Logo Goletty

Visual Features for Lithuanian Phone Recognition
Journal Title Electronics and Electrical Engineering
Journal Abbreviation elt
Publisher Group Kaunas University of Technology (KTU) Open Journal Systems (KTU)
Website http://www.eejournal.ktu.lt/index.php/elt
PDF (654 kb)
   
Title Visual Features for Lithuanian Phone Recognition
Authors Tamulevičius, G.; Eringis, D.
Abstract Paper presents visual features for speech recognition. Visual speech recognition can be applied as support for acoustical recognition process or as stand-alone speech recognition approach in the case of absence of acoustical data. Geometrical features of speaker‘s lips are presented. Statistical analysis of feature values enabled us to select individual feature for each analyzed phone and one combined feature for all phones. The discriminative power was tested using Bayes classification rule. 4th order analysis enabled us to recognize phones with the average rate of 60.3 %, the highest recognition rate of 81.3 % was achieved identifying phone [o].DOI: http://dx.doi.org/10.5755/j01.eee.19.5.1724
Publisher Kaunas University of Technology
Date 2013-05-15
Source Elektronika ir elektrotechnika Vol 19, No 5 (2013)
Rights Autorių teisės yra apibrėžtos Lietuvos Respublikos autorių teisių ir gretutinių teisių įstatymo 4-37 straipsniuose.

 

See other article in the same Issue


Goletty © 2024