Training and adapting MLP features for Arabic speech recognition
Lists
Only you see this
Abstract
Features derived from multilayer perceptrons (MLPs) are becoming increasingly popular for speech recognition. This paper describes various schemes for applying these features to state-of-the-art Arabic speech recognition: the use of MLP-features for short-vowel modelling in graphemic systems; rapid discriminative model training by standard PLP feature lattice reuse; and MLP feature adaptation using linear input networks (LIN). The use of rapid training using MLP features and their use for short-vowel modelling and LIN adaptation gave reductions in word error rate. However significant improvements over explicit short-vowel modelling with standard multi-pass adaptation were not obtained, although they were useful in combination.
BibTeX
@inproceedings{park2009training,
author = {Junho Park and Frank Diehl and Mark J. F. Gales and Marcus Tomalin and Philip C. Woodland},
title = {{Training and adapting MLP features for Arabic speech recognition}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2009},
doi = {10.1109/icassp.2009.4960620},
}Loading related content...