Score-based (denoising diffusion) generative models have recently gained a lot of success
in generating realistic and diverse data. These approaches define a forward diffusion …

Inspired by the recent progress in self-supervised learning for computer vision that
generates supervision using data augmentations, we explore a new general-purpose audio …

An ideal music synthesizer should be both interactive and expressive, generating high-
fidelity audio in realtime for arbitrary combinations of instruments and notes. Recent neural …

We present a novel way of conditioning a pretrained denoising diffusion speech model to
produce speech in the voice of a novel person unseen during training. The method requires …

This paper proposes a non-autoregressive extension of our previously proposed sequence-
to-sequence (S2S) model-based voice conversion (VC) methods. S2S model-based VC …

Diffusion models are a kind of math-based model that were first applied to image generation.
Recently, they have drawn wide interest in natural language generation (NLG), a sub-field of …

We propose Generative Probabilistic Image Colorization, a diffusion-based generative
process that trains a sequence of probabilistic models to reverse each step of noise …

The use of generated corrected accent speech with a learner's own voice holds potential for
second language learners to enhance their pronunciation through self-imitation exercises …

In this paper, we propose a non-parallel voice conversion method based on the
minimization of the free energy of a restricted Boltzmann machine (RBM). The proposed …

Diffusion generative models, which generate data by the timereverse dynamics of diffusion
processes, have attracted much attention recently, and have already been applied in the …