Search

26 Sep 2016: Principal Investigator). Dr. Milica Gašić (Lecturer in Spoken Dialogue Systems). Dr. Lina M. Rojas-Barahona (Research Associate). Dr. Stefan Ultes (Research Associate). Contents 2016 Lina Rojas - Powered by Nikola.

24 Jun 2016: log-linear and other discriminative models. People.

22 Feb 2016: Computer Vision:. Making machines see. Roberto Cipolla Department of Engineering. http://www.eng.cam.ac.uk/cipolla/people.html.

26 Jul 2016: Structured and InûniteDiscriminative Models for. Speech Recognition. Jingzhou YangHomerton College. Department of Engineering. University of Cambridge. A thesis submitted to the University of Cambridge for the degree of. Doctor of Philosophy.

26 Sep 2016: Spoken Dialogue Systems (SDS) encompass the technologies required to build effective man-machine interfaces which depend primarily on voice. To date they have mostly been deployed in telephone-based call centre applications such as banking, billing

12 May 2016: use discrimative criteria to train generative models– ML people not that happy with use and term! •

26 Sep 2016: Open Domain Statistical Spoken Dialogue Systems. In a conventional SDS, all of the shaded components are rule-driven (Bratman 1988, Paek and Pieraccini 2008). In a statistical SDS, however, the end-to-end process is modelled as a partially

12 May 2016: Can we eliminate the HMM? – Not yet - but people are working on it e.g.

26 Sep 2016: Contents 2016 Lina Rojas - Powered by Nikola.

26 Sep 2016: Lina M. Rojas-Barahona, M. Gašić, N. Mrkšić, P-H. Su,S. Ultes, T-H. Wen and S. Young. Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding. In Coling, 2016. To appear. M. Gašić, N.