White Papers

Diagnostics of Speech Recognition: On Evaluating Feature Set Performance

Overview This paper presents an explorative study of diagnostics of speech recognition for finding subsets of features that are most informative in terms of incorrect speech recognition, if variable speech is recognized. The impact on both MFCC and PLP features is investigated. Standard HMMGMM phoneme-based ASR system with no grammar is used for collection of the all the correct and wrong decodings, and decision tree analysis is used with questions about variance of feature coefficients in the tree nodes. The paper presents various results on importance of quefrency regions in terms of intrinsic speech variabilities, and contributes to better understanding of efficiency of used front-end.

Download White Paper

By downloading you agree to our Terms and Conditions. These include information regarding use of your personal data.

Publisher
Slovak Academy of Sciences
File Format
PDF
Date Published
Dec 13, 2008
Format
White Papers
Topics
Voice Recognition, Diagnostics and Analysis