1977
DOI: 10.1109/tassp.1977.1162944
|View full text |Cite
|
Sign up to set email alerts
|

A fixed point computation of partial correlation coefficients

Abstract: This paper introduces a new computational algorithm for the partial correlation coecients of a linear system given the covariance of its output when excited by a white input noise. Although derived from Levinson's well-known procedure, the proposed algorithm does not make use of the usual parameters in the linear prediction recursion. It may be implemented using xed point arithmetics. Application to speech waves is emphasized. 1

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
9
0
2

Year Published

1985
1985
2013
2013

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 126 publications
(11 citation statements)
references
References 5 publications
0
9
0
2
Order By: Relevance
“…An alternate method -Leroux Gueguen Algorithm (LGA) eliminates the problem related to dynamic range in a fixed-point environment by taking the application of Schwartz inequality in computation of this method [13]. This technique also reduces the computational time by avoiding the larger matrix inversion as in Normal Equation (9).…”
Section: Modified Leroux Gueguen Techniquementioning
confidence: 99%
“…An alternate method -Leroux Gueguen Algorithm (LGA) eliminates the problem related to dynamic range in a fixed-point environment by taking the application of Schwartz inequality in computation of this method [13]. This technique also reduces the computational time by avoiding the larger matrix inversion as in Normal Equation (9).…”
Section: Modified Leroux Gueguen Techniquementioning
confidence: 99%
“…The first fast Toeplitz solver of this type was proposed by Bareiss [2]. Later on, closely related algorithms were presented in [27,29,31]. Today, Toeplitz solvers based on (1.4) are usually referred to as Schur-type algorithms because of their intimate connection [1,25] with Schur's seminal work [32].…”
Section: Classical Fast Toeplitz Solversmentioning
confidence: 99%
“…The reflection (PARCOR) coefficients {kk } are computed from the set of normalized autocorrelation coefficients {rk} via the Le Roux-Gueguen algorithm suitable for a fixed point implementation (Le Roux and Gueguen 1977). The set of autoregressive (prediction) coefficients {ak } is evaluated iteratively using the recursion formula based on the well-known Levinson-Durbin's algorithm (Makhoul 1975):…”
Section: Processing Strategymentioning
confidence: 99%