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.

Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages

Domaine:

natural language processing

Type de record:

papermodel
Créateur:
LiaLev
Hôte:avatar
Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including spontaneous speech, environmental noise, and severely constrained datasets from under-documented languages. In this paper, we benchmark the performance of two fine-tuned multilingual ASR models, MMS and XLS-R, on five typologically diverse low-resource languages with control of training data duration. Our findings show that MMS is best suited when extremely small amounts of training data are available, whereas XLS-R shows parity performance once training data exceed one hour. We provide linguistically grounded analysis for further provide insights towards practical guidelines for field linguists, highlighting reproducible ASR adaptation approaches to mitigate the transcription bottleneck in language documentation.

Visit

arxiv.org

Tasks

automatic speech recognitionspeech processing

Tags

Computation and LanguageSoundAudio and Speech Processing

Similaires

Krishnateja244/Fine-tuning-of-ASR-models-on-low-resource-languagesFine Tuning Methods for Low-resource LanguagesFine-Tuning SLAM-ASR for Low-Resource Language Speech Recognition with High-Resource AlignmentFine-Tuning Whisper for Kinyarwanda: A Practical Approach to Low-Resource ASR DevelopmentBreaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource LanguagesEffective vocabulary expansion of multilingual language models for extremely low-resource languages

Krishnateja244/Fine-tuning-of-ASR-models-on-low-resource-languages

Fine tuning ASR models such as Wave2Vec2.0, Whisper, Nemo and MMS models on low-resource languages

Fine Tuning Methods for Low-resource Languages

The rise of Large Language Models has not been inclusive of all cultures. The models are mostly trai

Fine-Tuning SLAM-ASR for Low-Resource Language Speech Recognition with High-Resource Alignment

Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource

Fine-Tuning Whisper for Kinyarwanda: A Practical Approach to Low-Resource ASR Development

Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages

Pre-trained large language models (LLMs) have become a cornerstone of modern natural language proces

Effective vocabulary expansion of multilingual language models for extremely low-resource languages

Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource lan