Abstract:
A novel system that efficiently integrates two types of neural networks for reliably performing isolated word recognition is described. The recognition system comprises of a feature extractor that includes a Self Organizing Map for an optimal tailoring of trajectory representations of words in reduced dimension feature spaces. Experimental results indicate that such lower dimensional trajectories can provide a reliable representation of spoken words, while reducing the training complexity for the recognition of the trajectory. A recurrent neural network is employed for performing trajectory recognition and a method that allows to progressively grow the training set is utilized for network training. The optimal tailoring of trajectories and growing training sets are two innovations that result in a superior training of the recurrent neural network, which in turn delivers a robust word recognition performance tolerating wide variations in the speech signal. 1.
Citations
|
1390
|
Introduction to the theory of neural computation
– Hertz, Krogh, et al.
- 1991
|
|
263
|
Phoneme Recognition Using Time-Delay Neural Networks
– Waibel, Hanazawa, et al.
- 1989
|
|
84
|
R.”An overview of the SPHINX speech recognition system
– Lee, Hon, et al.
- 1990
|
|
12
|
Learning a Trajectory Using Adjoint Functions and Teacher Forcing
– Toomarian, Barhen
- 1992
|
|
6
|
Exponential Stability and a Systematic Synthesis of a Neural Network for Quadratic Minimization
– Sudharsanan, Sundareshan
- 1991
|
|
5
|
Classification of temporal trajectories by continuous-time recurrent nets
– Sotelino, Saerens, et al.
- 1994
|
|
4
|
Equilibrium Characterization of Dynamical Neural Networks and a Systematic Synthesis Procedure for Associative Memories
– Sudharsanan, Sundareshan
- 1991
|
|
3
|
Gradient Calculations for Dynamic Recurrent Networks: A Survey
– Pearlmutter
- 1995
|
|
2
|
Speech Recognition by Dynamic Recurrent Neural Networks
– Hasegawa, Inazumi
|
|
2
|
Towards a unified Design of Pattern Recognizers
– Watanabe, Bien, et al.
- 1996
|
|
1
|
Using the Topology-Preserving Properties of SOFMs
– Torkkola, Kokkonen
- 1991
|
|
1
|
Time-FrequencyEnergy representation based Real-Time Speech Recognition
– Wu, Gowdy
- 1993
|
|
1
|
Speech recognition Using Neural Networks”, Pontificia Universidad Católica de Chile, Engineer Thesis
– Zegers
- 1992
|
|
1
|
A Learning Automaton Approach to trajectory Learning and
– Condarcure, Sundareshan
- 1994
|
|
1
|
Faster Learning for Dynamic Recurrent
– Fang, Sejnowski
- 1990
|
