Training and adapting MLP features for Arabic speech recognition

Features derived from Multi-Layer 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 re-use; 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.

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: J. Park, Frank Diehl, M. J. F. Gales, Marcus Tomalin, Philip C. Woodland
• Keywords: ICASSP 2009, MLP Feature Adaptation, Short-vowel Modelling, Signal Processing, Speech Recognition