Triphone Clustering for High Accuracy Acoustic Modeling in Continuous Speech Recognition in Sinhala

No Thumbnail Available

Date

2014

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

Collections

Endorsement

Review

Supplemented By

Referenced By