, Le présent travail s'inscrit en outre dans le cadre du Labex « Fondements empiriques de la linguistique

. Références,

O. Adams, Automatic understanding of unwritten languages, 2017.

O. Adams, T. Cohn, G. Neubig, H. Cruz, S. Bird et al., Evaluating phonemic transcription of low-resource tonal languages for language documentation, Proceedings of LREC 2018 (Language Resources and Evaluation Conference, pp.3356-3365, 2018.
URL : https://hal.archives-ouvertes.fr/halshs-01709648

O. Adams, T. Cohn, G. Neubig, and A. Michaud, Phonemic transcription of low-resource tonal languages, Proceedings of ALTA 2017 (Australasian Language Technology Association Workshop), pp.53-60, 2017.
URL : https://hal.archives-ouvertes.fr/halshs-01656683

G. Adda, S. Stüker, M. Adda-decker, O. Ambouroue, L. Besacier et al., Breaking the unwritten language barrier: The BULB Project. SLTU-2016 5th Workshop on Spoken Language Technologies for Under-Resourced Languages 09-12, pp.8-14, 2016.
URL : https://hal.archives-ouvertes.fr/halshs-01428027

M. Brunelle, D. Chow, and T. N. Nguy?n, Effects of lexical frequency and lexical category on the duration of Vietnamese syllables, Proceedings of ICPhS XVIII. International Congress of the Phonetic Sciences XVIII, 2015.

L. Dilley and S. Shattuck-hufnagel, Glottalization of word-initial vowels as a function of prosodic structure, Journal of Phonetics, vol.24, pp.423-444, 1996.

T. N. Do, A. Michaud, and E. Castelli, Towards the automatic processing of Yongning Na (Sino-Tibetan): Developing a "light" acoustic model of the target language and testing "heavyweight" models from five national languages, Proceedings of the 4th International Workshop on Spoken Language Technologies for Under-Resourced Languages, pp.153-160, 2014.
URL : https://hal.archives-ouvertes.fr/halshs-00980431

M. Durand, . Didier, B. Foley, J. Arnold, R. Coto-solano et al., Building speech recognition systems for language documentation: The CoEDL Endangered Language Pipeline and Inference System (ELPIS), Proceedings of the 6th Intl. Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU), pp.200-204, 1930.

B. Foley, A. Rakhi, N. Lambourne, N. Buckeridge, and J. Wiles, Elpis, an accessible speech-to-text tool, Proceedings of Interspeech, pp.306-310, 2019.

C. Fougeron, Prosodically conditioned articulatory variations: A review. UCLA Working Papers in Phonetics, vol.97, pp.1-68, 1999.

C. Fougeron, Articulatory properties of initial segments in several prosodic constituents in French, Journal of Phonetics, vol.29, issue.2, pp.109-135, 2001.
URL : https://hal.archives-ouvertes.fr/halshs-00184988

J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, and D. S. Pallett, DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1. NASA STI/Recon Technical, p.93, 1993.

J. J. Godfrey, E. C. Holliman, and J. Mcdaniel, SWITCHBOARD: Telephone speech corpus for research and development, 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol.1, pp.517-520, 1992.

A. Gomez-marin, Causal circuit explanations of behavior: Are necessity and sufficiency necessary and sufficient?, Decoding neural circuit structure and function, pp.283-306, 2017.

A. Graves, A. Mohamed, and G. Hinton, Speech recognition with deep recurrent neural networks. ICASSP 2013 -2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.6645-6649, 2013.

S. Greenberg, J. Hollenback, and D. Ellis, Insights into spoken language gleaned from phonetic transcription of the Switchboard corpus, Proceedings of the International Conference on Spoken Language Processing, vol.96, pp.24-27, 1996.

N. Hjortnaes, N. Partanen, M. Rießler, and F. M. Tyers, Towards a speech recognizer for Komi, an endangered and low-resource Uralic language, Proceedings of the Sixth International Workshop on Computational Linguistics of Uralic Languages, pp.31-37, 2020.

F. Hohman, A. Head, R. Caruana, R. Deline, and S. M. Drucker, Gamut: A design probe to understand how data scientists understand Machine Learning models, ACM CHI Conference on Human Factors in Computing Systems, 2019.

G. Jacques and A. Michaud, Approaching the historical phonology of three highly eroded Sino-Tibetan languages: Naxi, Na and Laze, Diachronica, vol.28, issue.4, pp.468-498, 2011.
URL : https://hal.archives-ouvertes.fr/halshs-00537990

Z. Jiang, F. F. Xu, J. Araki, and G. Neubig, How can we know what language models know?, 2019.

R. Jimerson and E. Hommeaux, ASR for documenting acutely under-resourced indigenous languages, Proceedings of LREC 2018 (Language Resources and Evaluation Conference, pp.4161-4166, 2018.

D. Jones, The Phoneme, its Nature and Use, 1950.

J. Kuang, Creaky voice as a function of tonal categories and prosodic boundaries, Proceedings of Interspeech 2017, pp.3216-3220, 2017.

