Tacotron: Towards End-to-End Speech Synthesis
GPTKB entity
Statements (31)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:academic_journal
|
gptkbp:approach |
end-to-end speech synthesis
|
gptkbp:author |
gptkb:Rob_Clark
gptkb:Joel_Shor gptkb:Daisy_Stanton gptkb:RJ_Skerry-Ryan gptkb:Rif_A._Saurous gptkb:Yannis_Agiomyrgiannakis gptkb:Ying_Xiao Yuxuan Wang Jonathan Shen Ryan A. Saurous |
gptkbp:citation |
high
|
gptkbp:field |
deep learning
speech synthesis |
https://www.w3.org/2000/01/rdf-schema#label |
Tacotron: Towards End-to-End Speech Synthesis
|
gptkbp:influenced |
gptkb:Tacotron_2
modern TTS systems |
gptkbp:input |
gptkb:text
|
gptkbp:organization |
gptkb:Google
|
gptkbp:output |
mel spectrogram
|
gptkbp:proposedBy |
Tacotron model
|
gptkbp:publicationYear |
2017
|
gptkbp:publishedIn |
gptkb:arXiv
|
gptkbp:url |
https://arxiv.org/abs/1703.10135
|
gptkbp:uses |
attention mechanism
sequence-to-sequence model CBHG module Griffin-Lim algorithm |
gptkbp:bfsParent |
gptkb:Tacotron
|
gptkbp:bfsLayer |
7
|