# Enhancing ASR Performance in the Medical Domain for Dravidian Languages

arXiv: https://arxiv.org/abs/2604.19797 · HTML: https://mlsanity.com/paper/2604.19797/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [ASR Error Correction and Domain Adaptation Using Machine Translation](https://mlsanity.com/paper/2003.07692/) (2020)
- [Towards Building ASR Systems for the Next Billion Users](https://mlsanity.com/paper/2111.03945/) (2021)
- [IndicBART: A Pre-trained Model for Indic Natural Language Generation](https://mlsanity.com/paper/2109.02903/) (2021)
- [SynthASR: Unlocking Synthetic Data for Speech Recognition](https://mlsanity.com/paper/2106.07803/) (2021)
- [Towards Building Text-To-Speech Systems for the Next Billion Users](https://mlsanity.com/paper/2211.09536/) (2022)
- [Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation](https://mlsanity.com/paper/2410.13198/) (2024)
- [Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition](https://mlsanity.com/paper/2212.08703/) (2022)
- [An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR](https://mlsanity.com/paper/2503.08954/) (2025)
- [Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding](https://mlsanity.com/paper/2307.12134/) (2023)
- [A Unified Framework for Collecting Text-to-Speech Synthesis Datasets for 22 Indian Languages](https://mlsanity.com/paper/2410.14197/) (2024)
- [A Domain Adaptation Framework for Speech Recognition Systems with Only Synthetic data](https://mlsanity.com/paper/2501.12501/) (2025)
- [Adopting Whisper for Confidence Estimation](https://mlsanity.com/paper/2502.13446/) (2025)
- [TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASR](https://mlsanity.com/paper/2401.03251/) (2024)

## Abstract (arXiv)

Automatic Speech Recognition (ASR) for low-resource Dravidian languages like Telugu and Kannada faces significant challenges in specialized medical domains due to limited annotated data and morphological complexity. This work proposes a novel confidence-aware training framework that integrates real and synthetic speech data through a hybrid confidence mechanism combining static perceptual and acoustic similarity metrics with dynamic model entropy. Unlike direct fine-tuning approaches, the proposed methodology employs both fixed-weight and learnable-weight confidence aggregation strategies to guide sample weighting during training, enabling effective utilization of heterogeneous data sources. The framework is evaluated on Telugu and Kannada medical datasets containing both real recordings and TTS-generated synthetic speech. A 5-gram KenLM language model is applied for post-decoding correction. Results show that the hybrid confidence-aware approach with learnable weights substantially reduces recognition errors: Telugu Word Error Rate (WER) decreases from 24.3% to 15.8% (8.5% absolute improvement), while Kannada WER drops from 31.7% to 25.4% (6.3% absolute improvement), both significantly outperforming standard fine-tuning baselines. These findings confirm that combining adaptive confidence-aware training with statistical language modeling delivers superior performance for domain-specific ASR in morphologically complex Dravidian languages.