AudioDatastore input output error
1 vue (au cours des 30 derniers jours)
Afficher commentaires plus anciens
I am using audio files of unequal length,But for calculation of melSpectrograms i need equal datasamples in each file. I applied the transform function to make files equal. But then its not reading the transflrm files as desired. I am following https://in.mathworks.com/help/wavelet/examples/spoken-digit-recognition-with-wavelet-scattering-and-deep-learning.html example on my data. My code giving error
XTrain = helperspeechSpectrograms(scatds_Train,segmentDuration,frameDuration,hopDuration,numBands);
This scatds_Train is the transformed datastore, which is not readable by the support function there. I have attached this supporting file.
its giving me following error
"Unable to perform assignment because the size of the left side is 40-by-186 and the size of the right side is 40-by-187."
function X = helperspeechSpectrograms(ads,segmentDuration,frameDuration,hopDuration,numBands)
% This function is only for use in the
% "Spoken Digit Recognition with Wavelet Scattering and Deep Learning"
% example. It may change or be removed in a future release.
%
% helperspeechSpectrograms(ads,segmentDuration,frameDuration,hopDuration,numBands)
% computes speech spectrograms for the files in the datastore ads.
% segmentDuration is the total duration of the speech clips (in seconds),
% frameDuration the duration of each spectrogram frame, hopDuration the
% time shift between each spectrogram frame, and numBands the number of
% frequency bands.
disp("Computing speech spectrograms...");
numHops = ceil((segmentDuration - frameDuration)/hopDuration);
numFiles = length(ads.UnderlyingDatastore.Files);
X = zeros([numBands,numHops,1,numFiles],'single');
for i = 1:numFiles
[x,info] = read(ads);
% x = normalizeAndResize(x);
fs = info.SampleRate;
frameLength = round(frameDuration*fs);
hopLength = round(hopDuration*fs);
spec = melSpectrogram(x,fs, ...
'WindowLength',frameLength, ...
'OverlapLength',frameLength - hopLength, ...
'FFTLength',2048, ...
'NumBands',numBands, ...
'FrequencyRange',[50,4000]);
X(:,:,1,i) = spec;
end
disp("...done");
end
%--------------------------------------------------------------------------
1 commentaire
jibrahim
le 4 Juin 2020
krishna,
Put a breakpoint where you assign spec to X(:,:,1,i), and then call read on your transform datastore. I think there is a mismatch in sizes on that line
Réponses (0)
Voir également
Catégories
En savoir plus sur Feature Extraction dans Help Center et File Exchange
Produits
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!