paper-with-me

홈 › Papers

Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition

2024-09-25 · Andrés Piñeiro-Martín, Carmen García-Mateo, Laura Docío-Fernández, María del Carmen López-Pérez, Georg Rehm

This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to facilitate the integration of low-resource languages into pre-trained multilingual ASR models within the context of continual multilingual learning. We fine-tune the Whisper multilingual ASR model on five high-resource languages and one low-resource language, employing language-weighted dynamic cross-entropy and data augmentation. The results show a remarkable 6.69% word error rate (WER) reduction for the low-resource language compared to the fine-tuned model without applying our approach, and a 48.86% WER reduction compared to the original Whisper model. In addition, our approach yields an average WER reduction of 3.29% across the six languages, showing no degradation for the high-resource languages.

📄 PDF Abstract BibTeX arXiv:2409.16954

Code (1)

andrespimartin/weighted-x-entropy-asr 공식 구현 pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentationspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

A Multilingual Topic Model for Learning Weighted Topic Links Across Corpora with Low Comparability

2019-11-01 · IJCNLP 2019 11 · Weiwei Yang, Jordan Boyd-Graber, Philip Resnik

Multilingual topic models (MTMs) learn topics on documents in multiple languages. Past models align topics across languages by implicitly assuming the documents in different languages are highly comparable, often a false…

Topic Models

Language-specific Neurons Do Not Facilitate Cross-Lingual Transfer

2025-03-21 · Soumen Kumar Mondal, Sayambhu Sen, Abhishek Singhania, Preethi Jyothi

Multilingual large language models (LLMs) aim towards robust natural language understanding across diverse languages, yet their performance significantly degrades on low-resource languages. This work explores whether exi…

Cross-Lingual TransferNatural Language Understanding

IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia

2026-03-18 · Priyaranjan Pattnayak, Sanchari Chowdhuri arxiv

As large language models (LLMs) are deployed in multilingual settings, their safety behavior in culturally diverse, low-resource languages remains poorly understood. We present the first systematic evaluation of LLM safe…

Beyond WER: Probing Whisper's Sub-token Decoder Across Diverse Language Resource Levels

2025-09-29 · Siyu Liang, Nicolas Ballier, Gina-Anne Levow, Richard Wright arxiv

While large multilingual automatic speech recognition (ASR) models achieve remarkable performance, the internal mechanisms of the end-to-end pipeline, particularly concerning fairness and efficacy across languages, remai…

Speech Recognition

Phoneme Level Language Models for Sequence Based Low Resource ASR

2019-02-20 · Siddharth Dalmia, Xinjian Li, Alan W. black, Florian Metze

Building multilingual and crosslingual models help bring different languages together in a language universal space. It allows models to share parameters and transfer knowledge across languages, enabling faster and bette…

Language ModelingLanguage Modelling