DocumentCode
3180796
Title
Quantum neural network in speech recognition
Author
Li, Fei ; Zhao, Shengmei ; Zheng, Baoyu
Author_Institution
Inst. of Signal & Inf. Process., Nanjing Univ. of Posts & Telecommun., China
Volume
2
fYear
2002
fDate
26-30 Aug. 2002
Firstpage
1267
Abstract
This paper describes a new kind of neural network - quantum neural network (QNN) and its application to recognition of continuous digits. QNN combines the advantages of neural modeling and fuzzy theoretic principles. Experiment results show that more than 15% error reduction is achieved on a speaker-independent continuous digits recognition task compared with the backpropagation (BP) network.
Keywords
fuzzy neural nets; gradient methods; optical neural nets; quantum computing; speech recognition; artificial neural networks; backpropagation network; continuous digits recognition; error reduction; fuzzy theory; gradient-descent-based algorithm; neural modeling; neurocomputing; quantum computing; quantum neural network; speaker-independent continuous digits recognition; speech recognition; training algorithm; Artificial neural networks; Computer networks; Information processing; Intelligent networks; Neural networks; Neurons; Parallel processing; Quantum computing; Quantum mechanics; Speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing, 2002 6th International Conference on
Print_ISBN
0-7803-7488-6
Type
conf
DOI
10.1109/ICOSP.2002.1180022
Filename
1180022
Link To Document