Filters








2 Hits in 6.3 sec

Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama's voice using GAN, WaveNet and low-quality found data [article]

Jaime Lorenzo-Trueba, Fuming Fang, Xin Wang, Isao Echizen, Junichi Yamagishi, Tomi Kinnunen
2018 arXiv   pre-print
Such examples include direct waveform modelling and generative adversarial networks. We also need to investigate the feasibility of training spoofing systems using only low-quality found data.  ...  Using the enhanced data, we trained state-of-the-art text-to-speech and voice conversion models and evaluated them in terms of perceptual speech quality and speaker similarity.  ...  the used Obama's found data.  ... 
arXiv:1803.00860v1 fatcat:rpq6yrwcjja7xdqnj5fvvzpaku

Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama's voice using GAN, WaveNet and low-quality found data

Jaime Lorenzo-Trueba, Fuming Fang, Xin Wang, Isao Echizen, Junichi Yamagishi, Tomi Kinnunen
2018 Odyssey 2018 The Speaker and Language Recognition Workshop  
Such examples include direct waveform modelling and generative adversarial networks. We also need to investigate the feasibility of training spoofing systems using only low-quality found data.  ...  Using the enhanced data, we trained state-of-the-art text-to-speech and voice conversion models and evaluated them in terms of perceptual speech quality and speaker similarity.  ...  the used Obama's found data.  ... 
doi:10.21437/odyssey.2018-34 dblp:conf/odyssey/Lorenzo-TruebaF18 fatcat:y4wpkijikngifof4zlg5tkohye