Pakistan Science Abstracts
Choose Theme
1
2
3
4
Theme 1
— Green & Gold
Print
Save as PDF
Export BibTeX
Close
No Detail Found!
Home
›
Information technology Journal
Evaluating words of discriminative power in automatic speech recognition system.
Author(s)
V. Meenakshi
SRM Arts and Science College, No. 8/4, NH-1 Cheran Street Maraimalainagar, Kancheepuram, India
V. Shanthi
St. Joseph’s Engineering College, Chennai, India
Abstract
Confidence measures enable us to assess the output of a speech recognition system. The confidence measure provides us with an estimate of the probability that a word in the recognizer output is either correct or incorrect. A confidence measure is a quantitative estimate of a word’s correctness. There are several approaches that incorporates one or two earlier methods to quantify the performance of confidence measures. It can be applied to improve recognition by incorporating extra information into the recognition process or weighting hypothesized words. It can also be used for predicting recognition accuracy and detection of recognizer failure. This study presents an approach that incorporates confidence measures based on both acoustic model and language model for measuring the word-based recognition reliability.
Publication Details
Page(s)
909-913
DOI
DOI not available
Published
Journal: Information technology Journal, Volume: 6, Issue: 6, Year: 2007
Request the full text from PASTIC
More from
Information technology Journal
Internet based multimedia services and technologies in the context of e-government: A conceptual framework.
Extracting 2D projection contour from 3D model using ring-relationship-based method.
Block overlapped intensity-pair distribution approach for image contrast enhancement.
On-line monitoring of hydropower plants in Pakistan.
Distributed localization based on hessian local linear embedding algorithm in wireless sensor networks.
0
Citations
0
Downloads
61
Views