Title :
Description of Training Procedure for AlfaNum Continuous Speech Recognition System
Author :
Jakovljevic, Niksha ; Pekar, Darko
Author_Institution :
Fac. of Eng., Novi Sad Univ.
Abstract :
This paper presents training procedure for our continuous speech recognition system in Serbian, based on hidden Markov models. In this paper, we focus on solutions of the problem of insufficient training data, and improvements obtained by maximum likelihood train algorithm
Keywords :
hidden Markov models; maximum likelihood estimation; natural languages; speech recognition; AlfaNum continuous speech recognition system; Serbian language; hidden Markov models; maximum likelihood train algorithm; Automatic speech recognition; Context modeling; Hidden Markov models; Robustness; Spatial databases; Speech recognition; State estimation; Telephony; Testing; Training data; Automatic speech recognition; hidden Markov models; maximum likelihood train algorithm and tying procedure;
Conference_Titel :
Computer as a Tool, 2005. EUROCON 2005.The International Conference on
Conference_Location :
Belgrade
Print_ISBN :
1-4244-0049-X
DOI :
10.1109/EURCON.2005.1630286
