Real time Translation of Discrete Sinhala Speech to Unicode Text

dc.contributor.author	Gunasekara, M.K.H.
dc.contributor.author	Meegama, R.G.N.
dc.date.accessioned	2015-09-29T08:26:11Z
dc.date.available	2015-09-29T08:26:11Z
dc.date.issued	2015-09-29T08:26:11Z
dc.identifier.citation	Gunasekara, M.K.H., & Meegama, R.G.N. (2015). Real time Translation of Discrete Sinhala Speech to Unicode Text. Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer).
dc.identifier.uri	http://dr.lib.sjp.ac.lk/handle/123456789/1908
dc.description.abstract	This paper presents a methodology to translate discrete Sinhala speech to Sinhala Unicode text in real time. Initially, the Hidden Markov Model and the associated Hidden Markov Toolkit (HTK) is used as the speech recognizer. While real time decoding is obtained bythe Julius decoder a three-states Bakis HMM topology is used to build the acoustic model. The normalized Mel frequency cepstral coefficients with zeroth coefficient as feature vector is used to recognize speech. Although a single person is used during the training session, an average accuracy of 95% is obtained for both speaker dependent and speaker independent speech recognition. Performance evaluation shows the capabilities of the proposed system to convert discrete Sinhala speech to Sinhala Unicode in both quiet and noisy environments.	en_US
dc.language.iso	en	en_US
dc.subject	Automatic Speech recognition	en_US
dc.subject	Hidden Markov Models	en_US
dc.subject	Sinhala speech	en_US
dc.title	Real time Translation of Discrete Sinhala Speech to Unicode Text	en_US
dc.type	Article	en_US
dc.date.published	2015