Title :
A decoder for large vocabulary speech recognition
Author :
Nikša Jakovljević;Dragiša Mišković;Marko Janev;Darko Pekar
Author_Institution :
Dept. for Telecommunication and Signal Processing, Faculty of Technical Sciences, Novi Sad, Serbia
fDate :
6/1/2011 12:00:00 AM
Abstract :
This paper describes a decoder for large vocabulary continuous speech recognition developed at the Faculty of Technical Sciences, University of Novi Sad. The decoder is an open source solution written in the C++ programming language. The structure of the decoder is modular, allowing relatively simple modification and expansion of the code. It can be used in combination with standard speech recognition tools such as Hidden Markov Model Toolkit (HTK) and the language modelling tool SRILM.
Keywords :
"Hidden Markov models","Decoding","Acoustics","Speech recognition","Object oriented modeling","Load modeling","Dictionaries"
Conference_Titel :
Systems, Signals and Image Processing (IWSSIP), 2011 18th International Conference on
Print_ISBN :
978-1-4577-0074-3
Electronic_ISBN :
2157-8702
