Parallel Tacotron: Non-Autoregressive and Controllable TTS
| Autor: | Ron Weiss, Ye Jia, Jonathan Shen, Heiga Zen, Yu Zhang, Yonghui Wu, Isaac Elias |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer science Inference Residual Autoencoder Computer Science - Sound Naturalness Autoregressive model Audio and Speech Processing (eess.AS) Iterative refinement FOS: Electrical engineering electronic engineering information engineering Spectrogram Encoder Algorithm Electrical Engineering and Systems Science - Audio and Speech Processing |
| Zdroj: | ICASSP |
| Popis: | Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented with a variational autoencoder-based residual encoder. This model, called \emph{Parallel Tacotron}, is highly parallelizable during both training and inference, allowing efficient synthesis on modern parallel hardware. The use of the variational autoencoder relaxes the one-to-many mapping nature of the text-to-speech problem and improves naturalness. To further improve the naturalness, we use lightweight convolutions, which can efficiently capture local contexts, and introduce an iterative spectrogram loss inspired by iterative refinement. Experimental results show that Parallel Tacotron matches a strong autoregressive baseline in subjective evaluations with significantly decreased inference time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|