用新型神经网络提升语音理解效果，表现优于传统方法
"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding
- 将KAN层嵌入2D-CNN与Transformer模型中，替代线性层
- 在5个语音理解数据集上，多数任务性能持平或更优
- 揭示KAN与线性层对原始波形的不同注意力机制
Kolmogorov-Arnold Networks（KANs）作为传统神经网络的潜在替代方案，其在语音处理中的应用尚未充分探索。本文首次系统研究KAN在语音语言理解（SLU）任务中的表现。我们在两个数据集上测试了2D-CNN模型，将KAN层以五种不同方式集成到密集块中。最佳配置为在线性层之间插入KAN层，并将其直接应用于Transformer模型，在五个复杂度递增的SLU数据集上进行评估。结果表明，KAN层可有效替代线性层，在大多数情况下实现相当或更优的性能。最后，我们分析了KAN与线性层在Transformer模型中对原始波形输入区域的不同注意力模式。
原文摘要 · Abstract (English)
Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional neural architectures, yet their application to speech processing remains under explored. This work presents the first investigation of KANs for Spoken Language Understanding (SLU) tasks. We experiment with 2D-CNN models on two datasets, integrating KAN layers in five different configurations within the dense block. The best-performing setup, which places a KAN layer between two linear layers, is directly applied to transformer-based models and evaluated on five SLU datasets with increasing complexity. Our results show that KAN layers can effectively replace the linear layers, achieving comparable or superior performance in most cases. Finally, we provide insights into how KAN and linear layers on top of transformers differently attend to input regions of the raw waveforms.
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。