Title :
Least squares method for accurate speech analysis
Author :
Shimamura, Tetsuya
Author_Institution :
Dept. of Inf. & Comput. Sci., Saitama Univ., Japan
fDate :
23 Feb.-1 March 2003
Abstract :
This paper proposes a strategy to improve the performance of the linear prediction method used for speech analysis. The least squares (LS) method, one of system identification methods, is utilized to estimate the coefficients of the all-pole filter and the gain parameter. For the input estimation, a simple and effective method is proposed in which the operation of thresholding is used. It is revealed that the LS method provides a good performance independently on the pitch period of speech.
Keywords :
filtering theory; identification; least squares approximations; speech processing; all-pole filter coefficients; gain parameter; input estimation; least squares method; linear prediction method; pitch period; speech analysis; system identification methods; thresholding; Digital filters; Frequency estimation; Least squares approximation; Least squares methods; Prediction methods; Robustness; Speech analysis; Speech processing; System identification; Transfer functions;
Conference_Titel :
Telecommunications, 2003. ICT 2003. 10th International Conference on
Print_ISBN :
0-7803-7661-7
DOI :
10.1109/ICTEL.2003.1191492
