Extracting Unit Embeddings Using Sequence-To-Sequence Acoustic Models for Unit Selection Speech Synthesis

Citation Author(s):: Xiao Zhou
Submitted by:: Xiao Zhou
Last updated:: 13 May 2020 - 9:21pm
Document Type:: Presentation Slides
Event:: ICASSP 2020
Presenters:: Xiao Zhou
Paper Code:: 2378

Categories:: Speech Synthesis and Generation, including TTS (SPE-SYNT)

Log in to post comments

Tacotron2_CSS_zhling_finalAudio_无旁白版.pptx

Tacotron2_CSS_zhling_finalAudio_无旁白版.pptx (196)

Thumbs Up

CITE

QUESTIONS?