Title :
Two neural network paradigms of phoneme transcription - a comparison
Author :
Kristensen, Terje
Author_Institution :
Dept. of Comput. Eng., Bergen Univ. Coll., Norway
Abstract :
In this work a multi layer perceptron (MLP) and a counterpropagation (CP) network for transcription of Norwegian text is presented. Both paradigms are described and compared. The corpus consists of about 50,000 Norwegian words and their transcriptions, developed by the Norwegian Telecom Research Centre. The transcription scheme used is Sampa for Norwegian. The performance for each network has been tested on about 10,000 unknown Norwegian words.
Keywords :
backpropagation; character recognition; multilayer perceptrons; neural nets; speech recognition; Norwegian text; counterpropagation networks; multi layer perceptron; neural network; phoneme transcription; Artificial neural networks; Automatic speech recognition; Computer networks; Educational institutions; Electronic mail; Hidden Markov models; Neural networks; Speech synthesis; Telecommunications; Testing;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Conference_Location :
Budapest
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1381165
