DialogGraph-LLM: Graph-Informed LLMs for End-to-End Audio Dialogue Intent Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908656053780480 |
|---|---|
| author | Liu, HongYu Li, Junxin Guo, Changxi Chen, Hao Huang, Yaqian Guo, Yifu Yang, Huan Cai, Lihua |
| author_facet | Liu, HongYu Li, Junxin Guo, Changxi Chen, Hao Huang, Yaqian Guo, Yifu Yang, Huan Cai, Lihua |
| contents | Recognizing speaker intent in long audio dialogues among speakers has a wide range of applications, but is a non-trivial AI task due to complex inter-dependencies in speaker utterances and scarce annotated data. To address these challenges, an end-to-end framework, namely DialogGraph-LLM, is proposed in the current work. DialogGraph-LLM combines a novel Multi-Relational Dialogue Attention Network (MR-DAN) architecture with multimodal foundation models (e.g., Qwen2.5-Omni-7B) for direct acoustic-to-intent inference. An adaptive semi-supervised learning strategy is designed using LLM with a confidence-aware pseudo-label generation mechanism based on dual-threshold filtering using both global and class confidences, and an entropy-based sample selection process that prioritizes high-information unlabeled instances. Extensive evaluations on the proprietary MarketCalls corpus and the publicly available MIntRec 2.0 benchmark demonstrate DialogGraph-LLM's superiority over strong audio and text-driven baselines. The framework demonstrates strong performance and efficiency in intent recognition in real world scenario audio dialogues, proving its practical value for audio-rich domains with limited supervision. Our code is available at https://github.com/david188888/DialogGraph-LLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11000 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DialogGraph-LLM: Graph-Informed LLMs for End-to-End Audio Dialogue Intent Recognition Liu, HongYu Li, Junxin Guo, Changxi Chen, Hao Huang, Yaqian Guo, Yifu Yang, Huan Cai, Lihua Sound Artificial Intelligence Recognizing speaker intent in long audio dialogues among speakers has a wide range of applications, but is a non-trivial AI task due to complex inter-dependencies in speaker utterances and scarce annotated data. To address these challenges, an end-to-end framework, namely DialogGraph-LLM, is proposed in the current work. DialogGraph-LLM combines a novel Multi-Relational Dialogue Attention Network (MR-DAN) architecture with multimodal foundation models (e.g., Qwen2.5-Omni-7B) for direct acoustic-to-intent inference. An adaptive semi-supervised learning strategy is designed using LLM with a confidence-aware pseudo-label generation mechanism based on dual-threshold filtering using both global and class confidences, and an entropy-based sample selection process that prioritizes high-information unlabeled instances. Extensive evaluations on the proprietary MarketCalls corpus and the publicly available MIntRec 2.0 benchmark demonstrate DialogGraph-LLM's superiority over strong audio and text-driven baselines. The framework demonstrates strong performance and efficiency in intent recognition in real world scenario audio dialogues, proving its practical value for audio-rich domains with limited supervision. Our code is available at https://github.com/david188888/DialogGraph-LLM. |
| title | DialogGraph-LLM: Graph-Informed LLMs for End-to-End Audio Dialogue Intent Recognition |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2511.11000 |