提出一种新型音频特征提取层，可高效捕捉谐波信息。
Combolutional Neural Networks
- 用可学习延迟的IIR梳状滤波器提取时域谐波特征
- 在钢琴转录等任务中表现优于传统卷积层
- 参数少、计算快、结果可解释，适合音频分析场景
选择合适的归纳偏置是机器学习模型设计的关键，尤其在音频领域，即使短片段也可能包含数百万个采样点。为此，我们提出梳状卷积层：一种可学习延迟的IIR梳状滤波器与融合包络检测器，用于在时域中提取谐波特征。我们在三个信息检索任务上验证了该层的有效性，评估其相对于其他音频前端的计算成本，并提供了高效的训练实现。结果表明，当需要精确谐波分析时，梳状卷积层是卷积层的有效替代方案，如钢琴转录、说话人分类和调性检测。此外，该层还具备多项优势：参数量少、CPU推理效率高、严格实值计算，以及更好的可解释性。
原文摘要 · Abstract (English)
Selecting appropriate inductive biases is an essential step in the design of machine learning models, especially when working with audio, where even short clips may contain millions of samples. To this end, we propose the combolutional layer: a learned-delay IIR comb filter and fused envelope detector, which extracts harmonic features in the time domain. We demonstrate the efficacy of the combolutional layer on three information retrieval tasks, evaluate its computational cost relative to other audio frontends, and provide efficient implementations for training. We find that the combolutional layer is an effective replacement for convolutional layers in audio tasks where precise harmonic analysis is important, e.g., piano transcription, speaker classification, and key detection. Additionally, the combolutional layer has several other key benefits over existing frontends, namely: low parameter count, efficient CPU inference, strictly real-valued computations, and improved interpretability.
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。