ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

VAENAR-TTS: Variational Auto-Encoder Based Non-AutoRegressive Text-to-Speech Synthesis

Hui Lu, Zhiyong Wu, Xixin Wu, Xu Li, Shiyin Kang, Xunying Liu, Helen Meng

This paper describes a variational auto-encoder based non-autoregressive text-to-speech (VAENAR-TTS) model. The autoregressive TTS (AR-TTS) models based on the sequence-to-sequence architecture can generate high-quality speech, but their sequential decoding process can be time-consuming. Recently, non-autoregressive TTS (NAR-TTS) models have been shown to be more efficient with the parallel decoding process. However, these NAR-TTS models rely on phoneme-level durations to generate a hard alignment between the text and the spectrogram. Obtaining duration labels, either through forced alignment or knowledge distillation, is cumbersome. Furthermore, hard alignment based on phoneme expansion can degrade the naturalness of the synthesized speech. In contrast, the proposed model of VAENAR-TTS is an end-to-end approach that does not require phoneme-level durations. The VAENAR-TTS model does not contain recurrent structures and is completely non-autoregressive in both the training and inference phases. Based on the VAE architecture, the alignment information is encoded in the latent variable, and attention-based soft alignment between the text and the latent variable is used in the decoder to reconstruct the spectrogram. Experiments show that VAENAR-TTS achieves state-of-the-art synthesis quality, while the synthesis speed is comparable with other NAR-TTS models.

doi: 10.21437/Interspeech.2021-2121

Cite as: Lu, H., Wu, Z., Wu, X., Li, X., Kang, S., Liu, X., Meng, H. (2021) VAENAR-TTS: Variational Auto-Encoder Based Non-AutoRegressive Text-to-Speech Synthesis. Proc. Interspeech 2021, 3775-3779, doi: 10.21437/Interspeech.2021-2121

  author={Hui Lu and Zhiyong Wu and Xixin Wu and Xu Li and Shiyin Kang and Xunying Liu and Helen Meng},
  title={{VAENAR-TTS: Variational Auto-Encoder Based Non-AutoRegressive Text-to-Speech Synthesis}},
  booktitle={Proc. Interspeech 2021},