arXiv cs.CL· Kuan-Hsun Ho, Yuan-Chiao Cheng, Yen-Tung Yeh, Yi-Hsuan Yang·· 13 小时前AI 评分18
MixJudge：可语言查询的人声混音评判模型
MixJudge: Learning a Language-Queryable Critic for Vocal Mixing
AI 导读
MixJudge 是一个可用语言查询的音频评判模型，通过覆盖 11 类人声混音问题、多严重程度等级的课程训练而成，能检索混音问题、区分相反问题并对问题严重程度排序。其判断还可迁移到处理方案选择：给定一组候选版本，MixJudge 常偏好声学上更接近留出专业版本的选项。
正文 · 原文
Abstract:Mixing requires not only applying processing but also assessing the resulting mix. Audio-language models can provide conversa- tional mixing advice, but existing evaluations do not separately test whether they can judge specific mixing issues. Since professional supervision for such judgments is scarce, we construct a curriculum of 11 vocal-mix issues at multiple severity levels and use it to train MixJudge, a language-queryable audio critic. MixJudge shows its ability to retrieve mixing issues, distinguish opposite issues, and order the severity of an issue. Moreover, its judgments transfer to menu selection: given a set of processing candidates, MixJudge often favors versions acoustically closer to a held-out professional version, demonstrating how explicit mixing judgment can support comparison and downstream mixing decisions.
| Comments: | Submitted to ICASSP 2027 |
| Subjects: | Sound (cs.SD); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.30783 [cs.SD] |
| (or arXiv:2610.30783v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.30783 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kuan-Hsun Ho [view email]
[v1]
Thu, 22 Oct 2026 06:02:59 UTC (105 KB)
来源：arXiv cs.CL · arxiv.org