BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Prosody transfer evaluation and temporal prosody control in speech
  synthesis - Papercup
DTSTART:20210706T110000Z
DTEND:20210706T120000Z
UID:TALK161308@talks.cam.ac.uk
CONTACT:Dr Kate Knill
DESCRIPTION:*Ctrl-P: Temporal Control of Prosodic Variation for Speech Syn
 thesis*\n\nAbstract: We propose a model that generates speech explicitly c
 onditioned on the three primary acoustic correlates of prosody: F0\, energ
 y and duration. The model is flexible about how the values of these featur
 es are specified: they can be externally provided\, or predicted from text
 \, or predicted then subsequently modified. Compared to a model that emplo
 ys a variational auto-encoder to learn unsupervised latent features\, our 
 model provides more interpretable\, temporally-precise\, and disentangled 
 control.\n\n*ADEPT: A Dataset for Evaluating Prosody Transfer*\n\nAbstract
 : We introduce an English corpus of prosodically-varied reference natural 
 speech samples for evaluating prosody transfer. The samples include global
  and local variations across utterances. The corpus only includes prosodic
  variations that listeners are able to distinguish with reasonable accurac
 y\, and we report these figures as a benchmark against which text-to-speec
 h prosody transfer can be compared. We also propose a subjective prosody t
 ransfer evaluation methodology.\n\n*Speaker bios:*\n\nTian Huey Teh is a m
 achine learning engineer at Papercup\, based in London. She completed the 
 MSc Computational Statistics and Machine Learning programme at University 
 College London in 2018. Since graduating she has been working on TTS resea
 rch and development\, focusing on prosody modelling and scaling systems ac
 ross languages.\n\nAlexandra Torresquintero is a Data Engineer on the mach
 ine learning team at Papercup. She completed her MSc in Speech and Languag
 e processing at the University of Edinburgh in 2019. Whilst at Papercup\, 
 she has worked on formalising the processing behind the TTS training data\
 , including Linguistic Frontend optimisations\, research into g2p modellin
 g\, and building a database to store our data.
LOCATION:Zoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT
 2tDUT09
END:VEVENT
END:VCALENDAR