论文信息 - Recognizing Connected Digit Strings Using Neural Networks

Recognizing Connected Digit Strings Using Neural Networks

This paper discusses the usage of feed-forward and recurrent Artificial Neural Networks (ANNs) in whole word speech recognition The Long-Short Term Memory (LSTM) network has been trained to do speaker independent recognition of any series of connected digits in polish language, using only the acoustic features extracted from speech It is also shown how to effectively change the analog network output into binary information on recognized words The parametrs of the conversion are fine-tuned using artificial evolution.

Krzysztof Marasek | Lukasz Brocki | Danijel Korzinek

[1] Paul J. Werbos,et al. Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

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

[3] F. Gers,et al. Long short-term memory in recurrent neural networks , 2001 .

[4] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.

[5] Jürgen Schmidhuber,et al. Biologically Plausible Speech Recognition with LSTM Neural Nets , 2004, BioADIT.

[6] Zbigniew Michalewicz,et al. Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[7] Jürgen Schmidhuber,et al. Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[8] Yoshua Bengio,et al. Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[9] Steve Young,et al. The HTK book , 1995 .

[10] Zbigniew Michalewicz,et al. Genetic Algorithms Plus Data Structures Equals Evolution Programs , 1994 .

[11] SchmidhuberJürgen,et al. 2005 Special Issue , 2005 .

[12] Lawrence R. Rabiner,et al. A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[13] Dr. Zbigniew Michalewicz,et al. How to Solve It: Modern Heuristics , 2004 .