Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.06382 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914027388534784 |
|---|---|
| author | Ding, Yingke Wang, Zeyu Zhang, Xiyuxing Chen, Hongbin Xu, Zhenan |
| author_facet | Ding, Yingke Wang, Zeyu Zhang, Xiyuxing Chen, Hongbin Xu, Zhenan |
| contents | Traditional hearing aids often rely on static fittings that fail to adapt to their dynamic acoustic environments. We propose CAFA, a Context-Adaptive Fitting Advisor that provides personalized, real-time hearing aid adjustments through a multi-agent Large Language Model (LLM) workflow. CAFA combines live ambient audio, audiograms, and user feedback in a multi-turn conversational system. Ambient sound is classified into conversation, noise, or quiet with 91.2\% accuracy using a lightweight neural network based on YAMNet embeddings. This system utilizes a modular LLM workflow, comprising context acquisition, subproblem classification, strategy provision, and ethical regulation, and is overseen by an LLM Judge. The workflow translates context and feedback into precise, safe tuning commands. Evaluation confirms that real-time sound classification enhances conversational efficiency. CAFA exemplifies how agentic, multimodal AI can enable intelligent, user-centric assistive technologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06382 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Context-Adaptive Hearing Aid Fitting Advisor through Multi-turn Multimodal LLM Conversation Ding, Yingke Wang, Zeyu Zhang, Xiyuxing Chen, Hongbin Xu, Zhenan Human-Computer Interaction Traditional hearing aids often rely on static fittings that fail to adapt to their dynamic acoustic environments. We propose CAFA, a Context-Adaptive Fitting Advisor that provides personalized, real-time hearing aid adjustments through a multi-agent Large Language Model (LLM) workflow. CAFA combines live ambient audio, audiograms, and user feedback in a multi-turn conversational system. Ambient sound is classified into conversation, noise, or quiet with 91.2\% accuracy using a lightweight neural network based on YAMNet embeddings. This system utilizes a modular LLM workflow, comprising context acquisition, subproblem classification, strategy provision, and ethical regulation, and is overseen by an LLM Judge. The workflow translates context and feedback into precise, safe tuning commands. Evaluation confirms that real-time sound classification enhances conversational efficiency. CAFA exemplifies how agentic, multimodal AI can enable intelligent, user-centric assistive technologies. |
| title | Context-Adaptive Hearing Aid Fitting Advisor through Multi-turn Multimodal LLM Conversation |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.06382 |