DocumentCode
2960489
Title
AANN-HMM models for speaker verification and speech recognition
Author
Joshi, S. ; Prahallad, K. ; Yegnanarayana, B.
Author_Institution
Int. Inst. of Inf. Technol., Hyderabad
fYear
2008
fDate
1-8 June 2008
Firstpage
2681
Lastpage
2688
Abstract
Pattern classification is an important task in speech recognition and speaker verification. Given the feature vectors of an input the goal is to capture the characteristics of these features unique to each class. This paper deals with exploring Auto Associative Neural Network (AANN) models for the task of speaker verification and speech recognition. We show that AANN models produce comparable performance with that of GMM based speaker verification and speech recognition.
Keywords
neural nets; pattern classification; speaker recognition; auto associative neural network; feature vectors; pattern classification; speaker verification; speech recognition; Feedforward neural networks; Joining processes; Matrix decomposition; Neural networks; Pattern classification; Principal component analysis; Probability; Speaker recognition; Speech recognition; Statistical distributions;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location
Hong Kong
ISSN
1098-7576
Print_ISBN
978-1-4244-1820-6
Electronic_ISBN
1098-7576
Type
conf
DOI
10.1109/IJCNN.2008.4634174
Filename
4634174
Link To Document