边缘-云协同语音情绪描述 via 令牌级推测解码在音频-语言模型中
Edge-Cloud Collaborative Speech Emotion Captioning via Token-Level Speculative Decoding in Audio-Language Models
AI总结：
本文提出基于不确定性引导推测解码的边缘-云协同框架，通过轻量级边缘模型和云验证器的协同，提升语音情绪描述的准确率和效率，同时降低延迟和隐私风险。
摘要：
语音情绪描述（SEC）利用大型音频-语言模型生成丰富的、具有上下文感知的情感描述。然而，实际部署仍然具有挑战性，因为边缘设备在资源受限的情况下需要大量的计算需求，以及传输生物特征音频的隐私风险。虽然较小的音频-语言模型能够实现高效的设备端SEC，但其有限的容量通常会削弱细微的非语言学建模和细粒度的情感定位。我们提出了一种基于不确定性引导推测解码（UGSD）的边缘-云协同框架。一个轻量级的边缘模型在本地草拟描述，只有高不确定性令牌块才会被选择性地提升到更强的云验证器进行验证。在MER2024基准测试中，实验显示BLEU得分显著提高，最高达到62.7%。UGSD相比仅边缘模型实现了1.4倍的延迟降低和8.5倍的令牌吞吐量提升。这些结果经验地刻画了可部署SEC系统在质量-效率-隐私之间的权衡。
英文摘要：
Speech Emotion Captioning (SEC) leverages large audio-language models to generate rich, context-aware affective descriptions from speech. However, real-world deployment remains challenging due to the substantial computational demands on resource-constrained edge devices and the privacy risks of transmitting biometric audio. While smaller audio-language models enable efficient on-device SEC, their limited capacity often weakens subtle paralinguistic modeling and fine-grained affective grounding. We propose an edge-cloud collaborative framework based on Uncertainty-Guided Speculative Decoding (UGSD). A lightweight edge model drafts captions locally, and only high-uncertainty token blocks are selectively escalated to a stronger cloud verifier for validation. Experiments on the MER2024 benchmark demonstrate substantial BLEU improvements up to 62.7%. UGSD further achieves 1.4x lower latency and 8.5x higher token throughput compared to an edge-only model. These results empirically characterize the quality-efficiency-privacy trade-off in deployable SEC systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
