VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain

TL;DR

VietMed introduces the largest public Vietnamese medical speech dataset and pre-trained models, significantly advancing speech recognition in the medical domain with comprehensive coverage and improved accuracy.

Contribution

The paper presents VietMed, the largest Vietnamese medical speech dataset and associated pre-trained models, covering all disease groups and accents, and demonstrates strong generalization of models without medical data in pre-training.

Findings

VietMed is the largest public Vietnamese medical speech dataset.

Pre-trained models outperform state-of-the-art on medical ASR tasks.

Models generalize well even without medical data in pre-training.

Abstract

Due to privacy restrictions, there's a shortage of publicly available speech recognition datasets in the medical domain. In this work, we present VietMed - a Vietnamese speech recognition dataset in the medical domain comprising 16h of labeled medical speech, 1000h of unlabeled medical speech and 1200h of unlabeled general-domain speech. To our best knowledge, VietMed is by far the world's largest public medical speech recognition dataset in 7 aspects: total duration, number of speakers, diseases, recording conditions, speaker roles, unique medical terms and accents. VietMed is also by far the largest public Vietnamese speech dataset in terms of total duration. Additionally, we are the first to present a medical ASR dataset covering all ICD-10 disease groups and all accents within a country. Moreover, we release the first public large-scale pre-trained models for Vietnamese ASR, w2v2-Viet and XLSR-53-Viet, along with the first public large-scale fine-tuned models for medical ASR. Even without any medical data in unsupervised pre-training, our best pre-trained model XLSR-53-Viet generalizes very well to the medical domain by outperforming state-of-the-art XLSR-53, from 51.8% to 29.6% WER on test set (a relative reduction of more than 40%). All code, data and models are made publicly available: https://github.com/leduckhai/MultiMed/tree/master/VietMed.