发表机构
Center for Language and Speech Processing (CLSP), Johns Hopkins University, USA（约翰斯·霍普金斯大学语言与语音处理中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出指令引导的相对情感语音转换任务，构建相关数据集，基于Emo-Compass模块提出TRACE-EVC零样本框架，能依自然语言指令预测情感变化方向与程度，实验表明其效果良好。
AI 中文摘要
传统情感语音转换（EVC）基于明确目标情感生成，忽略转换方向。本文引入指令引导的相对情感语音转换任务，构建TRACE-Instruct数据集，提出TRACE-EVC零样本框架，围绕Emo-Compass模块建模转换，预测情感变化方向和程度，实验验证其有效性。
英文摘要
Traditional emotional voice conversion (EVC) conditions generation on explicit target emotions like labels or references, defining the target affective state but omitting the direction or nature of the transition. We introduce instruction-guided relative emotional voice conversion, a task where natural-language instructions specify source-conditioned affective transformations (e.g., "make the speech slightly calmer" or "sound noticeably more confident") instead of fixed targets. To support this task, we construct TRACE-Instruct, a dataset of relative emotion instructions covering categorical transitions, intensity modifications, and open-ended affective changes. We propose TRACE-EVC, a framework built around Emo-Compass, a module that models each conversion as a source-anchored rectified flow. Rather than conditioning on an explicit target, it predicts the direction and degree of the affective change. Experiments demonstrate that TRACE-EVC accurately follows relative emotion instructions while preserving speaker identity, linguistic content, and speech quality, generalizes to unseen speakers, and remains competitive with conventional EVC systems on standard categorical emotion conversion.
