Title :
Adjusted training of HMM models for Slovak speech recognition system
Author_Institution :
Fac. of Electr. Eng. & Inf. Technol., Slovak Univ. of Technol., Bratislava
Abstract :
In this article the relevant training aspects for building robust and accurate HMM models for large vocabulary recognition system in Slovak are discussed. As the basis for building HMM models the MASPER training procedure was assumed, and applied on the Slovak MOBILDAT database.
Keywords :
hidden Markov models; natural languages; speech recognition; training; HMM models; MOBILDAT database; Slovak; adjusted training; speech recognition system; Databases; GSM; Hidden Markov models; Information technology; Multi-layer neural network; Robustness; Speech recognition; Testing; Training data; Vocabulary;
Conference_Titel :
Signal Processing and Communication Systems, 2008. ICSPCS 2008. 2nd International Conference on
Conference_Location :
Gold Coast
Print_ISBN :
978-1-4244-4243-0
Electronic_ISBN :
978-1-4244-4243-0
DOI :
10.1109/ICSPCS.2008.4813758
