Triphone Clustering for High Accuracy Acoustic Modeling in Continuous Speech Recognition in Sinhala
No Thumbnail Available
Date
2014
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Book of Abstracts, Annual Research Symposium 2014
Abstract
Word-internal context-dependent phoneme models, such as triphones, are used to create Hidden Markov Models (HMMs) for speech recognition. The large number of triphones results the excessive number of model parameters to be trained the HMMs. In order to reduce the number of model parameters, created triphones can be tied together to enhance the quality and robustness of HMMs. Data driven clustering or decision tree state clustering can be used to tie triphones to share the same set of parameters.
Description
Keywords
Citation
Annual Research Symposium,Faculty of Graduate Studies, University of Kelaniya, Sri Lanka; 2014 :117p