343 citations · 615 across the 10 of their papers we have counts for
5 papers · 1 filter
WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration
Yuma Koizumi, Kohei Yatabe, Heiga Zen +1
Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characteriz…
WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
Nanxin Chen, Yu Zhang, Heiga Zen +4
This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density…
WaveGrad: Estimating Gradients for Waveform Generation
Nanxin Chen, Yu Zhang, Heiga Zen +3
This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and di…
Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior
Guangzhi Sun, Yu Zhang, Ron J. Weiss +5
Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech. Such models typically incorporate a fine-gr…
Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis
Guangzhi Sun, Yu Zhang, Ron J. Weiss +3
This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution mode…