Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks

Voice Conversion

Categories: Adversarial Training | Convolutional Neural Network | Deep Learning | Generative Adversarial Network | Recurrent Neural Network

Tags: 2017 | Hirokazu Kameoka | Takuhiro Kaneko

We propose a parallel-data-free voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is general purpose, high quality, and parallel-data free and works without any extra data, modules, or alignment procedure. It also avoids over-smoothing, which occurs in many conventional statistical model-based VC methods. Our method, called CycleGAN-VC, uses a cycle-consistent adversarial network (CycleGAN) with gated convolutional neural networks (CNNs) and an identity-mapping loss. A CycleGAN learns forward and inverse map...

Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior Probabilities

Voice Conversion

Categories: Dynamic Time Warping | Fourier Transform | Mel-spectrogram | Recurrent Neural Network

Tags: 2017 | Hiroshi Saruwatari | Hiroyuki Miyoshi | Shinnosuke Takamichi | Yuki Saito

Voice conversion (VC) using sequence-to-sequence learning of context posterior probabilities is proposed. Conventional VC using shared context posterior probabilities predicts target speech parameters from the context posterior probabilities estimated from the source speech parameters. Although conventional VC can be built from non-parallel data, it is difficult to convert speaker individuality such as phonetic property and speaking rate contained in the posterior probabilities because the source posterior probabilities are directly used for predicting target speech parameters. In this work, w...

Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks

Voice Conversion

Categories: Adversarial Training | Autoencoder | Deep Learning | Generative Adversarial Network | Mean Opinion Score

Tags: 2017 | Chin-Cheng Hsu | Hsin-Min Wang | Hsin-Te Hwang | Yi-Chiao Wu | Yu Tsao

Building a voice conversion (VC) system from non-parallel speech corpora is challenging but highly valuable in real application scenarios. In most situations, the source and the target speakers do not repeat the same texts or they may even speak different languages. In this case, one possible, although indirect, solution is to build a generative model for speech. Generative models focus on explaining the observations with latent variables instead of learning a pairwise transformation function, thereby bypassing the requirement of speech frame alignment. In this paper, we propose a non-parallel...