T
Tony Robinson
Researcher at University of Cambridge
Publications - 58
Citations - 3171
Tony Robinson is an academic researcher from University of Cambridge. The author has contributed to research in topics: Hidden Markov model & Language model. The author has an hindex of 23, co-authored 58 publications receiving 2972 citations. Previous affiliations of Tony Robinson include Carnegie Mellon University & University of Colorado Denver.
Papers
More filters
Posted Content
One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
Ciprian Chelba,Tomas Mikolov,Mike Schuster,Qi Ge,Thorsten Brants,Phillipp Koehn,Tony Robinson +6 more
TL;DR: This paper proposed a new benchmark corpus for measuring progress in statistical language modeling, which consists of almost one billion words of training data and can be used to quickly evaluate novel language modeling techniques, and to compare their contribution when combined with other advanced techniques.
Proceedings ArticleDOI
One billion word benchmark for measuring progress in statistical language modeling.
Ciprian Chelba,Tomas Mikolov,Mike Schuster,Qi Ge,Thorsten Brants,Phillipp Koehn,Tony Robinson +6 more
TL;DR: A new benchmark corpus to be used for measuring progress in statistical language modeling, with almost one billion words of training data, is proposed, which is useful to quickly evaluate novel language modeling techniques, and to compare their contribution when combined with other advanced techniques.
Proceedings ArticleDOI
WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition
TL;DR: The motivation for the corpus, the processes undertaken in its construction and the utilities needed as support tools are described, and comparative results on these tasks for British and American English are concluded.
Proceedings Article
Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System
João Paulo Neto,Luís B. Almeida,Mike Hochberg,Ciro Martins,Luís Nunes,Steve Renals,Tony Robinson +6 more
TL;DR: These techniques are applied to a well trained, speaker-independent, hybrid HMM-ANN system and the recognizer parameters are adapted to a new speaker through o -line procedures and show that speaker-adaptation within the hybrid framework can substantially improve system performance.
Journal ArticleDOI
A recurrent error propagation network speech recognition system
Tony Robinson,Frank Fallside +1 more
TL;DR: A speaker-independent phoneme and word recognition system based on a recurrent error propagation network trained on the TIMIT database and analysis of the phoneme recognition results shows that information available from bigram and durational constraints is adequately handled within the network allowing for efficient parsing of the network output.