Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Collins, Jack, Buzea, Adrian, Collier, Chris, Rosen, Alejandro Ballesta, Maclaren, Julian, Lyon, Richard F., Carlile, Simon
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.23590
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911085761658880
author Collins, Jack
Buzea, Adrian
Collier, Chris
Rosen, Alejandro Ballesta
Maclaren, Julian
Lyon, Richard F.
Carlile, Simon
author_facet Collins, Jack
Buzea, Adrian
Collier, Chris
Rosen, Alejandro Ballesta
Maclaren, Julian
Lyon, Richard F.
Carlile, Simon
contents Individuals regularly experience Hearing Difficulty Moments in everyday conversation. Identifying these moments of hearing difficulty has particular significance in the field of hearing assistive technology where timely interventions are key for realtime hearing assistance. In this paper, we propose and compare machine learning solutions for continuously detecting utterances that identify these specific moments in conversational audio. We show that audio language models, through their multimodal reasoning capabilities, excel at this task, significantly outperforming a simple ASR hotword heuristic and a more conventional fine-tuning approach with Wav2Vec, an audio-only input architecture that is state-of-the-art for automatic speech recognition (ASR).
format Preprint
id arxiv_https___arxiv_org_abs_2507_23590
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Identifying Hearing Difficulty Moments in Conversational Audio
Collins, Jack
Buzea, Adrian
Collier, Chris
Rosen, Alejandro Ballesta
Maclaren, Julian
Lyon, Richard F.
Carlile, Simon
Sound
Audio and Speech Processing
Individuals regularly experience Hearing Difficulty Moments in everyday conversation. Identifying these moments of hearing difficulty has particular significance in the field of hearing assistive technology where timely interventions are key for realtime hearing assistance. In this paper, we propose and compare machine learning solutions for continuously detecting utterances that identify these specific moments in conversational audio. We show that audio language models, through their multimodal reasoning capabilities, excel at this task, significantly outperforming a simple ASR hotword heuristic and a more conventional fine-tuning approach with Wav2Vec, an audio-only input architecture that is state-of-the-art for automatic speech recognition (ASR).
title Identifying Hearing Difficulty Moments in Conversational Audio
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.23590