User-Friendly Automatic Transcription of Low-Resource Languages: Plugging ESPnet into Elpis

Adams, Oliver; Galliot, Benjamin; Wisniewski, Guillaume; Lambourne, Nicholas; Foley, Ben; Sanders-Dwyer, Rahasya; Wiles, Janet; Michaud, Alexis; Guillaume, Séverine; Besacier, Laurent; Cox, Christopher; Aplonova, Katya; Jacques, Guillaume; Hill, Nathan W.

doi:10.33011/computel.v1i.969

Cited by 8 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For orthographic systems, the pronunciation dictionary is statistical method. For details of the phonemic transcription system used in Elpis, see Adams et al (2020).…”

Section: Workflowmentioning

confidence: 99%

Managing Transcription Data for Automatic Speech Recognition with Elpis

Foley¹,

Esch²,

San³

2022

The Open Handbook of Linguistic Data Management

View full text Add to dashboard Cite

“…For orthographic systems, the pronunciation dictionary is statistical method. For details of the phonemic transcription system used in Elpis, see Adams et al (2020).…”

Section: Workflowmentioning

confidence: 99%

Managing Transcription Data for Automatic Speech Recognition with Elpis

Foley¹,

Esch²,

San³

2022

The Open Handbook of Linguistic Data Management

View full text Add to dashboard Cite

“…What it comes to the usability and accessibility of ASR systems, Adams et al (2020) describe their work on a user friendly interface for the language workers to train and use ASR tools. Cox (2019) has created an ELAN plugin, and the same approach was recently extended for DeepSpeech by Partanen (2021).…”

Section: Prior Workmentioning

confidence: 99%

The Relevance of the Source Language in Transfer Learning for ASR

et al. 2021

View full text Add to dashboard Cite

This study presents new experiments on Zyrian Komi speech recognition. We use Deep-Speech to train ASR models from a language documentation corpus that contains both contemporary and archival recordings. Earlier studies have shown that transfer learning from English and using a domain matching Komi language model both improve the CER and WER. In this study we experiment with transfer learning from a more relevant source language, Russian, and including Russian text in the language model construction. The motivation for this is that Russian and Komi are contemporary contact languages, and Russian is regularly present in the corpus. We found that despite the close contact of Russian and Komi, the size of the English speech corpus yielded greater performance when used as the source language. Additionally, we can report that already an update in DeepSpeech version improved the CER by 3.9% against the earlier studies, which is an important step in the development of Komi ASR.

show abstract

“…In practice, E2E ASR systems are less affected by linguistic constraints and are generally easier to train. The benefits of such systems are reflected in the recent trends of using end-to-end ASR for EL documentation (Adams et al, 2020;Thai et al, 2020;Matsuura et al, 2020;Hjortnaes et al, 2020;Shi et al, 2021).…”

Section: End-to-end Asr Experiments 41 Experiments Settingsmentioning

confidence: 99%

“…Interest in applying machine learning to endangered language documentation is also manifested in four biennial workshops on this topic, the first in 2014 (Good et al, 2021). Finally, articles directly referencing ASR of endangered languages have become increasingly common over the last five years (Adams et al, , 2020Ćavar et al, 2016;Foley et al, 2018Foley et al, , 2019Gupta and Boulianne, 2020;Michaud et al, 2018;Mitra et al, 2016;Shi et al, 2021).…”

mentioning

confidence: 99%

End-to-End Automatic Speech Recognition: Its Impact on the Workflowin Documenting Yoloxóchitl Mixtec

Amith¹,

Shi²,

García³

2021

Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas

View full text Add to dashboard Cite

This paper describes three open access Yoloxóchitl Mixtec corpora and presents the results and implications of end-to-end automatic speech recognition for endangered language documentation. Two issues are addressed. First, the advantage for ASR accuracy of targeting informational (BPE) units in addition to, or in substitution of, linguistic units (word, morpheme, morae) and then using ROVER for system combination. BPE units consistently outperform linguistic units although the best results are obtained by system combination of different BPE targets. Second, a case is made that for endangered language documentation, ASR contributions should be evaluated according to extrinsic criteria (e.g., positive impact on downstream tasks) and not simply intrinsic metrics (e.g., CER and WER). The extrinsic metric chosen is the level of reduction in the human effort needed to produce high-quality transcriptions for permanent archiving.

show abstract

User-Friendly Automatic Transcription of Low-Resource Languages: Plugging ESPnet into Elpis

Cited by 8 publications

References 36 publications

Managing Transcription Data for Automatic Speech Recognition with Elpis

Managing Transcription Data for Automatic Speech Recognition with Elpis

The Relevance of the Source Language in Transfer Learning for ASR

End-to-End Automatic Speech Recognition: Its Impact on the Workflowin Documenting Yoloxóchitl Mixtec

Contact Info

Product

Resources

About