Performance Evaluation of Loss Functions for Margin Based Robust Speech Recognition
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 2
Abstract
Margin-based model estimation methods are applied for speech recognition to enhance the generalization capability of acoustic model by increasing the margin. An important aspects of margin based acoustic model for parameter estimation is that, the acoustic models are derived from soft margin concept and hinge loss function used in SVM as loss function to attained enhanced speech recognition performance. In this study, performance evaluation of loss functions (Logistic, Savage, Sigmoid) have been computed in the presence of white noise, pink noise, and brown noise with and without SVM classifiers to analyze the impact of noise on loss functions in comparison with hinge loss function used in SVM for parameter estimation in margin based acoustic model. Experimental results show that hinge loss function in the presence of pink noise and white noise have significant effects on isolated digits (0-9) in both pre-conditioned and recorded data samples in comparison with brown noise. Whereas hinge loss functions show serious anomalies with savage loss and sigmoid loss in term of performance and sigmoid loss function provides exceptionally good results in term of percentage error for all prescribed conditions.
Authors and Affiliations
Syed Ali, Maria Andleeb, Raheela Asif, Danish-ur-Rehman
Keywords
Related Articles
- EP ID EP159283
- DOI 10.14569/IJACSA.2016.070249
- Views 112
- Downloads 0
Predicting Fork Visibility Performance on Programming Language Interoperability in Open Source Projects
Despite a variety of programming languages adopted in open source (OS) projects, fork variation on some languages has been minimal and slow to be adopted, and there is little research as to why this is so. We therefore e...
On the Sampling and the Performance Comparison of Controlled LTI Systems
In this paper, the impact of the discretization techniques and the sampling time, on the finite-time stabilization of sampled-data controlled Linear Time Invariant (LTI) systems, is investigated. To stabilize the process...
Zynq FPGA based and Optimized Design of Points of Interest Detection and Tracking in Moving Images for Mobility System
In this paper, an FPGA based mobile feature detection and tracking solution is proposed for complex video processing systems. Presented algorithms include feature (corner) detection and robust memory allocation solution...
Applying Social Network Analysis to Analyze a Web-Based Community
This paper deals with a very renowned website (that is Book-Crossing) from two angles: The first angle focuses on the direct relations between users and books. Many things can be inferred from this part of analysis such...
A Linear Array for Short Range Radio Location and Application Systems
Patch array antennas have primarily been good candidates for higher performance results in communication systems. This paper comprises of linear 1x4 patch antenna array study constructed on 1.575mm thick Roggers 5880 sub...