You are here


Posters (Atrium)

  • Investigating the shortcomings of HMM synthesis (Tom Merritt) [poster]
  • The Sheffield Wargames Corpus (Charles Fox , Yulan Liu , Erich Zwyssig and Thomas Hain) + demo [poster]
  • A grapheme-based method for automatic alignment of speech and text data (Adriana Stan, Peter Bell, and Simon King)[poster]
  • Transcription of multi-genre media archives using out-of-domain data (Peter Bell, Mark Gales, Pierre Lanchantin, Andrew Liu, Yanhua Long, Steve Renals, Pawel Swietojanski, Phil Woodland) [poster]
  • Multi-level adaptive networks in tandem and hybrid ASR systems (Peter Bell, Pawel Swietojanski, and Steve Renals) [poster]
  • Cross-lingual knowledge transfer in DNN-based low-resource LVCSR (Pawel Swietojanski, Arnab Ghoshal, and Steve Renals) [poster]
  • Fast, low-artifact speech synthesis considering global variance (Matt Shannon and William Byrne) [poster]
  • Factorized context modelling for text-to-speech synthesis (Heng Lu and Simon King) [poster]
  • Improving Lightly Supervised Training for Broadcast Transcription (Yanhua Long, Mark Gales, Pierre Lanchantin, Xunying Liu, Matt Seigel and Phil Woodland) [poster]

Posters in G.03 (demo room)

  • homeService: making natural, voice-enabled interfaces (Heidi Christensen, Stuart Cunningham, Charles Fox, Phil Green, Thomas Hain) [poster]
  • A comparative study of adaptive, automatic recognition of disordered speech (Heidi Christensen, Stuart Cunningham, Charles Fox, Phil Green and Thomas Hain) [poster]

Linked posters (Atrium)

  • Ultrax (University of Edinburgh) [poster]
  • SPECS (University of Sheffield)
  • Simple4All (University of Edinburgh) [poster]
  • EU-Bridge (University of Edinburgh) [poster]