Saved in:
Bibliographic Details
Main Authors: Liu, Meizhu, Mitra, Nistha, Li, Paul, Abdaoui, Amine, Ledyard, Adam, Sheng, Tao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.23284
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911622989086720
author Liu, Meizhu
Mitra, Nistha
Li, Paul
Abdaoui, Amine
Ledyard, Adam
Sheng, Tao
author_facet Liu, Meizhu
Mitra, Nistha
Li, Paul
Abdaoui, Amine
Ledyard, Adam
Sheng, Tao
contents In this work, we present Au-M-ol, a novel multimodal architecture that extends Large Language Models (LLMs) with audio processing. It is designed to improve performance on clinically relevant tasks such as Automatic Speech Recognition (ASR). Au-M-ol has three main components: (1) an audio encoder that extracts rich acoustic features from medical speech, (2) an adaptation layer that maps audio features into the LLM input space, and (3) a pretrained LLM that performs transcription and clinical language understanding. This design allows the model to interpret spoken medical content directly, improving both accuracy and robustness. In experiments, Au-M-ol reduces Word Error Rate (WER) by 56\% compared to state-of-the-art baselines on medical transcription tasks. The model also performs well in challenging conditions, including noisy environments, domain-specific terminology, and speaker variability. These results suggest that Au-M-ol is a strong candidate for real-world clinical applications, where reliable and context-aware audio understanding is essential.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23284
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Au-M-ol: A Unified Model for Medical Audio and Language Understanding
Liu, Meizhu
Mitra, Nistha
Li, Paul
Abdaoui, Amine
Ledyard, Adam
Sheng, Tao
Computation and Language
Artificial Intelligence
In this work, we present Au-M-ol, a novel multimodal architecture that extends Large Language Models (LLMs) with audio processing. It is designed to improve performance on clinically relevant tasks such as Automatic Speech Recognition (ASR). Au-M-ol has three main components: (1) an audio encoder that extracts rich acoustic features from medical speech, (2) an adaptation layer that maps audio features into the LLM input space, and (3) a pretrained LLM that performs transcription and clinical language understanding. This design allows the model to interpret spoken medical content directly, improving both accuracy and robustness. In experiments, Au-M-ol reduces Word Error Rate (WER) by 56\% compared to state-of-the-art baselines on medical transcription tasks. The model also performs well in challenging conditions, including noisy environments, domain-specific terminology, and speaker variability. These results suggest that Au-M-ol is a strong candidate for real-world clinical applications, where reliable and context-aware audio understanding is essential.
title Au-M-ol: A Unified Model for Medical Audio and Language Understanding
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.23284