P
Pierre Lanchantin
Researcher at University of Cambridge
Publications - 53
Citations - 1071
Pierre Lanchantin is an academic researcher from University of Cambridge. The author has contributed to research in topics: Speech synthesis & Hidden Markov model. The author has an hindex of 18, co-authored 53 publications receiving 992 citations. Previous affiliations of Pierre Lanchantin include Telecom SudParis & Citigroup.
Papers
More filters
Proceedings ArticleDOI
The MGB challenge: Evaluating multi-genre broadcast media recognition
Peter Bell,Mark J. F. Gales,Thomas Hain,Jonathan Kilgour,Pierre Lanchantin,Xunying Liu,A McParland,Steve Renals,Oscar Saz,Mirjam Wester,Philip C. Woodland +10 more
TL;DR: An evaluation focused on speech recognition, speaker diarization, and "lightly supervised" alignment of BBC TV recordings at ASRU 2015 is described, and the results obtained are summarized.
Proceedings ArticleDOI
Recurrent neural network language model adaptation for multi-genre broadcast speech recognition
Xie Chen,Tian Tan,Xunying Liu,Pierre Lanchantin,Moquan Wan,Mark J. F. Gales,Philip C. Woodland +6 more
TL;DR: Experiments using a state-of-theart LVCSR system showed adaptation could yield perplexity reductions of 8% relatively over the baseline RNNLM and small but consistent word error rate reductions.
Proceedings ArticleDOI
Statistical image segmentation using Triplet Markov fields
TL;DR: The PMF is generalized to Triplet Markov Fields (TMF) by adding a third random field U=(Us) and considering the Markovianity of (X, U, Y) and it is shown that in TMF X is still estimable from Y by Bayesian methods.
Journal ArticleDOI
Unsupervised segmentation of randomly switching data hidden with non-Gaussian correlated noise
TL;DR: This paper proposes a simultaneous solution to semi-supervised and unsupervised image segmentation problems using triplet Markov chains (TMC) and copulas.
Journal ArticleDOI
Unsupervised restoration of hidden nonstationary Markov chains using evidential priors
TL;DR: This paper shows, via simulations, that the classical restoration results can be improved by the use of the theory of evidence and Dempster-Shafer fusion, and is performed in an entirely unsupervised way using an original parameter estimation method.