对比多种注意力机制，发现高效模型可大幅降低语音情感识别的计算开销。
How Attention Shapes Emotion: A Comparative Study of Attention Mechanisms for Speech Emotion Recognition
- 系统评测五种优化注意力模型在语音情感识别中的表现。
- 标准自注意力准确率最高，但效率低；优化模型推理延迟和内存降低十倍。
- 为构建高效可扩展的语音情感识别系统提供实用指导。
语音情感识别（SER）在提升人机交互中具有关键作用。注意力机制因其捕捉长程依赖和突出关键信息的能力，已成为建模情感语音的主流方法。然而，标准自注意力存在二次方计算与内存复杂度，限制了其可扩展性。本文系统评估了五种优化注意力机制（RetNet、LightNet、GSA、FoX、KDA）在MSP-Podcast基准数据集上的表现。实验表明，尽管标准自注意力在所有测试集上取得最佳识别性能，但高效注意力变体显著提升可扩展性，推理延迟和内存占用最高降低一个数量级。结果揭示了精度与效率之间的关键权衡，为设计可扩展的SER系统提供了实用洞见。
原文摘要 · Abstract (English)
Speech Emotion Recognition (SER) plays a key role in advancing human-computer interaction. Attention mechanisms have become the dominant approach for modeling emotional speech due to their ability to capture long-range dependencies and emphasize salient information. However, standard self-attention suffers from quadratic computational and memory complexity, limiting its scalability. In this work, we present a systematic benchmark of optimized attention mechanisms for SER, including RetNet, LightNet, GSA, FoX, and KDA. Experiments on both MSP-Podcast benchmark versions show that while standard self-attention achieves the strongest recognition performance across test sets, efficient attention variants dramatically improve scalability, reducing inference latency and memory usage by up to an order of magnitude. These results highlight a critical trade-off between accuracy and efficiency, providing practical insights for designing scalable SER systems.
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。