Generalization of Spectrum Differential based Direct Waveform Modification for Voice Conversion

TL;DR

This paper introduces a flexible waveform modification method for voice conversion that eliminates the need for retraining spectral differential models, improving quality and generalizability across models.

Contribution

It proposes a novel F0 transformation-based DIFFVC framework that simplifies waveform generation and enhances compatibility with various spectral conversion models.

Findings

Outperforms vocoder-based baseline in quality

Compatible with non-parallel VAE spectral conversion

Eliminates retraining of spectral differential models

Abstract

We present a modification to the spectrum differential based direct waveform modification for voice conversion (DIFFVC) so that it can be directly applied as a waveform generation module to voice conversion models. The recently proposed DIFFVC avoids the use of a vocoder, meanwhile preserves rich spectral details hence capable of generating high quality converted voice. To apply the DIFFVC framework, a model that can estimate the spectral differential from the F0 transformed input speech needs to be trained beforehand. This requirement imposes several constraints, including a limitation on the estimation model to parallel training and the need of extra training on each conversion pair, which make DIFFVC inflexible. Based on the above motivations, we propose a new DIFFVC framework based on an F0 transformation in the residual domain. By performing inverse filtering on the input signal followed by synthesis filtering on the F0 transformed residual signal using the converted spectral features directly, the spectral conversion model does not need to be retrained or capable of predicting the spectral differential. We describe several details that need to be taken care of under this modification, and by applying our proposed method to a non-parallel, variational autoencoder (VAE)-based spectral conversion model, we demonstrate that this framework can be generalized to any spectral conversion model, and experimental evaluations show that it can outperform a baseline framework whose waveform generation process is carried out by a vocoder.