activity
20192022
most citedBuilding a mixed-lingual neural TTS system with only monolingual data

4 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing 2020Show all

1 paper · 1 filter

eess.AS2020

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

Guanghui Xu, Wei Song, Zhengchen Zhang +3

Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which ma…