用API调用大模型+无源数据，让小模型超越大模型情绪识别能力。
MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
- 通过融合大模型与小模型预测，用互信息评估不确定性加权融合。
- 在6个跨域任务中，学生模型性能超过大模型3.9%以上。
- 适合隐私敏感场景，无需共享原始训练数据的语音情绪识别。
大型音频语言模型（LALMs）在语音任务中表现出强大的零样本能力，为语音情绪识别（SER）带来希望。然而，真实部署中常因领域不匹配导致失效，此时源数据不可用，而强大LALMs仅可通过API访问。我们提出：在仅有目标域无标签音频和仅能调用API的LALM前提下，能否训练一个学生模型，使其在目标域表现优于LALM？为此，我们提出MI-Fuse，一种去噪标签融合框架，将预训练于源域的SER分类器作为辅助教师。该框架从两个教师模型获取多组随机预测，基于互信息评估不确定性对均值分布进行加权，并采用指数移动平均教师稳定训练过程。在三个公开情绪数据集及六组跨域迁移实验中，结果持续提升，学生模型超越了LALM，且优于最强基线3.9%。该方法在不共享源数据的前提下强化了情绪感知语音系统，实现了现实可行的领域自适应。
原文摘要 · Abstract (English)
Large audio-language models (LALMs) show strong zero-shot ability on speech tasks, suggesting promise for speech emotion recognition (SER). However, SER in real-world deployments often fails under domain mismatch, where source data are unavailable and powerful LALMs are accessible only through an API. We ask: given only unlabeled target-domain audio and an API-only LALM, can a student model be adapted to outperform the LALM in the target domain? To this end, we propose MI-Fuse, a denoised label fusion framework that supplements the LALM with a source-domain trained SER classifier as an auxiliary teacher. The framework draws multiple stochastic predictions from both teachers, weights their mean distributions by mutual-information-based uncertainty, and stabilizes training with an exponential moving average teacher. Experiments across three public emotion datasets and six cross-domain transfers show consistent gains, with the student surpassing the LALM and outperforming the strongest baseline by 3.9%. This approach strengthens emotion-aware speech systems without sharing source data, enabling realistic adaptation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。