Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.16975 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909798667124736 |
|---|---|
| author | Jia, Yuhang Zhang, Xu Chen, Yang Wang, Hui Wang, Enzhi Qin, Yong |
| author_facet | Jia, Yuhang Zhang, Xu Chen, Yang Wang, Hui Wang, Enzhi Qin, Yong |
| contents | Automatic mean opinion score (MOS) prediction provides a more perceptual alternative to objective metrics, offering deeper insights into the evaluated models. With the rapid progress of multimodal large language models (MLLMs), their enhanced perceptual and reasoning abilities enable more comprehensive and interpretable audio quality assessment. In this work, we tackle the challenging task of audio editing evaluation and propose the first natural language-based automated evaluation framework built on MLLMs. Our approach introduces two fine-tuning tasks to boost multi-audio understanding, combined with Chain-of-Thought prompting, and lightweight instruction tuning, to enhance step-by-step reasoning. Experiment demonstrate that our framework delivers accurate, interpretable, and text-based editing evaluation, closely aligning with human judgments and objective metrics while substantially improving over baselines. The code and demo are available at https://github.com/NKU-HLT/Eval_Reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16975 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interpretable Audio Editing Evaluation via Chain-of-Thought Difference-Commonality Reasoning with Multimodal LLMs Jia, Yuhang Zhang, Xu Chen, Yang Wang, Hui Wang, Enzhi Qin, Yong Sound Audio and Speech Processing Automatic mean opinion score (MOS) prediction provides a more perceptual alternative to objective metrics, offering deeper insights into the evaluated models. With the rapid progress of multimodal large language models (MLLMs), their enhanced perceptual and reasoning abilities enable more comprehensive and interpretable audio quality assessment. In this work, we tackle the challenging task of audio editing evaluation and propose the first natural language-based automated evaluation framework built on MLLMs. Our approach introduces two fine-tuning tasks to boost multi-audio understanding, combined with Chain-of-Thought prompting, and lightweight instruction tuning, to enhance step-by-step reasoning. Experiment demonstrate that our framework delivers accurate, interpretable, and text-based editing evaluation, closely aligning with human judgments and objective metrics while substantially improving over baselines. The code and demo are available at https://github.com/NKU-HLT/Eval_Reasoning. |
| title | Interpretable Audio Editing Evaluation via Chain-of-Thought Difference-Commonality Reasoning with Multimodal LLMs |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.16975 |