You are here

Natural Speech Technology Annual Meeting 2012

Informatics Forum

The Natural Speech Technology Annual Meeting was hosted by CSTR at the Informatics Forum, Edinburgh University on 24 April 2012.  About 50 people attended from the project partners, the user group, the advisory board and EPSRC.  

The following talks provide an overview of the NST programme:

  • Overview of Natural Speech Technology (Steve Renals) [pdf]
  • Natural Speech Transcription (Phil Woodland) [pdf]
  • Natural Speech Synthesis (Simon King) [pdf]
  • homeService Application (Phil Green, Heidi Christensen) [pdf]

More details of specific research topics were presented in these talks:

  • Structuring Diverse Data (Pierre Lanchantin) [pdf]
  • BBC Sample Data Processing (Yanhua Long) [pdf]
  • Acoustic Modelling with Subspace Gaussian Mixture Models (Arnab Ghoshal) [pdf]
  • Deep Neural Networks for Cross-lingual Speech Recognition (Pawel Swietojanski) [pdf]
  • Natural Speech Recognition Output (Marcus Tomalin) [pdf]
  • Paraphrastic Language Models (Xunying Liu) [pdf]

These are some initial demonstrations, presented at the NST Annual Meeting in Edinburgh on 24 April 2012: