This preview shows pages 1–2. Sign up to view the full content.
UCLA
Dept. of Electrical Engineering
EE 114, Winter 2009
Computer Assignment 4: Linear Predictive Analysis
Introduction
: This assignment explores the role of linear prediction in spectral analysis of
speech. Speciﬁcally, this assignment focusses on the eﬀect of prediction order on resulting spectral
approximations.
Linear Prediction Order
:
Load the necessary speech data into your workspace by typing:
load
in;
at the prompt. Analyze the male /a/ segment using the ”zpﬀt” script:
zpﬀt(male
a);
Questions
:
1. Does the spectral analysis provided by the ”zpﬀt” script correspond to narrowband or wide
band analysis?
2. Approximate the spectral locations of the ﬁrst 3 formant frequencies.
MATLAB provides a function ”lpc” which, given a signal
x
and predictive order
P
, will output
the coeﬃcients of the inverse ﬁlter
A
(
z
):
a=lpc(x,P);
Recall that this is the same expression,
A
(
z
), that is used to approximate the spectrum during
linear predictive analysis:
H
(
z
) =
G
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview. Sign up
to
access the rest of the document.
This note was uploaded on 05/10/2010 for the course EE EE114 taught by Professor Vanderschaar during the Spring '09 term at UCLA.
 Spring '09
 VANDERSCHAAR
 Electrical Engineering

Click to edit the document details