Medical Speech Recognition

Latest papers

11 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa
Nov 3, 2026Oche David Ankeli, Hassan Adelani Luqman, Theodora Ngozi Egbunike +2Domain Adaptation for ASR Automatic Speech Recognition
RUZIVO Research Lab, African Leadership University, Kigali, Rwanda · Stanford University, Stanford, CA, USA · Mila – Quebec AI Institute and McGill University, Montreal, Canada
Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages
Sep 24, 2026Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu +3ASR Evaluation Domain Adaptation for ASR
Department of Mathematics, University of Cape Coast, Ghana · Ghana Natural Language Processing, Cape Coast, Ghana
MedWER: A Reproducible, Model-Free Evaluation Protocol for Medical Speech Recognition
Sep 4, 2026Justin BehlingMedical Speech Recognition ASR Evaluation
NORDIS TECH INC.
Understanding Multilingual Medical ASR Adaptation Through Layer-Wise Analysis
Aug 19, 2026Souranil Kahali, Rituparna Bose, Abner Hernandez +4Medical Speech Recognition Automatic Speech Recognition
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany · School of Computer Science, University of Sheffield, Sheffield, UK · Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM), Munich, Germany
Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving
Jul 2, 2026Ruchao Fan, Yiming Wang, Rui Zhao +10Medical Speech Recognition Automatic Speech Recognition
Microsoft, USA
Symphony for Speech-to-Text: Supporting Real-Time Medical Voice Interfaces
May 15, 2026Arne Nix, Robert James, Lasse Borgholt +6Healthcare Streaming ASR
Corti
Au-M-ol: A Unified Model for Medical Audio and Language Understanding
Apr 25, 2026Meizhu Liu, Nistha Mitra, Paul Li +3Medical Speech Recognition Speech Processing
Oracle AI Science · Neuramill
Enhancing ASR Performance in the Medical Domain for Dravidian Languages
Apr 10, 2026Sri Charan Devarakonda, Ravi Sastry Kolluru, Manjula Sri Rayudu +3Medical Speech Recognition Automatic Speech Recognition
Language Technologies Research Centre (LTRC), International Institute of Information Technology Hyderabad (IIIT-H), Hyderabad, India · Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology (VNRVJIET), Hyderabad, India
From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation
Mar 2, 2026Abdolamir Karbalaie, Fernando Seoane, Farhad AbtahiMedical Speech Recognition Automatic Speech Recognition
Department of Clinical Science, Intervention and Technology, Karolinska Institutet, 17177 Stockholm, Sweden · Department of Clinical Physiology, Karolinska University Hospital, 17176 Stockholm, Sweden · Department of Textile Technology, Faculty of Textiles, Engineering and Business Swedish School of Textiles, University of Borås, 503 32 Borås, Sweden +2
Quality of Automatic Speech Recognition -- Polish Language case study -- from Wav2Vec to Scribe ElevenLabs
Feb 25, 2026Marcin Pietroń, Szymon Piórkowski, Kamil Faber +6Medical Speech Recognition Automatic Speech Recognition
Institute of Electronics AGH, Krakow · Coraz Zdrowiej, Krakow · Department of Computer Science AGH, Krakow +2
ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark
Feb 13, 2026Tung X. Nguyen, Nhu Vo, Giang-Son Nguyen +6Code-Switching Speech Recognition Medical Speech Recognition
College of Engineering and Computer Science, VinUniversity, Vietnam · Center for AI Research, VinUniversity, Vietnam · University of Technology Sydney, Australia +1

Nov 3, 2026J/K move · Enter open · S save

Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa

Oche David Ankeli, Hassan Adelani Luqman, Theodora Ngozi Egbunike, Joshua Gottschalk+1

RUZIVO Research Lab, African Leadership University, Kigali, Rwanda · Stanford University, Stanford, CA, USA · Mila – Quebec AI Institute and McGill University, Montreal, Canada

Domain Adaptation for ASR Automatic Speech Recognition Medical Speech Recognition Low-Resource Speech Recognition

Open paper AskPDF arXiv

Automatic speech recognition (ASR) systems often struggle with specialised medical vocabulary, especially in low-resource languages where domain-specific speech data are scarce. We investigate text-only domain adaptation for Hausa medical ASR using the fixed MMS-1B-FL102 acoustic model and two decoding-time language-model fusion methods: Shallow Fusion (SF) and the Density Ratio Approach (DRA). A 4-gram KenLM trained on 19,421 Hausa health sentences serves as the medical target model, while a 75,372-sentence general-domain model provides the source prior for DRA. Evaluation uses 250 recordings of 25 physician-reviewed prompts from 10 speakers across six northern Nigerian states. Under prompt-disjoint five-fold cross-validation, SF and DRA reduce WER from 29.56% to 23.55% and 23.33%, respectively. Both significantly outperform greedy decoding (p < 0.001), while their difference is not significant (p = 0.423). However, general-LM-only SF achieves 23.96% WER, indicating that the medical LM's additional improvement over a general LM is modest. Medical Term Error Rate also improves under fusion, but does not establish a distinct medical-domain advantage. These findings demonstrate that lightweight, text-only language-model fusion can improve Hausa medical ASR without additional domain-specific speech collection.