Browse > Article

A Method on the Learning Speed Improvement of the Online Error Backpropagation Algorithm in Speech Processing  

이태승 (한국항공대학교 항공전자공학과)
이백영 (한국항공대학교 항공전자공학과)
황병원 (한국항공대학교 항공전자공학과)
Abstract
Having a variety of good characteristics against other pattern recognition techniques, the multilayer perceptron (MLP) has been widely used in speech recognition and speaker recognition. But, it is known that the error backpropagation (EBP) algorithm that MLP uses in learning has the defect that requires restricts long learning time, and it restricts severely the applications like speaker recognition and speaker adaptation requiring real time processing. Because the learning data for pattern recognition contain high redundancy, in order to increase the learning speed it is very effective to use the online-based learning methods, which update the weight vector of the MLP by the pattern. A typical online EBP algorithm applies the fixed learning rate for each update of the weight vector. Though a large amount of speedup with the online EBP can be obtained by choosing the appropriate fixed rate, firing the rate leads to the problem that the algorithm cannot respond effectively to different learning phases as the phases change and the number of patterns contributing to learning decreases. To solve this problem, this paper proposes a Changing rate and Omitting patterns in Instant Learning (COIL) method to apply the variable rate and the only patterns necessary to the learning phase when the phases come to change. In this paper, experimentations are conducted for speaker verification and speech recognition, and results are presented to verify the performance of the COIL.
Keywords
Multilayer perceptron; Error backpropagation; Fast learning algorithm; Speaker verification; Sheech recognition; Fatten recognition;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Dynamic programming algorithm optimization for spoken word recognition /
[ H.Sakoe;S.Chiba ] / IEET Transactions on Acoustics,Speech,and Signal Processing   DOI
2 Integrating time alignment and connectionist networks for high performance continuous speech recognition /
[ P.Haffner;M.Franzini;A.Waibel ] / Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
3 A high performance text independent speaker recognition system based on vowel spotting and neural nets /
[ N.Fakotakis;J.Sirigos ] / Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing   DOI
4 A direct adaptive method for faster backpropagation learning: the rprop algorithm /
[ M.Riedmiller;H.Braun ] / Proceedings of the IEEE International Conference on Neural Networks
5 Links between hidden markov models and multilayer perceptrons /
[ H.Bourlard;C.Wellekens ] / IEEE Transactions on Pattern Analysis and Machine Intelligence   DOI   ScienceOn
6 Supervised learning on large redundant training sets /
[ M.Moller ] / Proceedings of the 1992 IEEE-SP Workshop Neural Networks for Signal Processing
7 Phoneme recognition using time-delay neural networks /
[ A.Waibel;T.Hanazawa;G.Hinton;K.Shikano;K.J.Lang ] / IEEE Transactions on Acoustics,Speech,and Signal Processing   DOI   ScienceOn
8 Learning Internal representations by error propagation /
[ D.E.Rumelhart;G.E.Hinton;R.J.Williams ] / Parallel Distributed Processing
9 /
[ S.Haykin ] / Neural Networks
10 /
[ C.Becchetti;L.P.Ricotti ] / Speech Recognition
11 /
[ Y.Bengio ] / Neural Networks for Speech and Sequence Recognition
12 A modular connectionist architecture for text-independent talker identification /
[ Y.Bennani;P.Gallinari ] / Proceedings of the International Joint Conference on Neural Networks
13 /
[ H.Demuth;M.Beale ] / Neural Network Toolbox
14 A segment-based speaker adaptation neural network applied to continuous speech recognition /
[ K.Fukuzawa;Y.Komori;H.Sawai;M.Sugiyama ] / Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
15 Speaker verification: a tutorial /
[ J.M.Naik ] / IEEE Communications Magazine
16 Improving the convergence of back-propagation learning with second-order methods /
[ S.Becker;Y.LeCun ] / Proceedings of the 1988 Connectionist Models Summer School
17 The need for small learning rates on large problems /
[ D.R.Wilson;T.R.Martinez ] / Proceedings of the International Joint Conference on Neural Networks
18 /
[ R.Fletcher ] / Practical Methods of Optimization
19 Speaker-Independent word recognition using dynamic programming neural networks /
[ H.Sakoe;R.Isotani;K.Yoshida;K.I.Iso;T.Watanabe ] / Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
20 A tutorial on hidden markov models and selected applications in speech recognition /
[ L.R.Rabiner ] / Proceedings of the IEEE   DOI   ScienceOn
21 Hybrid connectionist models for continuous speech recognition /
[ N.Morgan;H.Bourlard ] / Automatic Speech and Speaker Recognition