Publication Details
Differences between context dependent and context independent Hidden Markov Models for recognition of Czech
speech recognition, Hidden Markov models, context modeling, Czech speech recognition
Differences between context dependent (CD) and context independent (CI) Hidden Markov Models for recognition of Czech. The models were trained on SpeechDat-E database. The results with different training setups are presented. CD models are producing better results.
In speech recognition, context dependent (CD) models generally provide
better recognition accuracy than context independent (CI) ones. ThIn this
paper, we describe the tests of CD models on the recognition of Czech
isolated words. The models were trained on SpeechDat-E database. The
results with different training setups are presented, and some problems
are discussed
@INPROCEEDINGS{FITPUB7066, author = "Jan \v{C}ernock\'{y} and Martin Karafi\'{a}t", title = "Differences between context dependent and context independent Hidden Markov Models for recognition of Czech", pages = 5, booktitle = "Proc. of 8th student conference STUDENT EEICT 2002", year = 2002, location = "Brno, CZ", publisher = "Faculty of Electrical Engineering TUB", ISBN = "80-214-2116-9", language = "english", url = "https://www.fit.vut.cz/research/publication/7066" }