Please use this identifier to cite or link to this item:
|Title:||Model-based articulatory phonetic features for improved speech recognition||Authors:||Huang, Guangpu
Er, Meng Joo
|Keywords:||DRNTU::Engineering::Electrical and electronic engineering||Issue Date:||2012||Source:||Huang, G., & Er, M. J. (2012). Model-based articulatory phonetic features for improved speech recognition. The 2012 International Joint Conference on Neural Networks (IJCNN).||Abstract:||We describe a neural based articulatory phonetic inversion model to improve the recognition of the acoustically varying vowels and the syllable initial plosives. The model uses a set of continuous valued articulatory phonetic features (APFs) to explore the interactions between the motor control of articulators and the acoustic phonetic events. We demonstrate that the neural model gives more accurate and robust recognition performance on the TIMIT sentences. The model offers two salient properties: it allows asynchronous feature changes at phoneme boundaries, and it accounts for the dual aspects of human speech production and perception through a heuristic learning algorithm during APFs mapping.||URI:||https://hdl.handle.net/10356/97868
|DOI:||10.1109/IJCNN.2012.6252748||Rights:||© 2012 IEEE.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||EEE Conference Papers|
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.