Title :
The analysis of existing signal preconditioning algorithms for speech recognition
Author :
Rostuntsev, S.D. ; Aksyonov, K.A.
Author_Institution :
Ural Fed. Univ., Yekaterinburg, Russia
Abstract :
In this work are described main algorithms steps of signal preconditioning for speech recognition systems. Existing methods are discussed in the paper such as: statistical data collection of speech signals for system learning; input data filtering; frontiers detection of a message information part; and spectral transformation of a speech signal with normalization of frequency specter.
Keywords :
filtering theory; spectral analysis; speech recognition; frequency specter normalization; frontiers detection; input data filtering; signal preconditioning algorithms; spectral transformation; speech recognition systems; speech signal; statistical data collection; system learning; Abstracts; Algorithm design and analysis; Educational institutions; Electronic mail; Region 8; Speech; Speech recognition;
Conference_Titel :
Microwave and Telecommunication Technology (CriMiCo), 2013 23rd International Crimean Conference
Conference_Location :
Sevastopol
Print_ISBN :
978-966-335-395-1
