|
gptkbp:instanceOf
|
speech synthesis system
|
|
gptkbp:application
|
text-to-speech
|
|
gptkbp:arXivID
|
1703.10135
|
|
gptkbp:author
|
gptkb:Rob_Clark
gptkb:Samy_Bengio
gptkb:Navdeep_Jaitly
gptkb:Quoc_V._Le
gptkb:Daisy_Stanton
gptkb:RJ_Skerry-Ryan
gptkb:Rif_A._Saurous
gptkb:Ron_J._Weiss
gptkb:Yannis_Agiomyrgiannakis
gptkb:Ying_Xiao
gptkb:Yonghui_Wu
gptkb:Zhifeng_Chen
gptkb:Zongheng_Yang
Yuxuan Wang
|
|
gptkbp:citation
|
gptkb:Tacotron:_Towards_End-to-End_Speech_Synthesis
2017
|
|
gptkbp:developedBy
|
gptkb:Google
|
|
gptkbp:field
|
gptkb:artificial_intelligence
gptkb:machine_learning
natural language processing
speech synthesis
|
|
gptkbp:firstReleased
|
2017
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Tacotron
|
|
gptkbp:input
|
gptkb:text
|
|
gptkbp:language
|
English
|
|
gptkbp:openSource
|
yes
|
|
gptkbp:output
|
mel spectrogram
|
|
gptkbp:relatedTo
|
gptkb:WaveNet
gptkb:Deep_Voice
gptkb:Tacotron_2
|
|
gptkbp:successor
|
gptkb:Tacotron_2
|
|
gptkbp:uses
|
recurrent neural network
attention mechanism
sequence-to-sequence model
|
|
gptkbp:bfsParent
|
gptkb:Speech_Synthesis
gptkb:WaveNet
|
|
gptkbp:bfsLayer
|
6
|