myMediWhisper: Construction of Burmese Medical Speech Corpus and Whisper Fine-Tuning for Clinical Dialogue ASR

2026-08-11

AI Summary

This study addresses the low speech recognition accuracy of Burmese medical audio in existing large models, primarily due to data scarcity in clinical settings and environmental noise. To tackle this challenge, we present the first high-quality Burmese medical speech corpus comprising 28 hours of native-speaker-recorded and validated utterances. Leveraging this dataset, we fine-tune the Whisper model using both full-parameter fine-tuning (FFT) and parameter-efficient LoRA-based fine-tuning (PEFT), further enhancing robustness through waveform- and spectrogram-level data augmentation to mitigate the effects of noise and reverberation. Our best-performing system, myMediWhisper-Medium, achieves a word error rate (WER) of 23.44% without data augmentation, significantly outperforming larger general-domain fine-tuned models and establishing a new state-of-the-art result for Burmese medical speech recognition.

Abstract

Although Whisper models benefit from large-scale multilingual pre-training, their performance on Burmese medical speech remains limited. This work presents a Burmese medical speech recognition framework built on a high-quality 28-hour corpus recorded and validated by native speakers. We fine-tune Whisper models using full fine-tuning (FFT) and parameter-efficient fine-tuning (PEFT) with LoRA. To evaluate robustness, we apply waveform- and spectrogram-level data augmentation under controlled noise and simulated room acoustics. While augmentation reduces performance on clean speech, it significantly improves robustness in noisy and reverberant environments across FFT and PEFT settings. Our best-performing system, fully fine-tuned myMediWhisper-Medium without augmentation, achieves a state-of-the-art Word Error Rate (WER) of 23.44%, outperforming much larger general-domain fine-tuned models. Dataset and other resources can be found at the Huggingface repository: https://huggingface.co/datasets/LULab/mediTalk-mm-rdy.

Problem

• Burmese medical speech
• automatic speech recognition
• Whisper models
• clinical dialogue
• low-resource ASR

Innovation

• Burmese medical ASR
• Whisper fine-tuning
• LoRA
• data augmentation
• speech corpus