Yuki SAITO


Joint Adversarial Training of Speech Recognition and Synthesis Models for Many-to-One Voice Conversion Using Phonetic Posteriorgrams
Yuki SAITO Kei AKUZAWA Kentaro TACHIBANA 
Publication:   
Publication Date: 2020/09/01
Vol. E103-D  No. 9  pp. 1978-1987
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
many-to-one voice conversionphonetic posteriorgramsdeep neural networksover-smoothingdomain-adversarial traininggenerative adversarial networks
 Summary | Full Text:PDF(574.7KB)

Generative Moment Matching Network-Based Neural Double-Tracking for Synthesized and Natural Singing Voices
Hiroki TAMARU Yuki SAITO Shinnosuke TAKAMICHI Tomoki KORIYAMA Hiroshi SARUWATARI 
Publication:   
Publication Date: 2020/03/01
Vol. E103-D  No. 3  pp. 639-647
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
DNN-based singing-voice synthesisgenerative moment matching networkinter-utterance pitch variationartificial double-trackingmodulation spectrum
 Summary | Full Text:PDF(893.2KB)

Voice Conversion Using Input-to-Output Highway Networks
Yuki SAITO Shinnosuke TAKAMICHI Hiroshi SARUWATARI 
Publication:   
Publication Date: 2017/08/01
Vol. E100-D  No. 8  pp. 1925-1928
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
statistical parametric speech synthesisDNN-based voice conversionhighway networksover-smoothing
 Summary | Full Text:PDF(557.9KB)