SOTAVerified

Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions

2017-12-16Code Available1· sign in to hype

Jonathan Shen, Ruoming Pang, Ron J. Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, RJ Skerry-Ryan, Rif A. Saurous, Yannis Agiomyrgiannakis, Yonghui Wu

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of 4.53 comparable to a MOS of 4.58 for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and F_0 features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture.

Tasks

Speech Synthesis

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
North American EnglishTacotron 2Mean Opinion Score4.53—Unverified
North American EnglishWaveNet (Linguistic)Mean Opinion Score4.34—Unverified

Reproductions