Patrick Wambacq — accepted AI-conference papers

2016

Language model adaptation for ASR of spoken translations using phrase-based translation models and named entity models

Joris Pelemans, Tom Vanallemeersch, Kris Demuynck, Lyan Verwimp, Hugo Van hamme, Patrick Wambacq

ICASSP 2016accepted

Language model adaptation based on Machine Translation (MT) is a recently proposed approach to improve the Automatic Speech Recognition (ASR) of spoken translations that does not suffer from a common problem in approaches based on rescoring i.e. errors made during recognition cannot be recovered by…

Cited by 4 Source ↗Scholar ↗

2015

Improving n-gram probability estimates by compound-head clustering

Joris Pelemans, Kris Demuynck, Hugo Van hamme, Patrick Wambacq

ICASSP 2015accepted

Compounding is one of the most productive word formation processes in many languages and is therefore a main source of data sparsity in language modeling. Many solutions have been suggested to model compound words, most of which break the compound into its constituents and train a new model with the…

Cited by 0 Source ↗Scholar ↗