Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech

Yang Li, Cheng Yu, Guangzhi Sun, Hua Jiang, Fanglei Sun, Weiqin Zu, Ying Wen, Yang Yang, Jun Wang


Abstract
Modelling prosody variation is critical for synthesizing natural and expressive speech in end-to-end text-to-speech (TTS) systems. In this paper, a cross-utterance conditional VAE (CUC-VAE) is proposed to estimate a posterior probability distribution of the latent prosody features for each phoneme by conditioning on acoustic features, speaker information, and text features obtained from both past and future sentences. At inference time, instead of the standard Gaussian distribution used by VAE, CUC-VAE allows sampling from an utterance-specific prior distribution conditioned on cross-utterance information, which allows the prosody features generated by the TTS system to be related to the context and is more similar to how humans naturally produce prosody. The performance of CUC-VAE is evaluated via a qualitative listening test for naturalness, intelligibility and quantitative measurements, including word error rates and the standard deviation of prosody attributes. Experimental results on LJ-Speech and LibriTTS data show that the proposed CUC-VAE TTS system improves naturalness and prosody diversity with clear margins.
Anthology ID:
2022.acl-long.30
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
391–400
Language:
URL:
https://aclanthology.org/2022.acl-long.30
DOI:
10.18653/v1/2022.acl-long.30
Bibkey:
Cite (ACL):
Yang Li, Cheng Yu, Guangzhi Sun, Hua Jiang, Fanglei Sun, Weiqin Zu, Ying Wen, Yang Yang, and Jun Wang. 2022. Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 391–400, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech (Li et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.30.pdf
Code
 neurowave-ai/cucvae-tts
Data
LJSpeech