Peak Isolation Algorithm

Started by Sattu in comp.dsp15 years ago 6 replies

One of the good features to recognize the voice gender is the periodicity of residual autocorrelation function. To implement the algorithm, We...

One of the good features to recognize the voice gender is the periodicity of residual autocorrelation function. To implement the algorithm, We calculate the distance between the first and second peak of autocorrelation for each frame , average it all over the nonzero frames and take it as a feature of gender voice. Needless to say, using autocorrelation of residual can be identified as linea...


problem with fft on autocorrelation data

Started by acc in comp.dsp14 years ago 4 replies

Hi all, Thanks for reading and please feel free to comment. I am having problems with matlab fft on autocorrelation data. When performing...

Hi all, Thanks for reading and please feel free to comment. I am having problems with matlab fft on autocorrelation data. When performing a fft on my normalised autocorrelation data i got a imagnary part that is not equal to zero around x=0 and also at the near end of the x-axis, but, in between all points are equal to zero. Imagnary plot that i got looked like below, ...


Good reference for pitch tracking by autocorrelation

Started by Anonymous in comp.dsp16 years ago 2 replies

Hi. Does anyone have a good reference for pitch tracking by autocorrelation? I do note that there is a very long thread on this topic, but it's...

Hi. Does anyone have a good reference for pitch tracking by autocorrelation? I do note that there is a very long thread on this topic, but it's too long to follow. So far I've written a very straightforward program to calculate autocorrelation in a signal and also a crude envelope follower to approximate volume at each pixel. I now want to refine my approach and need a proper reference. What ...


How do I handle harmonics for autocorrelation peaks? Need an algorithm I think.

Started by noodle22 in comp.dsp12 years ago 12 replies

Hi, I am trying to determine the pitch of an audio signal using autocorrelation. My autocorrelation peaks come out quite clearly and after a...

Hi, I am trying to determine the pitch of an audio signal using autocorrelation. My autocorrelation peaks come out quite clearly and after a bit of processing, I have a signal where one of the following is true a) all the peaks are close to the same height as their neighbors b) Every second peak is significantly taller than the previous peak c) Every third peak is significantly taller tha...


When does sampled autocorrelation = autocorrelation of sampled sequence?

Started by Oli Charlesworth in comp.dsp12 years ago 17 replies

Hello, It feels like this will be a standard DSP result that I should be able to dig up, but I'm not sure where to look, so here goes! If...

Hello, It feels like this will be a standard DSP result that I should be able to dig up, but I'm not sure where to look, so here goes! If we have a continuous-time function, h(t) (assuming real and "sufficiently well-behaved" for now), then define the autocorrelation as: r(t) = int { h(tau) h(tau - t) d tau } Let's also define the discrete-time sampled sequence, h[n] = h(nT), whe...


Autocorrelation

Started by OZ in comp.dsp16 years ago 6 replies

Hi, I am using an autocorrelation function to calculate the period of a signal. It is a signal which is periodic. My problem is that there...

Hi, I am using an autocorrelation function to calculate the period of a signal. It is a signal which is periodic. My problem is that there are some parts with big amplitudes and some part with small amplitudes. The disadvantage of the autocorrelation is that the big amplitudes are dominant and that it is very difficult to calculate the period of the signal if there is only 1.5 periods ava...


A question on autocorrelation

Started by Jay in comp.dsp17 years ago 12 replies

Hello group Let X(n) = Y for all n. X(n) is a stochastic process. Y is random variable with uniform distribution in (0,1). ...

Hello group Let X(n) = Y for all n. X(n) is a stochastic process. Y is random variable with uniform distribution in (0,1). The autocorrelation of X, rxx(m) = E{X(n)X(n-m)} = E{Y.Y} = E{Y^2} 1 E{Y^2} = integral y^2 pdf(y) dy = 1/3 0 rxx(m) = 1/3 which is a constant. Matlab N =...


autocorrelation negative values

Started by Thomas Magma in comp.dsp15 years ago 7 replies

Hi, If your data consists of ones and negative ones then you get negative values in your autocorrelation function, but if your data is ones...

Hi, If your data consists of ones and negative ones then you get negative values in your autocorrelation function, but if your data is ones and zeros you don't. In an autocorrelation plot you often see large negative values on either side of your correlation peak. Is this a good thing or bad thing? The reason I ask is because at first glance it appears to be a good thing, however now ...


sample autocorrelation matrix eigenvalues negative

Started by doublehelics in comp.dsp10 years ago 3 replies

Hey all, i am computing sample autocorrelation for some continouous valued data (using...

Hey all, i am computing sample autocorrelation for some continouous valued data (using this: https://ccrma.stanford.edu/~jos/sasp/Sample_Autocorrelation.html) but the generated correlation matrix has negative eigenvalues. Is there a way to fix the autocorrelation matrix to have non-negative eigenvalues? I always thought that the sample correlation matrix should have been positive semidefinite. th...


nonstationary autocorrelation but stationary PSD

Started by fisico32 in comp.dsp11 years ago 3 replies

Hello Forum the nonstationary autocorrelation function R(t1, t2) depends on two variables t1,t2. If t2-t1=tau, then R(t1, t1+tau) It turns...

