← 研踪 PaperTrailarXiv:2611.17181 · v1
Convolutional VocalTrax: Replacing Backpropagation Through Time with Convolution in Differentiable Articulatory Synthesis
卷积 VocalTrax：用卷积替代时间反向传播的可微发音合成
首次提交 2026-11-13 01:49
版本更新 2026-11-13 01:49
雷达观测 2026-11-13 14:15
摘要
VocalTrax recovers interpretable articulatory controls from a recording by gradient descent through a differentiable Pink Trombone synthesizer. Its vocal tract is a Kelly-Lochbaum waveguide updated twice per audio sample, so every gradient step backpropagates through a long recurrence, which is slow on GPUs. We propose Convolutional VocalTrax, which computes the exact frequency response of the same waveguide and applies it as a causal convolution. We assume that the tract is stationary within 5.8 ms blocks and that its lossy impulse response can be truncated after 93 ms. Gradients then pass through FFTs and a short recursion along the tract instead of through time. On 600 AudioMNIST recordings, the tract forward and backward pass runs 47 to 63 times faster on an A100 GPU, and a classifier trained only on real speech recognizes our reconstructions more often than those of VocalTrax (14.5% vs. 10.0%), although the log-mel distance to the target is 11% higher. Parameters fitted with our model keep this gain when rendered by the original VocalTrax (13.8%).
作者备注：9 pages, 3 figures, 5 tables
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-13 01:49 · 最新观测版本
Convolutional VocalTrax: Replacing Backpropagation Through Time with Convolution in Differentiable Articulatory Synthesis
VocalTrax recovers interpretable articulatory controls from a recording by gradient descent through a differentiable Pink Trombone synthesizer. Its vocal tract is a Kelly-Lochbaum waveguide updated twice per audio sample, so every gradient step backpropagates through a long recurrence, which is slow on GPUs. We propose Convolutional VocalTrax, which computes the exact frequency response of the same waveguide and applies it as a causal convolution. We assume that the tract is stationary within 5.8 ms blocks and that its lossy impulse response can be truncated after 93 ms. Gradients then pass through FFTs and a short recursion along the tract instead of through time. On 600 AudioMNIST recordings, the tract forward and backward pass runs 47 to 63 times faster on an A100 GPU, and a classifier trained only on real speech recognizes our reconstructions more often than those of VocalTrax (14.5% vs. 10.0%), although the log-mel distance to the target is 11% higher. Parameters fitted with our model keep this gain when rendered by the original VocalTrax (13.8%).
查看此版本解读 →查看此版本原文 ↗