Title :
A Novel Visual Feature Extraction and Its Application in Vowel Recognition
Author :
Sadeghi, Vahideh Sadat ; Yaghmaie, Khashayar
Author_Institution :
Univ. of Semnan, Semnan
Abstract :
Speech recognition techniques have been developed dramatically in recent years. Nevertheless, errors caused by environmental noise are still a serious problem in recognition. Employing algorithms to detect and follow the motion of lips have been widely used to improve the performance of speech recognition algorithms. This paper presents a novel technique to recognize vowels. Lip features extracted by using a combined method are used as input parameters to a neural network system for recognition. Accuracy of the proposed method is verified by using it to recognize 6 main Farsi vowels.
Keywords :
feature extraction; image motion analysis; image recognition; neural nets; speech recognition; Farsi vowels; environmental noise; lip feature extraction; lips motion; neural network system; speech recognition algorithms; speech recognition techniques; visual feature extraction; vowel recognition; Clustering algorithms; Feature extraction; Lips; Mouth; Neural networks; Partitioning algorithms; Pixel; Speech recognition; Tracking; Voting;
Conference_Titel :
Data Engineering Workshop, 2007 IEEE 23rd International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-0832-0
Electronic_ISBN :
978-1-4244-0832-0
DOI :
10.1109/ICDEW.2007.4401091