Hello Forum the nonstationary autocorrelation function R(t1, t2) depends on two variables t1,t2. If t2-t1=tau, then R(t1, t1+tau) It turns out that the power spectral density S(w), for a nonstationary autocorrelation function is equal to: S(w)= FT { }, the Fourier transform of the "long-time average of R(t, t+tau)" is the power spectral density. Why is S(w) not a function of


Autocorrelation matrix with matlab

Started by thom in comp.dsp15 years ago 4 replies

Hi I would like to compute the autocorrelation matrix from a vector with Matlab. I don't have the statistical signal processing toolbox (I can...

Hi I would like to compute the autocorrelation matrix from a vector with Matlab. I don't have the statistical signal processing toolbox (I can only use "cov" and "corrcoef" functions, or build my own function). Could someone explain how I can do? Thanks a lot. Thom


Autocorrelation

Started by angelredrose in comp.dsp13 years ago 1 reply

Hi, I am trying to understand the autocorrelation function for better timing resolution. I am bit confused how to find out the auto correlation...

Hi, I am trying to understand the autocorrelation function for better timing resolution. I am bit confused how to find out the auto correlation PEAK from the output of M-Sequence? and What is the impact of distance between the two peaks? In other words, the impact of the length of the M-Sequence? Thanks,


Matrix equation

Started by Jani Huhtanen in comp.dsp16 years ago 19 replies

Hi! I'm hoping here's someone who can help me with a "hairy" matrix equation. I stumbled upon this developing my lossless audio codec. I have...

Hi! I'm hoping here's someone who can help me with a "hairy" matrix equation. I stumbled upon this developing my lossless audio codec. I have this: e = r^T * (R^-1 - A^T * (A*R*A^T)^-1 * A) * r, where r is 1xk vector (lags 1 to k of autocorrelation), R is kxk matrix (autocorrelation matrix) and it's usually positive definite, A = [I 0]^T of size (k-1)xk, ie. (k-1)x(k-1) identity matrix...


Phase detection using Autocorrelation

Started by Kenny_EE_UTD in comp.dsp15 years ago

As part of a senior design project designing a QAM modem. One major issue that I am trying to tackle is the ideal of tracking the phase of the...

As part of a senior design project designing a QAM modem. One major issue that I am trying to tackle is the ideal of tracking the phase of the incomming signal to the reciever so that the data can be sampled at the appropriate times. I am currently playing with the ideal of using the autocorrelation function. Does anyone have any advice that they could offer to this ideal? Thanks, -K...


Autocorrelation

Started by Ekkehard in comp.dsp15 years ago

Hello, I have just made some tests with the correl function of the "Numerical Recipes"...

Hello, I have just made some tests with the correl function of the "Numerical Recipes" (www.nr.com, http://library.lanl.gov/numerical/bookcpdf/c13-2.pdf). I am interessted in the autocorrelation (== both input sets are equal). When the input (1..8) is 0, 1, 0, 0, 1, 0, 0, 0 The Result is 2, 0, 0, 1, 0, 1, 0, 0 Using the given reordering the result should be interpreted as Source 0 1 ...


Maximum data extraction from autocorrelation

Started by Dirk Bruere at NeoPax in comp.dsp7 years ago 18 replies

So, I have a 1024 data set containing a signal and it's reflection. The signal and reflections are around 10 cycles of sine wave, eye-shaped. I...

So, I have a 1024 data set containing a signal and it's reflection. The signal and reflections are around 10 cycles of sine wave, eye-shaped. I need to find the time between the two. I do autocorrelation and get peaks at zero and the samples where there is maximum correlation. However, this only gives me an accuracy of one sample size - there must be far more information in the data


Pitch Estimation using spectral Autocorrelation method.

Started by Anonymous in comp.dsp7 years ago 6 replies

please help me to find pitch of a speech signal using spectral autocorrelation method. Thank You Regards Girish Babu S

please help me to find pitch of a speech signal using spectral autocorrelation method. Thank You Regards Girish Babu S


Definition of autocorrelation -- it was obvious but not now

Started by Anonymous in comp.dsp12 years ago 2 replies

Hello, Signal Processing Experts, There is something that I have been so used to and does not look so obvious today. On page 98 of...

Hello, Signal Processing Experts, There is something that I have been so used to and does not look so obvious today. On page 98 of Communication Systems Engineering by Proakis (1st edition), it defines the autocorrelation function as the convolution between the signal itself and time reversed version of its complex conjugate: Rx(tau) = x(tau) convolve x*(-tau) ...


Basic Power Spectral Density question

Started by sergio in comp.dsp16 years ago 1 reply

Hi, I'm looking for a more fundamental answer here. I'm starting to learn about PSD and autocorrelation etc., and while time domain makes...

Hi, I'm looking for a more fundamental answer here. I'm starting to learn about PSD and autocorrelation etc., and while time domain makes sense to me, I have trouble imagining what Fourier tranform does to the autocorrelation function except tranforming it the frequency domain. Or put differently, if PSD shows how is the power (mean square value) spreads through different frequencies, the...


Help with pitch extraction

Started by bouyang in comp.dsp16 years ago 1 reply

I have looked at some literature on using autocorrelation or AMDF for picth detection/extraction. If I understand correctly, all these methods...

I have looked at some literature on using autocorrelation or AMDF for picth detection/extraction. If I understand correctly, all these methods have two parts -- first construct the functional that can be used to extrac the period/pitch (AMDF, autocorrelation etc.), second, find peak/null and the associated lag index to obtain the pitch. What I need help is how the extraction part is general...