InterSpeech 2021

WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
(Oral presentation)

Nanxin Chen (Johns Hopkins University, USA), Yu Zhang (Google, USA), Heiga Zen (Google, Japan), Ron J. Weiss (Google, USA), Mohammad Norouzi (Google, Canada), Najim Dehak (Johns Hopkins University, USA), William Chan (Google, Canada)
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 of the waveform given a phoneme sequence. The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform. This contrasts to the original WaveGrad vocoder which conditions on mel-spectrogram features, generated by a separate model. The iterative refinement process starts from Gaussian noise, and through a series of refinement steps (e.g., 50 steps), progressively recovers the audio sequence. WaveGrad 2 offers a natural way to trade-off between inference speed and sample quality, through adjusting the number of refinement steps. Experiments show that the model can generate high fidelity audio, approaching the performance of a state-of-the-art neural TTS system. We also report various ablation studies over different model configurations. Audio samples are publicly available.