How to generate audio from colored MFCC in the form of image?
6 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
Shilpa Sonawane
il 9 Mag 2023
Commentato: Shilpa Sonawane
il 15 Mag 2023
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1378999/image.png)
In above fig, 41 images are tiled. Each image is generated mfcc. Its size is 28x28x3. It is rgb image. I have to find inverse of mfcc to generate sound. I have used inverse mfcc function from mathworks website. but it is applicable to 2-D matrix of mfcc. It can not be used with rgb image. I am unable to find audio signal from coloured mfcc.
please provide guidance.
0 Commenti
Risposta accettata
Sarthak
il 15 Mag 2023
Hi Shilpa,
MFCC goes through multiple computations like STFT, Mel Projection, etc. Assuming you are mentioning the invMFCC function available on FileExchange, it should reverse all such computations and introduce necessary approximations. If it is only applicable for double 2-D matrices, you can use the im2double function. However, if the function doesnt behave as expected, you may need to write your own inverse functions for MFCC or leverage other third-party libraries.
Attaching links to the mentioned functions for your reference
Più risposte (1)
Brian Hemmat
il 15 Mag 2023
Modificato: Brian Hemmat
il 15 Mag 2023
Inverting MFCC will require knowledge of the algorithm and parameters used to extract the MFCC. Note that perfectly reconstructing the audio is by definition impossible since you are discarding a lot of information during the feature extraction. It's just an interesting toy to understand what information is actually preserved in MFCC.
Here is an example of extracting MFCC using Audio Toolbox functionality and then attempting to reconstruct.
[audioIn,fs] = audioread("Counting-16-44p1-mono-15secs.wav");
audioIn = resample(audioIn,16e3,fs);
fs = 16e3;
audioIn = audioIn./max(abs(audioIn));
%% Extract MFCC
% This is roughly equivalent to how audioFeatureExtractor works with
% default settings.
win = hann(round(fs*0.025),"periodic");
overlap = round(fs*0.01);
fftlength = 2048;
numBands = 40;
% Design auditory filter bank.
filterBank = designAuditoryFilterBank(fs, ...
FrequencyScale="mel", ...
NumBands=numBands, ...
FFTLength=fftlength, ...
FrequencyRange=[0,4000], ...
Normalization="none");
% Compute STFT of speech signal.
X = stft(audioIn, ...
Window=win, ...
OverlapLength=overlap, ...
FFTLength=fftlength, ...
FrequencyRange="onesided");
% Compute Mel auditory spectrogram
B = filterBank*abs(X);
% Compute cepstral coefficients
coeffs = cepstralCoefficients(B);
%% Visualize MFCC
figure
imh = imagesc(normalize(coeffs'));
ylabel('Coefficient')
xlabel('Frame')
set(imh.Parent,YDir="normal")
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1384099/image.png)
%% Inverse MFCC
% Inverse Cepstral Coefficients
B_reconstruct = 10.^(idct(coeffs',size(filterBank,1),Type=2));
% Inverse Mel Spectrum
% Scale the band per time step energy.
B_reconstruct = permute(B_reconstruct,[1,3,2]);
bands = filterBank.*B_reconstruct;
% Sum the bands at each time step so that you have a single spectrum per
% time step.
X = squeeze(sum(bands,1));
% Reconstruct signal from magnitude spectrum
audioOut = stftmag2sig(X,fftlength,fs,FrequencyRange="onesided", ...
OverlapLength=overlap,Window=win,Method='fgla');
% Clean up the edges
audioOut([1:numel(win),end-numel(win):end]) = 0;
audioOut = audioOut./max(abs(audioOut));
%% Listen to and plot the reconstruction
soundsc(audioIn,fs),pause(size(audioIn,1)/fs+1)
soundsc(audioOut,fs)
figure
tiledlayout(3,1)
nexttile
plot(audioIn,'bo'),hold on
plot(audioOut,'r*'),hold off
legend("Original","Reconstruction")
nexttile
stft(audioIn,fs,Window=win,OverlapLength=overlap,FrequencyRange="onesided")
title("Original audio")
nexttile
stft(audioOut,fs,Window=win,OverlapLength=overlap,FrequencyRange="onesided")
title("Reconstructed audio")
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1384104/image.png)
Vedere anche
Categorie
Scopri di più su Audio and Video Data in Help Center e File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!