Abstract
Inthischapter,we are going to derive the most useful performance measures for speech enhancement in the general framework where any function f( ) can be used. We can divide these performance measures into two categories. The first category evaluates the noise reduction performance while the second one evaluates speech distortion. We also discuss the very convenient mean-square error (MSE) criterion and show how it is related to the performance measures.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Benesty, J., Huang, Y. (2011). Performance Measures. In: A Perspective on Single-Channel Frequency-Domain Speech Enhancement. Synthesis Lectures on Speech and Audio Processing. Springer, Cham. https://doi.org/10.1007/978-3-031-02561-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-02561-7_3
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-01433-8
Online ISBN: 978-3-031-02561-7
eBook Packages: Synthesis Collection of Technology (R0)eBColl Synthesis Collection 3