AIConfPaper
← Search

Zhengchen Zhang

2 accepted papers

2021

Dian: Duration Informed Auto-Regressive Network for Voice Cloning

Wei Song, Xin Yuan, Zhengchen Zhang, Chao Zhang, Youzheng Wu, Xiaodong He +1
ICASSP 2021accepted

In this paper, we propose a novel end-to-end speech synthesis approach, Duration Informed Auto-regressive Network (DIAN), which consists of an acoustic model and a separate duration model. Un-like other auto-regressive TTS methods, the duration information of phonemes is provided as part of the inpu…

Cited by 0Source ↗Scholar ↗
2021

Improving Prosody Modelling with Cross-Utterance Bert Embeddings for End-to-End Speech Synthesis

Guanghui Xu, Wei Song, Zhengchen Zhang, Chao Zhang, Xiaodong He, Bowen Zhou
ICASSP 2021accepted

Although speech prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account the information within each sentence. This makes it challenging when converting a paragraph of text into natural and expressive speech. In this pap…

Cited by 0Source ↗Scholar ↗