Paper Info
Title
Speech Enhancement Using Gain Function of Noisy Power Estimates and Linear Regression
Abstract
Speech enhancement algorithm is proposed based on calculating the ratio of the average noisy power spectrum in time-frequency bins to the normalized time-frequency average. If the ratio is greater than the linear regression estimator threshold, speech is considered to be present. The algorithm has the advantage of being computationally simple and it produces significantly less residual noise. We evaluated the algorithm under various noise conditions to demonstrate its general superiority to conventional methods.
Year
DOI
Venue
2007
10.1109/FBIT.2007.163
FBIT
Keywords
Field
DocType
conventional method,various noise condition,linear regression estimator threshold,average noisy power spectrum,normalized time-frequency average,speech enhancement,linear regression,gain function,residual noise,general superiority,noisy power estimates,time-frequency bin,speech enhancement algorithm,noise,time frequency,power spectrum,regression analysis
Speech enhancement,Normalization (statistics),Regression analysis,Speech enhancement algorithm,Speech recognition,Gain function,Spectral density,Mathematics,Estimator,Linear regression
Conference
Citations 
PageRank 
References 
0
0.34
4
Authors
2
Name
Order
Citations
PageRank
Soojeong Lee1515.93
Soon-Hyob Kim212.07