ISOLATED WORD RECOGNITION

Publication Date : 29/02/2016


Author(s) :

JULNA NAZER , SAJEER K.

Volume/Issue :
Volume 2
,
Issue 2
(02 - 2016)

Abstract :

Isolated word recognition is a technical process that allows translation of spoken words into a readable text format. The objective of this work is to explore how the neural networks are used to recognize individual words in a speech. These general techniques can be developed further extended to other applications. Back-propagation neural network algorithm make use of input training samples and their respective desired output values to learn and recognize specific patterns, by modifying the activation values of its nodes and weights of the links connecting its nodes. Such a trained network is later used for feature recognition in automatic speech recognition systems. System is trained with same words with different dialects in order to identify the words that are spoken with different accents. Index Terms— word recognizer, dialects, accent, neural network architecture, back propagation algorithm

No. of Downloads :

5