Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICASSP.2009.4960620 | Taipei |
Keywords | Field | DocType |
learning (artificial intelligence),multilayer perceptrons,natural languages,speech recognition,Arabic speech recognition,MLP feature training,graphemic system,linear input network,multilayer perceptron,short vowel modelling,word error rate,Acoustic Modelling,Arabic Speech Recognition,Multi-Layer Perceptron,Speaker Adaptation | Pattern recognition,Computer science,Word error rate,Speech recognition,Multilayer perceptron,Natural language,Artificial intelligence,Hidden Markov model,Loudspeaker,Discriminative model,Vocabulary,Perceptron | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4244-2354-5 | 978-1-4244-2354-5 | 13 |
PageRank | References | Authors |
1.27 | 5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jihoon Park | 1 | 143 | 27.61 |
Diehl, F. | 2 | 13 | 1.27 |
Mark J. F. Gales | 3 | 3905 | 367.45 |
Marcus Tomalin | 4 | 114 | 11.25 |