Recognizing connected digit strings using neural networks

Authors:
Łukasz Brocki;Danijel Koržinek;Krzysztof Marasek
Affiliations:
Polish-Japanese Institute of Information Technology, Warsaw, Poland;Polish-Japanese Institute of Information Technology, Warsaw, Poland;Polish-Japanese Institute of Information Technology, Warsaw, Poland
Venue:
TSD'06 Proceedings of the 9th international conference on Text, Speech and Dialogue
Year:
2006

Citing 6
Cited 0

A tutorial on hidden Markov models and selected applications in speech recognition

Readings in speech recognition
How to solve it: modern heuristics

How to solve it: modern heuristics
Genetic Algorithms Plus Data Structures Equals Evolution Programs

Genetic Algorithms Plus Data Structures Equals Evolution Programs
2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures

Neural Networks - 2005 Special issue: IJCNN 2005
Long Short-Term Memory

Neural Computation
A learning algorithm for continually running fully recurrent neural networks

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.