用可微模型分析人声效果参数分布，助力自动混音研究
DiffVox: A Differentiable Model for Capturing and Analysing Vocal Effects Distributions
- 构建可梯度优化的可微人声效果模型，整合均衡、压缩、延迟与混响
- 在70首MedleyDB和365首私有数据上发现参数强相关性，如高通与低 shelf 滤波器协同作用
- 主成分分析关联到麦克阿达姆斯音色维度，揭示空间感与频谱亮度的调控机制
本文提出一种新型可解释的人声效果匹配模型 DiffVox（Differentiable Vocal Fx），通过参数化均衡、动态范围控制、延迟和混响的高效可微实现，支持基于梯度的参数估计。从两个数据集提取人声预设：70首来自 MedleyDB，365首来自私有收集。分析显示效果参数间存在强相关性，例如高通滤波器与低 shelf 滤波器常协同塑造低频响应，延迟时间与延时信号强度显著相关。主成分分析揭示了与 McAdams 音色维度的联系，第一主成分调控感知空间感，第二主成分影响频谱亮度。统计检验确认参数分布非高斯，凸显人声效果空间的复杂性。这些初步发现为未来人声效果建模与自动混音研究奠定基础。源代码与数据集已开源：https://github.com/SonyResearch/diffvox。
原文摘要 · Abstract (English)
This study introduces a novel and interpretable model, DiffVox, for matching vocal effects in music production. DiffVox, short for ``Differentiable Vocal Fx", integrates parametric equalisation, dynamic range control, delay, and reverb with efficient differentiable implementations to enable gradient-based optimisation for parameter estimation. Vocal presets are retrieved from two datasets, comprising 70 tracks from MedleyDB and 365 tracks from a private collection. Analysis of parameter correlations reveals strong relationships between effects and parameters, such as the high-pass and low-shelf filters often working together to shape the low end, and the delay time correlating with the intensity of the delayed signals. Principal component analysis reveals connections to McAdams' timbre dimensions, where the most crucial component modulates the perceived spaciousness while the secondary components influence spectral brightness. Statistical testing confirms the non-Gaussian nature of the parameter distribution, highlighting the complexity of the vocal effects space. These initial findings on the parameter distributions set the foundation for future research in vocal effects modelling and automatic mixing. Our source code and datasets are accessible at https://github.com/SonyResearch/diffvox.
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。