Enhancing ASR Performance in the Medical Domain for Dravidian Languages

• URL: http://arxiv.org/abs/2604.19797v1
• Date: Fri, 10 Apr 2026 09:41:26 GMT
• Title: Enhancing ASR Performance in the Medical Domain for Dravidian Languages
• Abstract summary: This work proposes a novel confidence-aware training framework that integrates real and synthetic speech data.<n>A 5-gram KenLM language model is applied for post-decoding correction.<n>Results show that the hybrid confidence-aware approach with learnable weights substantially reduces recognition errors.
• Score: 4.188779570200089
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Robust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper Models [1.4095958360608893]
  This paper presents a controlled, fine-tuned Whisper-based Assamese ASR system trained on the Mozilla Common Voice 24.0-Assamese corpus.<n>A hardware-aware optimized training pipeline is implemented for resource-constrained environments.
  arXiv  Detail & Related papers  (2026-07-19T09:54:52Z)
• Team RAS in 11th ABAW Competition: Multimodal Ambivalence Recognition Approach [52.92973028971813]
  We present a single text-centered multimodal approach for video-level ambivalence and hesitancy recognition.<n>The proposed approach combines linguistic, acoustic, facial, and scene features using text-centered multimodal fusion model.<n>Experiments on the Behavioural Ambivalence/Hesitancy (BAH) corpus confirm that text is the strongest unimodal modality.
  arXiv  Detail & Related papers  (2026-07-16T08:04:23Z)
• Human-Guided Reasoning with Large Language Models for Vietnamese Speech Emotion Recognition [1.744935381873858]
  This paper proposes a human-machine collaborative framework that integrates human knowledge into the learning process.<n>A confidence-based routing mechanism is introduced to distinguish between easy and ambiguous samples.<n> Experiments are conducted on a Vietnamese speech dataset of 2,764 samples across three emotion classes.
  arXiv  Detail & Related papers  (2026-04-02T07:24:14Z)
• Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards [8.109014000578766]
  We present ASR-TRA, a novel Testtime Reinforcement Adaptation framework inspired by causal intervention.<n>Our method achieves higher accuracy while maintaining lower latency than existing TTA baselines.<n>Our approach provides a practical and robust solution for deploying ASR systems in challenging real-world conditions.
  arXiv  Detail & Related papers  (2026-03-05T14:43:15Z)
• Lightweight Diffusion-based Framework for Online Imagined Speech Decoding in Aphasia [1.299941371793082]
  A diffusion-based neural decoding framework is optimized for real-time imagined speech classification in individuals with aphasia.<n>A dual-criterion early stopping strategy enabled rapid convergence under limited calibration data.<n>The proposed framework advances the translation of imagined speech brain-computer interfaces toward clinical communication support.
  arXiv  Detail & Related papers  (2025-11-11T07:18:35Z)
• MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds [50.94175872742232]
  We propose the Mixture of Stylistic Experts (MoSEs) framework that enables stylistics-aware quantification uncertainty.<n>MoSEs contains three core components, namely, the Stylistics Reference Repository (SRR), the Stylistics-Aware Router (SAR), and the Conditional Threshold Estimator (CTE)<n>With a discrimination score, MoSEs yields prediction labels with the corresponding confidence level.
  arXiv  Detail & Related papers  (2025-09-02T16:51:43Z)
• High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR [1.3810901729134184]
  We introduce United-MedASR, a novel architecture that addresses challenges by integrating synthetic data generation, precision ASR fine-tuning, and semantic enhancement techniques.<n>United-MedASR constructs a specialised medical vocabulary by synthesising data from authoritative sources such as ICD-10, MIMS, and FDA databases.<n>To enhance processing speed, we incorporate Faster Whisper, ensuring streamlined and high-speed ASR performance.
  arXiv  Detail & Related papers  (2024-11-24T17:02:48Z)
• Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation [71.31331402404662]
  This paper proposes two novel data-efficient methods to learn dysarthric and elderly speaker-level features. Speaker-regularized spectral basis embedding-SBE features that exploit a special regularization term to enforce homogeneity of speaker features in adaptation. Feature-based learning hidden unit contributions (f-LHUC) that are conditioned on VR-LH features that are shown to be insensitive to speaker-level data quantity in testtime adaptation.
  arXiv  Detail & Related papers  (2024-07-08T18:20:24Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation [22.733285434532068]
  Large-scale pre-trained language models (PLMs) have shown great potential in natural language processing tasks. We propose the hierarchical knowledge distillation (HKD) on the continuous integrate-and-fire (CIF) based ASR models. Compared with the original CIF-based model, our method achieves 15% and 9% relative error rate reduction on the AISHELL-1 and LibriSpeech datasets.
  arXiv  Detail & Related papers  (2023-01-30T15:44:55Z)
• Understanding and Improving Lexical Choice in Non-Autoregressive Translation [98.11249019844281]
  We propose to expose the raw data to NAT models to restore the useful information of low-frequency words. Our approach pushes the SOTA NAT performance on the WMT14 English-German and WMT16 Romanian-English datasets up to 27.8 and 33.8 BLEU points, respectively.
  arXiv  Detail & Related papers  (2020-12-29T03:18:50Z)
• Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription [73.66530509749305]
  In this paper, we argue that, even in difficult cases, some end-to-end approaches show performance close to the hybrid baseline. We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures. Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline.
  arXiv  Detail & Related papers  (2020-04-22T19:08:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.