S. Lapuschkin, S. Wäldchen, A. Binder, G. Montavon, W. Samek et al.,

, Unmasking Clever Hans predictors and assessing what machines really learn, Nature Communications, vol.10, issue.1, p.1096

L. Lidz, A descriptive grammar of Yongning Na (Mosuo), 2010.

. Lidz-dissertation, P. Littell, A. Kazantseva, R. Kuhn, A. Pine et al., Indigenous language technologies in Canada: Assessment, challenges, and successes, Proceedings of the 27th International Conference on Computational Linguistics, pp.2620-2632, 2018.

B. Michailovsky, M. Mazaudon, A. Michaud, S. Guillaume, A. François et al., Documenting and researching endangered languages: The Pangloss Collection. Language Documentation and Conservation, vol.8, pp.119-135, 2014.
URL : https://hal.archives-ouvertes.fr/halshs-01003734

A. Michaud, Phonemic and tonal analysis of Yongning Na, vol.37, pp.159-196, 2008.
URL : https://hal.archives-ouvertes.fr/halshs-00358610

A. Michaud, Monosyllabicization: Patterns of evolution in Asian languages, Monosyllables: From phonology to typology, pp.115-130, 2012.
URL : https://hal.archives-ouvertes.fr/halshs-00436432

A. Michaud, Dictionnaire na-chinois-français, 2015.

A. Michaud, Tone in Yongning Na: Lexical tones and morphotonology, 2017.
URL : https://hal.archives-ouvertes.fr/halshs-01094049

A. Michaud, O. Adams, T. Cohn, G. Neubig, and S. Guillaume, Integrating automatic transcription into the language documentation workflow: Experiments with Na data and the Persephone toolkit. Language Documentation and Conservation, vol.12, pp.393-429, 2018.
URL : https://hal.archives-ouvertes.fr/halshs-01841979

A. Michaud, O. Adams, C. Cox, and S. Guillaume, Phonetic lessons from automatic phonemic transcription: Preliminary reflections on Na (Sino-Tibetan) and Tsuut'ina (Dene) data, Proceedings of ICPhS XIX (19th International Congress of Phonetic Sciences). ICPhS XIX (19th International Congress of Phonetic Sciences), 2019.
URL : https://hal.archives-ouvertes.fr/halshs-02059313

A. Michaud, S. Guillaume, G. Jacques, ?. M?c, M. Jacobson et al., Contribuer au progrès solidaire des recherches et de la documentation: La Collection Pangloss et la Collection AuCo. Actes de La Conférence Conjointe JEP-TALN-RECITAL 2016, vol.1, pp.155-163, 2016.

A. Michaud, A. Hardie, S. Guillaume, and M. Toda, Combining documentation and research: Ongoing work on an endangered language, Proceedings of IALP 2012 (2012 International Conference on Asian Language Processing, pp.169-172, 2012.
URL : https://hal.archives-ouvertes.fr/halshs-00731261

G. Montavon, W. Samek, and K. Müller, Methods for interpreting and understanding deep neural networks, Digital Signal Processing, vol.73, pp.1-15, 2017.

G. Neubig, S. Rijhwani, A. Palmer, J. Mackenzie, H. Cruz et al., A summary of the first Workshop on Language Technology for Language Documentation and Revitalization, Proceedings of the 1st Joint SLTU (Spoken Language Technologies for Under-Resourced Languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop, 2020.

V. Pratap, A. Hannun, Q. Xu, J. Cai, J. Kahn et al., wav2letter++: The fastest open-source speech recognition system, 2018.

B. Shao and R. Ridouane, La « voyelle apicale » en chinois de Jixi: Caractéristiques acoustiques et comportement phonologique. XXXIIe Journées d'Études, pp.685-693, 2018.

I. Stavness, B. Gick, D. Derrick, and S. Fels, Biomechanical modeling of English /r/ variants, The Journal of the Acoustical Society of America, vol.131, issue.5, 2012.

N. Thieberger, LD&C possibilities for the next decade. Language Documentation and Conservation, vol.11, pp.1-4, 2017.

N. Tomashenko and Y. Estève, Impact des techniques d'adaptation au locuteur dans l'espace des paramètres pour des modèles acoustiques purement neuronaux, XXXIIe Journées d'Études, pp.559-567, 2018.

N. Tomashenko, Y. Khokhlov, and Y. Estève, Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models, 2020.
URL : https://hal.archives-ouvertes.fr/hal-02551714

J. Vaissière, The perception of intonation, Handbook of Speech Perception, pp.236-263, 2004.

J. Vaissière, On the acoustic and perceptual characterization of reference vowels in a cross-language perspective, Proceedings of ICPhS XVII. ICPhS XVII, p.461, 2011.

J. Vaissière, Proposals for a representation of sounds based on their main acousticoperceptual properties, Tones and Features, pp.306-330, 2011.

D. Van-esch, B. Foley, N. San, S. Watanabe, T. Hori et al., Future directions in technological support for language documentation, Proceedings of the Workshop on Computational Methods for Endangered Languages, vol.1, 2018.

G. Wisniewski, S. Guillaume, and A. Michaud, Phonemic transcription of low-resource languages: To what extent can preprocessing be automated?, Proceedings of the 1st Joint SLTU (Spoken Language Technologies for Under-Resourced Languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop. 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop, 2020.
URL : https://hal.archives-ouvertes.fr/hal-02513914

M. Wu, F. Liu, and T. Cohn, Evaluating the utility of hand-crafted features in sequence labelling, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp.2850-2856, 2018.