Tweeted By @ml_review
FastSpeech: Fast, Robust and Controllable Text to Speech
— ML Review (@ml_review) May 27, 2019
speeds up the mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x
ArXivhttps://t.co/foMEVhqA5y
Sampleshttps://t.co/HhLtzvBrkV pic.twitter.com/INHrX7WQQN