MATLAB: Audio sample path no valid

audio signal

function kNN_model_add_class(modelName, className, classPath, ...
    listOfStatistics, stWin, stStep, mtWin, mtStep)
%



% function kNN_model_add_class(modelName, className, classPath, ...
%         listOfStatistics, stWin, stStep, mtWin, mtStep)
%
% This function adds an audio class to the kNN classification model
% 
% ARGUMENTS;
% - modelName:  the filename of the model (mat file)
% - className:  the name of the audio class to be added to the model
% - classPath:  the path of the directory where the audio segments of the
%               new class are stored
% - listOfStatistics:   list of mid-term statistics (cell array)
% - stWin, stStep:      short-term window size and step
% - mtWin, mtStep:      mid-term window size and step
%
% Example:
% kNN_model_add_class('modelSpeech.mat', 'speech', './Music/', ...
%  {'mean','std',}, 0.050, 0.025, 2.0, 1.0);
%
if ~exist(classPath,'dir')
    error('Audio sample path is not valid!');
else
    classPath = [classPath filesep];
end
% check if the model elaready exists:
fp = fopen(modelName, 'r');
if fp>0 % check if file already exists
    load(modelName);
end
% Feature extraction:
D = dir([classPath '*.wav']);
F = [];
for (i=1:length(D)) % for each wav file in the given path:
    curFileName = [classPath D(i).name];
    FileNamesTemp{i} = curFileName;
    % mid-term feature extraction for each wav file:
    midFeatures = featureExtractionFile(curFileName, ...
        stWin, stStep, mtWin, mtStep, listOfStatistics);
    % long-term averaging:
    longFeatures = mean(midFeatures,2);       
    
    F = [F longFeatures];
end
% save the model:
Statistics = listOfStatistics;
fp = fopen(modelName, 'r');
if fp<0 % model does not exist --> generate     
    ClassNames{1} = className;
    Features{1} = F;   
    FileNames{1} = FileNamesTemp;
    save(modelName, 'ClassNames', 'Features', ...
        'Statistics', 'stWin', 'stStep', 'mtWin', 'mtStep', 'FileNames');
else
    load(modelName);
    ClassNames{end+1} = className;
    Features{end+1} = F;
    FileNames{end+1} = FileNamesTemp;
    save(modelName, 'ClassNames', 'Features', ...
        'Statistics', 'stWin', 'stStep', 'mtWin', 'mtStep', 'FileNames');
end
I have this function and when i try to call it with command
strDir = 'C:\Users\User\Desktop\3rd year\bachelor thesis\cats_dogs\train';
Statistics = {'mean', 'median', 'std', 'stdbymean', 'max', 'min'};
stWin = 0.040;
stStep = 0.040;
mtWin = 2;
mtStep = 1;
kNN_model_add_class('model8.mat', 'dog', [strDir '.dog/'], ...
    Statistics, stWin, stStep, mtWin, mtStep);
It gives me an error… probably a path of srtDir is incorrectly written. Can you please help me.
Example of a code call would be great

Best Answer
Now I get this error I am assuming i need to pass a struct to the function featureExtractionFile but I dont know how
so it can go throught every audio in directory.
Example of call would be appreciative
function [midFeatures, Centers, stFeaturesPerSegment] = ...
    featureExtractionFile(signal, stWin, stStep, mtWin, mtStep, featureStatistics)
% function [midFeatures, Centers, stFeaturesPerSegment] = ...
%    featureExtractionFile(fileName, stWin, stStep, mtWin, mtStep, ...
%    featureStatistics)
%




% [mtFeatures, centers] = featureExtractionFile(fileName,  ...
%    0.040, 0.040, 2.0, 1.0, {'mean','std'});
%
% This function reads a struct element and computes 
% audio feature statitstics on a mid-term basis.
%
% ARGUMENTS:
% - signal:             audio signal (struct)
% - stWin:              short-term window size (in seconds)
% - stStep:             short-term window step (in seconds)
% - mtWin:              mid-term window size (in seconds)
% - mtStep:             mid-term window step (in seconds)
% - featureStatistics:  list of statistics to be computed (cell array)
%
% RETURNS
% - midFeatures         [numOfFeatures x numOfMidTermWins] matrix 
%                       (each collumn represents a mid-term feature vector)
% - Centers:            representive centers for each 
%                       mid-term window (in seconds)
% - stFeaturesPerSegment cell that contains short-term feature sequences
%
% (c) 2014 T. Giannakopoulos, A. Pikrakis
% convert mt win and step to ratio (compared to the short-term):
mtWinRatio  = round(mtWin  / stStep);
mtStepRatio = round(mtStep / stStep);
readBlockSize = 60; % one minute block size:
% get the length of the audio signal to be analyzed:
% ndret til struct brug!

a = signal.Filt_data;
fs = signal.SampleRate;
numOfSamples = length(a);
BLOCK_SIZE = round(readBlockSize * fs); % Antal samples per minut
curSample = 1;
count = 0;
midFeatures = [];
Centers = [];
stFeaturesPerSegment = {};
while (curSample <= numOfSamples) % while the end of file has not been reahed
    % find limits of current block:
    N1 = curSample;
    N2 = curSample + BLOCK_SIZE - 1;
    if (N2>numOfSamples)
        N2 = numOfSamples;
    end
    
    tempX = signal.Filt_data(N1:N2,:);    % ndret til struct brug!
    % STEP 1: short-term feature extraction:
    Features = stFeatureExtraction(tempX, fs, stWin, stStep);
       
    % STEP 2: mid-term feature extraction:
    [mtFeatures, st] = mtFeatureExtraction(...
        Features, mtWinRatio, mtStepRatio, featureStatistics);
    
    for (i=1:length(st)) 
        stFeaturesPerSegment{end+1} = st{i}; 
    end
    Centers = [Centers readBlockSize * count + (0:mtStep:(N2-N1)/fs)];
    midFeatures = [midFeatures mtFeatures];
    
    % update counter:
    curSample = curSample + BLOCK_SIZE;
    count = count + 1;    
end
if (length(Centers)==1)
    Centers = (numOfSamples / fs) / 2;
else
    C1 = Centers(1:end-1);
    C2 = Centers(2:end);
    Centers = (C1+C2) / 2;
end
if (size(midFeatures,2)>length(Centers))
    midFeatures = midFeatures(:, 1:length(Centers));
end
if (size(midFeatures,2)<length(Centers))
    Centers = Centers(:, 1:size(midFeatures,2));
end
Related Question