BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:On modern techniques for parallel waveform generation of speech - 
 Lorenzo Foglianti\, Papercup
DTSTART:20190205T160000Z
DTEND:20190205T170000Z
UID:TALK116548@talks.cam.ac.uk
CONTACT:CCA
DESCRIPTION:At Papercup\, we aim to translate the world's content. What th
 is means in practice is to translate audio from an input language to an ou
 tput language. In this talk\, we will focus on what we consider the most i
 nteresting part of this problem\, which is the function mapping text to au
 dio. Over the past few years\, Machine Learning research has made a giant 
 leap forward in the quality of the synthesised audio compared to more trad
 itional methods. However\, these methods are inherently autoregressive and
  therefore cannot be parallelised on modern machines. Because of this\, th
 ese methods can rarely be deployed in practice. Hence\, the synthesis time
  is limited by the nature of the model\, rather than the hardware. In this
  talk\, we present a new class of models\, called Flows\, which allows us 
 to generate audio in a non autoregressive way. We will also show sample au
 dio synthesised by state of the art models.
LOCATION:MR5
END:VEVENT
END:VCALENDAR