function [predictor,response,segmentsPerFile] = vggishPreprocess(ads,overlap)
% This function is for example purposes only and may be changed or removed
% in a future release.

% Create filter bank
FFTLength = 512;
numBands = 64;
fs0 = 16e3;
filterBank = designAuditoryFilterBank(fs0, ...
    'FrequencyScale','mel', ...
    'FFTLength',FFTLength, ...
    'FrequencyRange',[125 7500], ...
    'NumBands',numBands, ...
    'Normalization','none', ...
    'FilterBankDesignDomain','warped');

% Define STFT parameters
windowLength = 0.025 * fs0;
hopLength = 0.01 * fs0;
win = hann(windowLength,'periodic');

% Define spectrogram segmentation parameters
segmentDuration = 0.96; % seconds
segmentRate = 100; % hertz
segmentLength = segmentDuration*segmentRate; % Number of spectrums per auditory spectrograms
segmentHopDuration = (100-overlap) * segmentDuration / 100; % Duration (s) advanced between auditory spectrograms
segmentHopLength = round(segmentHopDuration * segmentRate); % Number of spectrums advanced between auditory spectrograms

% Preallocate cell arrays for the predictors and responses
numFiles = numel(ads.Files)
predictor = cell(numFiles,1);
response = predictor;
segmentsPerFile = zeros(numFiles,1);

% Extract predictors and responses for each file
for ii = 1:numFiles
     try
        [audioIn,info] = read(ads);

        [m, n] = size(audioIn); %gives dimensions of array where n is the number of stereo channels
if n == 2
            audioIny = audioIn(:, 1) + audioIn(:, 2); %sum(y, 2) also accomplishes this
            peakAmp = max(abs(audioIny)); 
            audioIny = audioIny/peakAmp;
             %  check the L/R channels for orig. peak Amplitudes
             peakL = max(abs(audioIn(:, 1)));
             peakR = max(abs(audioIn(:, 2))); 
             maxPeak = max([peakL peakR]);
             %apply x's original peak amplitude to the normalized mono mixdown 
             audioIny = audioIny*maxPeak;
        else
          audioIny = audioIn; %it is stereo so we will return it as is (e.g., for additional processing)
        end

        audioIn=audioIny;
        x = single(resample(audioIn,fs0,info.SampleRate));

        Y = stft(x, ...
            'Window',win, ...
            'OverlapLength',windowLength-hopLength, ...
            'FFTLength',FFTLength, ...
            'FrequencyRange','onesided');
        Y = abs(Y);


    %       filterBankMultiplicationL=filterBank*Y(:,:,1);
    %       filterBankMultiplicationR=filterBank*Y(:,:,2);
    %       filterBankMultiplication(:,:,1)=filterBankMultiplicationL;
    %       filterBankMultiplication(:,:,2)=filterBankMultiplicationR;
    %       logMelSpectrogram = log(filterBankMultiplication + single(0.01));
    %       logMelSpectrogram =permute(logMelSpectrogram, [2 1 3]);
         logMelSpectrogram = log(filterBank*Y + single(0.01))';
        % Segment log-mel spectrogram
        numHops = floor((size(Y,2)-segmentLength)/segmentHopLength) + 1;
        segmentedLogMelSpectrogram = zeros(segmentLength,numBands,1,numHops);
        for hop = 1:numHops
            segmentedLogMelSpectrogram(:,:,1,hop) = logMelSpectrogram(1+segmentHopLength*(hop-1):segmentLength+segmentHopLength*(hop-1),:);
        end
        predictor{ii} = segmentedLogMelSpectrogram;
        response{ii} = repelem(info.Label,numHops);
        segmentsPerFile(ii) = numHops;
    catch
        fprintf('loop number %d failed\n',ii)
    end
    
end

% Concatenate predictors and responses into arrays
predictor = cat(4,predictor{:});
response = cat(2,response{:});

end