arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.16682cs.SD
收藏

用于电吉他的情感音色数据集

A Semantic Timbre Dataset for the Electric Guitar

Department of Computer Science \& Technology, University of Cambridge\ , United Kingdom

Joseph Cameron, Alan Blackwell

AI总结:

本文提出一个电吉他音色数据集,通过19个语义音色描述符和对应幅度标注,支持音色控制和语义音频生成,验证了数据集的有效性。

摘要:

理解并操控音色是音频合成的核心,但因缺乏将感知音色维度与语义描述符关联的标注数据集,在机器学习中研究不足。我们提出了语义音色数据集,一个经过精心编纂的单音电吉他声音集合,每个声音均标注有19个语义音色描述符及其对应幅度。这些描述符源自对物理和虚拟吉他效果单元的定性分析,并系统应用于干净的吉他音色。该数据集连接了感知音色与机器学习表示,支持学习音色控制和语义音频生成。我们通过在潜在空间上训练变分自编码器(VAE)并使用人类感知判断和描述符分类器评估数据集。结果表明,VAE能够捕捉音色结构,并在描述符之间实现平滑插值。我们发布该数据集、代码和评估协议,以支持音色感知生成式AI研究。

英文摘要:

Understanding and manipulating timbre is central to audio synthesis, yet this remains under-explored in machine learning due to a lack of annotated datasets linking perceptual timbre dimensions to semantic descriptors. We present the Semantic Timbre Dataset, a curated collection of monophonic electric guitar sounds, each labeled with one of 19 semantic timbre descriptors and corresponding magnitudes. These descriptors were derived from a qualitative analysis of physical and virtual guitar effect units and applied systematically to clean guitar tones. The dataset bridges perceptual timbre and machine learning representations, supporting learning for timbre control and semantic audio generation. We validate the dataset by training a variational autoencoder (VAE) on its latent space and evaluating it using human perceptual judgments and descriptor classifiers. Results show that the VAE captures timbral structure and enables smooth interpolation across descriptors. We release the dataset, code, and evaluation protocols to support timbre-aware generative AI research.

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。

↑