Avtor/Urednik		Štrancar, Andrej; Rozman, Robert; Kodek, Dušan M
Naslov		Razpoznavanje govora z nevronskimi mrežami
Prevedeni naslov		Automatic speech recognition using neural networks
Tip		članek
Vir		In: Zajc B, editor. Zbornik 9. elektrotehniške in računalniške konference ERK 2000. Zvezek B. Računalništvo in informatika, umetna inteligenca, robotika, razpoznavanje vzorcev, biomedicinska tehnika, močnostna elektrotehnika, didaktika, študentski članki; 2000 sep 21-23; Portorož. Ljubljana: Slovenska sekcija IEEE,
Leto izdaje		1999
Obseg		str. 173-6
Jezik		slo
Abstrakt		In this paper we present a neural network based speech recognition system. The system allows several types of neural networks to be used as a class probability estimator. The system is built with two toolkits. Speech parametrisation and Viterbi search are done in CSLU toolkit, building training and frame level testing of neural networks are done using NICO toolkit. The focus of this paper is on using neural networks with delayed connections, TDNNs (Time Delay Neural Networks) and RTDNNs (Recurrent TDNN) in speech recognition systems. Both types of networks are known to be very successful at phoneme recognition. We performed an experiment that compares these types of networks with MLPs (Multi Laver Perceptron), which are used in most systems. in the same recognition system we integrated MLPs, TDNNs and RTDNNs with various number of neurons and evaluated the results on our Slovenian digits corpora. Initially TDNNS were slightly less successful than MLPs, but after the recurrent connections in hidden layer of TDNNs were added the, resulting networks performed significantly better than MLPs.
Deskriptorji		SPEECH ACOUSTICS PATTERN RECOGNITION NEURAL NETWORKS (COMPUTER) PHONETICS