Using recurrent fuzzy neural networks for predicting word boundaries in a phoneme sequence in persian language

Authors:
Mohammad Reza Feizi Derakhshi;Mohammad Reza Kangavari
Affiliations:
Computer engineering faculty, University of science and technology of Iran, Iran;Computer engineering faculty, University of science and technology of Iran, Iran
Venue:
HCI'07 Proceedings of the 12th international conference on Human-computer interaction: intelligent multimodal interaction environments
Year:
2007

Citing 5
Cited 0

Block-structured recurrent neural networks

Neural Networks
A new fuzzy neural network with fast learning algorithm and guaranteed stability for manufacturing process control

Fuzzy Sets and Systems - Fuzzy systems
Word boundary identification from phoneme sequence constraints in automatic continuous speech recognition

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 1
Identification and control of dynamic systems using recurrent fuzzy neural networks

IEEE Transactions on Fuzzy Systems
Diagonal recurrent neural networks for dynamic systems control

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The word boundary detection has an application in speech processing systems. The problem this paper tries to solve is to separate words of a sequence of phonemes where there is no delimiter between phonemes. In this paper, at first, a recurrent fuzzy neural network (RFNN) together with its relevant structure is proposed and learning algorithm is presented. Next, this RFNN is used to predict word boundaries. Some experiments have already been implemented to determine complete structure of RFNN. Here in this paper, three methods are proposed to encode input phoneme and their performance have been evaluated. Some experiments have been conducted to determine required number of fuzzy rules and then performance of RFNN in predicting word boundaries is tested. Experimental results show an acceptable performance.