CycleVAE optimizes non-parallel voice conversion indirectly via cyclic reconstructed spectra, yielding higher spectral accuracy, latent feature correlation, and improved converted speech quality.
Learning Latent Representations for Speech Generation and Transformation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as Variational Autoencoders (VAEs) have achieved tremendous success in modeling natural images. In this paper, we apply a convolutional VAE to model the generative process of natural speech. We derive latent space arithmetic operations to disentangle learned latent representations. We demonstrate the capability of our model to modify the phonetic content or the speaker identity for speech segments using the derived operations, without the need for parallel supervisory data.
years
2019 2verdicts
UNVERDICTED 2representative citing papers
VAEs are trained on classical music to encode pieces into latent space and predict continuations, enabling composition of new music from existing pieces or random starts even with small training sets.
citing papers explorer
-
Non-Parallel Voice Conversion with Cyclic Variational Autoencoder
CycleVAE optimizes non-parallel voice conversion indirectly via cyclic reconstructed spectra, yielding higher spectral accuracy, latent feature correlation, and improved converted speech quality.
-
Classical Music Prediction and Composition by means of Variational Autoencoders
VAEs are trained on classical music to encode pieces into latent space and predict continuations, enabling composition of new music from existing pieces or random starts even with small training sets.