KL: A Neural Model for Capturing Structure in Speech

In this paper we propose a neural model conceived for problems of word recognition and understanding of small protocol-driven sentences. The model is based on an unified approach to integrate priori knowledge and learning by example. The priori knowledge, injected into the network connections, can be of different levels, while learning is mainly conceived as a refinement process, and is responsible of dealing with uncertainty. We describe a small prototype for problems of isolated word recognition.

[1]  Barak A. Pearlmutter.  Learning state space trajectories in recurrent neural networks : a preliminary report. , 1988 .

[2]  Pietro Laface,et al.  On the use of neural networks for speaker independent isolated word recognition , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[3]  Alberto Tesi,et al.  On the Problem of Local Minima in Backpropagation , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Giovanni Soda,et al.  Local Feedback Multilayered Networks , 1992, Neural Computation.

[5]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[6]  Barak A. Pearlmutter.  Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[7]  Giovanni Soda,et al.  An unified approach for integrating explicit knowledge and learning by example in recurrent networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[8]  J. Stephen Judd,et al.  On the complexity of loading shallow neural networks , 1988, J. Complex..

[9]  B. R. Kammerer,et al.  Design of hierarchical perceptron structures and their application to the task of isolated-word recognition , 1989, International 1989 Joint Conference on Neural Networks.

[10]  Lokendra Shastri,et al.  Speech recognition using connectionist networks , 1988 .

[11]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..