轻量级语音情感识别模型，参数少且精度高，适合部署在设备端。
Speech Emotion Recognition using Attention-based LSTM-Network with Residual Connection
- 在LSTM中加入残差连接与软注意力机制，提升特征提取能力。
- 在RAVDESS数据集上达到0.6517的未加权平均召回率，仅需46.8k参数。
- 参数量比大型自监督模型少三个数量级，适合边缘设备实时使用。
语音情感识别是现代人机交互系统的重要组成部分。然而，许多先进方法依赖于大规模预训练模型，计算和内存开销大，限制了实际应用。本文提出ResLSTM-SA，一种将残差连接与软注意力机制融合于LSTM框架的轻量级架构。在严格说话人无关划分的RAVDESS数据集上评估，该模型在未加权平均召回率（UAR）上优于传统注意力LSTM基线及多个先前报道的CNN与混合CNN-LSTM结构。最佳变体（ResLSTM-SA-h64）实现最高UAR为0.6517，仅含46.8k可训练参数，相较大规模自监督模型减少三个数量级参数，具备高效部署于边缘设备和实时语音助手的能力。源代码已公开于https://github.com/Mak-Sim/ResLSTM-SER。
原文摘要 · Abstract (English)
Speech emotion recognition is an important component of modern human-computer interaction systems. However, many state-of-the-art approaches rely on large pretrained models with high computational and memory requirements, limiting their applicability. This paper proposes ResLSTM-SA, a lightweight architecture that integrates residual connections with soft attention within an LSTM-based framework. Evaluated on the RAVDESS dataset under strict speaker-independent partitioning, the proposed model outperforms conventional attention-based LSTM baselines and several previously reported CNN- and hybrid CNN-LSTM architectures in terms of unweighted average recall (UAR). The best-performing variant (ResLSTM-SA-h64) achieves a maximum UAR of 0.6517 with only 46.8k trainable parameters, delivering competitive accuracy with three orders of magnitude fewer parameters than large-scale self-supervised alternatives, thereby enabling efficient deployment on edge devices and real-time voice assistants. The source code is available at https://github.com/Mak-Sim/ResLSTM-SER.
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。