Abstract

11:00-12:00 Oral presentations:

Xunying Liu, Federico Flego, Linlin Wang, C. Zhang, Mark J.F. Gales, Philip C. Woodland

The Cambridge University 2014 BOLT Conversational Telephone Mandarin Chinese LVCSR System for Speech Translation

X. Chen, T. Tan, Xunying Liu, Pierre Lanchantin, M. Wan, Mark J.F. Gales, Philip C. Woodland

Recurrent Neural Network Language Model Adaptation for Multi-Genre Broadcast Speech Recognition

Rogier C. van Dalen, Kate M. Knill, Mark J. F. Gales

Automatically Grading Learners’ English Using a Gaussian Process (SLaTE paper)

12:00-13:00 Posters (and sandwiches):

Pierre Lanchantin, Christophe Veaux, Mark J.F. Gales, Simon King, Junichi Yamagishi

Reconstructing Voices Within the Multiple-Average-Voice-Model Framework

C. Zhang, Philip C. Woodland

Parameterised Sigmoid and ReLU Hidden Activation Functions for DNN Acoustic Modelling

Chao Zhang, Philip C. Woodland

A General Artificial Neural Network Extension for HTK

Haipeng Wang, Anton Ragni, Mark J.F. Gales, Kate M. Knill, Philip C. Woodland, C. Zhang

Joint Decoding of Tandem and Hybrid Systems for Improved Keyword Spotting on Low Resource Languages