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.

Strategies for improving low resource speech to text translation relying on pre-trained ASR models

Domaine:

natural language processing

Type de record:

paper
Créateur:
KesSarPavMac
Hôte:avatar
This paper presents techniques and findings for improving the performance of low-resource speech to text translation (ST). We conducted experiments on both simulated and real-low resource setups, on language pairs English - Portuguese, and Tamasheq - French respectively. Using the encoder-decoder framework for ST, our results show that a multilingual automatic speech recognition system acts as a good initialization under low-resource scenarios. Furthermore, using the CTC as an additional objective for translation during training and decoding helps to reorder the internal representations and improves the final translation. Through our experiments, we try to identify various factors (initializations, objectives, and hyper-parameters) that contribute the most for improvements in low-resource setups. With only 300 hours of pre-training data, our model achieved 7.3 BLEU score on Tamasheq - French data, outperforming prior published works from IWSLT 2022 by 1.6 points.

Visit

arxiv.org

Tasks

speech translationspeech processingmachine translation

Languages

Tamasheq

Tags

Computation and LanguageSoundAudio and Speech Processing

Similaires

IMPROVING ARABIC TEXT SUMMARIZATION USING ADVANCED PRE-TRAINED MODELSLow-Resource Hate Speech Detection in English-Swahili Code-Switched Text Using Fine-Tuning of Pre-trained Language ModelsDisfluent-to-Fluent Tunisian Dialect Speech Translation with Fine-Tuning Pre-trained Language ModelsPre-Trained Transformer-Based Models for Text Classification Using Low-Resourced Ewe LanguageImproving End-to-End Speech Translation for the Low Resource Language Fongbe to FrenchImproving Pre-trained Segmentation Models using Post-Processing

IMPROVING ARABIC TEXT SUMMARIZATION USING ADVANCED PRE-TRAINED MODELS

The exponential growth of online content has made the task of locating specific information increasi

Low-Resource Hate Speech Detection in English-Swahili Code-Switched Text Using Fine-Tuning of Pre-trained Language Models

The use of social media in East Africa has grown rapidly, and with it, the spread of hate speech has

Disfluent-to-Fluent Tunisian Dialect Speech Translation with Fine-Tuning Pre-trained Language Models

Pre-Trained Transformer-Based Models for Text Classification Using Low-Resourced Ewe Language

Despite a few attempts to automatically crawl Ewe text from online news portals and magazines, the A

Improving End-to-End Speech Translation for the Low Resource Language Fongbe to French

This study addresses the challenges of end-to-end (E2E) Speech-to-Text Translation (STT) for the low

Improving Pre-trained Segmentation Models using Post-Processing

Gliomas are the most common malignant brain tumors in adults and are among the most lethal. Despite