Burman Area ; https://halshs.archives-ouvertes.fr/halshs-01141389 ; Linguistics of the Tibeto-Burman Area, Dept. of Linguistics, University of California, 2015, 38 (1), pp.124-162. ⟨10.1075/ltba.38.1.04mic⟩ ; https://benjamins.com/#catalog/journals/ltba/main (2015)
|
|
BASE
|
|
Show details
|
|
|
|