DocumentCode :
3622347
Title :
On Real-Time Mean-and-Variance Normalization of Speech Recognition Features
Author :
P. Pujol;D. Macho;C. Nadeu
Author_Institution :
TALP Research Center, Universitat Politecnica de Catalunya, Barcelona, Spain. pujol@talp.upc.edu
Volume :
1
fYear :
2006
fDate :
6/28/1905 12:00:00 AM
Abstract :
This work aims at gaining an insight into the mean and variance normalization technique (MVN), which is commonly used to increase the robustness of speech recognition features. Several versions of MVN are empirically investigated, and the factors affecting their performance are considered. The reported experimental work with real-world speech data (Speecon) particularly focuses on the recursive updating of MVN parameters, paying attention to the involved algorithmical delay. First, we propose a decoupling of the look-ahead factor (which determines the delay) and the initial estimation of mean and variance, and show that the latter is a key factor for the recognition performance. Then, several kinds of initial estimations that make sense in different application environments are tested, and their performance is compared
Keywords :
"Speech recognition","Delay estimation","Testing","Microphones","Hidden Markov models","Databases","Microwave integrated circuits","Helium","Gaussian processes","Robustness"
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
1-4244-0469-X
Electronic_ISBN :
2379-190X
Type :
conf
DOI :
10.1109/ICASSP.2006.1660135
Filename :
1660135
Link To Document :
بازگشت