English

Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction

Sound 2021-07-06 v2 Computation and Language Machine Learning Audio and Speech Processing

Abstract

This paper presents a low-latency real-time (LLRT) non-parallel voice conversion (VC) framework based on cyclic variational autoencoder (CycleVAE) and multiband WaveRNN with data-driven linear prediction (MWDLP). CycleVAE is a robust non-parallel multispeaker spectral model, which utilizes a speaker-independent latent space and a speaker-dependent code to generate reconstructed/converted spectral features given the spectral features of an input speaker. On the other hand, MWDLP is an efficient and a high-quality neural vocoder that can handle multispeaker data and generate speech waveform for LLRT applications with CPU. To accommodate LLRT constraint with CPU, we propose a novel CycleVAE framework that utilizes mel-spectrogram as spectral features and is built with a sparse network architecture. Further, to improve the modeling performance, we also propose a novel fine-tuning procedure that refines the frame-rate CycleVAE network by utilizing the waveform loss from the MWDLP network. The experimental results demonstrate that the proposed framework achieves high-performance VC, while allowing for LLRT usage with a single-core of 2.12.1--2.72.7 GHz CPU on a real-time factor of 0.870.87--0.950.95, including input/output, feature extraction, on a frame shift of 1010 ms, a window length of 27.527.5 ms, and 22 lookup frames.

Keywords

Cite

@article{arxiv.2105.09858,
  title  = {Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction},
  author = {Patrick Lumban Tobing and Tomoki Toda},
  journal= {arXiv preprint arXiv:2105.09858},
  year   = {2021}
}

Comments

Accepted for SSW11

R2 v1 2026-06-24T02:18:35.698Z