Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis

Domaine:

natural language processing

Type de record:

papersoftwaremodel
Créateur:
AdaGalWisLam
Éditeur:
AtoLanLabThe
Éditeur:
CCSD
Hôte:avatar
International audience This paper reports on progress integrating the speech recognition toolkit ESPnet into Elpis, a web front-end originally designed to provide access to the Kaldi automatic speech recognition toolkit. The goal of this work is to make end-to-end speech recognition models available to language workers via a user-friendly graphical interface. Encouraging results are reported on (i) development of an ESPnet recipe for use in Elpis, with preliminary results on data sets previously used for training acoustic models with the Persephone toolkit along with a new data set that had not previously been used in speech recognition, and (ii) incorporating ESPnet into Elpis along with UI enhancements and a CUDA-supported Dockerfile.

Visit

shs.hal.science

Tasks

automatic speech recognitionspeech processing

Tags

automatic transcriptionlanguage documentationendangered languagesautomatic speech recognitionComputational Language DocumentationMESH: reconnaissance automatique de la paroleMESH: transcription automatiqueMESH: Traitement Automatique des Langues NaturellesMESH: documentation linguistiqueMESH: langues en danger+5

Licenses

https://creativecommons.org/licenses/by-nc-sa/4.0/info:eu-repo/semantics/OpenAccess

Similaires

SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian LanguagesFast transcription of speech in low-resource languagesAutomatic Keyboard Layout Design for Low-Resource Latin-Script LanguagesMachine Assisted Translation of Wikipedia Articles into Low Resource LanguagesEnhancing Automatic Speech Recognition for Child Speech in Low-Resource LanguagesSustainable dictionaries of low-resource languages: The “Dictionaria” series and its user-friendliness

SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages

While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities i

Fast transcription of speech in low-resource languages

We present software that, in only a few hours, transcribes forty hours of recorded speech in a surpr

Automatic Keyboard Layout Design for Low-Resource Latin-Script Languages

We present our approach to automatically designing and implementing keyboard layouts on mobile devic

Machine Assisted Translation of Wikipedia Articles into Low Resource Languages

Wikipedia is the largest encyclopedia ever assembled with the vision of enabling every human being to freely share in the sum of all knowledge. Wikipedia currently has a total of more than six million articles and over 17 billion words in its English edition. Unfor

Enhancing Automatic Speech Recognition for Child Speech in Low-Resource Languages

Automatic speech recognition (ASR) for children is demanding because their speech differs c

Sustainable dictionaries of low-resource languages: The “Dictionaria” series and its user-friendliness