Title :
Neural network models for recognition of consonant-vowel (Cn V) utterances
Author :
Gangashetty, Suryakanth V. ; Yegnanarayana, B.
Author_Institution :
Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., Madras, India
Abstract :
In this paper, we present an approach based on neural network models for recognition of utterances of syllable-like units in Indian languages. The distribution capturing ability of an autoassociative neural network model is exploited to perform nonlinear principal component analysis for compressing the size of the feature vector. A constraint satisfaction model is proposed to incorporate the acoustic-phonetic knowledge and to combine the outputs of subnets to arrive at the overall decision on the class of an input utterance
Keywords :
constraint theory; neural nets; principal component analysis; speech recognition; CnV utterance recognition; Indian languages; acoustic-phonetic knowledge; autoassociative neural network model; consonant-vowel utterance recognition; constraint satisfaction model; feature vector compression; input utterance; neural network models; nonlinear PCA; nonlinear principal component analysis; subnet outputs; syllable-like units; Computer science; Feature extraction; Information analysis; Laboratories; Natural languages; Neural networks; Principal component analysis; Speech analysis; Speech recognition; Vectors;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.939594
