DocumentCode :
966725
Title :
Regularized Linear Prediction of Speech
Author :
Ekman, Anders L. ; Kleijn, Bastiaan W. ; Murthi, Manohar N.
Author_Institution :
KTH (R. Inst. of Technol.), Stockholm
Volume :
16
Issue :
1
fYear :
2008
Firstpage :
65
Lastpage :
73
Abstract :
All-pole spectral envelope estimates based on linear prediction (LP) for speech signals often exhibit unnaturally sharp peaks, especially for high-pitch speakers. In this paper, regularization is used to penalize rapid changes in the spectral envelope, which improves the spectral envelope estimate. Based on extensive experimental evidence, we conclude that regularized linear prediction outperforms bandwidth-expanded linear prediction. The regularization approach gives lower spectral distortion on average, and fewer outliers, while maintaining a very low computational complexity.
Keywords :
prediction theory; spectral analysis; speech processing; all-pole spectral envelope estimation; regularized linear prediction; speech signal; Autocorrelation; Bandwidth; Computational complexity; Contamination; Frequency; Predictive models; Research and development; Sampling methods; Speaker recognition; Speech coding; Bandwidth expansion; envelope estimation; linear prediction (LP); regularization;
fLanguage :
English
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1558-7916
Type :
jour
DOI :
10.1109/TASL.2007.909448
Filename :
4378273
Link To Document :
بازگشت