我希望创建一个Octave程序,加载音频文件(wav,flac),计算其mfcc特征并将其作为输出提供。问题在于我没有太多的Octave经验,无法让Octave加载音频文件,因此我不确定提取算法是否正确。有没有简单的方法来加载文件并获取其特征?
error: 'mp3read' undefined near line 9 column 11
命令为:
[d,sr] = mp3read('a.mp3',[1 30*22050],1,2);
- nstanchev function frame = create_frames(y, Fs, Fsize, Fstep)
N = length(y);
% divide the signal into frames with overlap = framestep
samplesPerFrame = floor(Fs*Fsize);
samplesPerFramestep = floor(Fs*Fstep);
i = 1;
frame = [];
while(i <= N-samplesPerFrame)
frame = [frame y(i:(i+samplesPerFrame-1))];
i = i+samplesPerFramestep;
endwhile
return
endfunction
function ans = hz2mel(f)
ans = 1125*log(1+f/700);
return
endfunction
function ans = mel2hz(f)
ans = 700*(exp(f/1125) - 1);
return
endfunction
function bank = melbank(n, min, max, sr)
% n = number of banks
% min = min frequency in hertz
% max = max frequency in hertz
% convert the min and max freq in mel scale
NFFT = 512;
% figure out bin value of min and max freq
minBin = floor((NFFT)*min/(sr/2));
maxBin = floor((NFFT)*max/(sr/2));
% convert the min, max in mel scale
min_mel = hz2mel(min);
max_mel = hz2mel(max);
m = [min_mel:(max_mel-min_mel)/(n+2-1):max_mel];
%disp(m);
h = mel2hz(m);
% replace frequencies in h with thier respective bin values
fbin = floor((NFFT)*h/(sr/2));
%disp(h);
% create triangular melfilter vectors
H = zeros(NFFT,n);
for vect = 2:n+1
for k = minBin:maxBin
if k >= fbin(vect-1) && k <= fbin(vect)
H(k,vect) = (k-fbin(vect-1))/(fbin(vect)-fbin(vect-1));
elseif k >= fbin(vect) && k <= fbin(vect+1)
H(k,vect) = (fbin(vect+1) - k)/(fbin(vect+1)-fbin(vect));
endif
endfor
endfor
bank = H;
return
endfunction
clc;
clear all;
close all;
pkg load signal;
% record audio
Fs = 44100;
y = record(3,44100);
% OR %
% Load existing file
%[y, Fs] = wavread('../FILE_PATH/');
%y = y(44100:2*44100);
% create mel filterbanks
minFreq = 500; % minimum cutoff frequency in Hz
maxFreq = 10000; % maximum cutoff frequency in Hz
% melbank(number_of_banks, minFreq, mazFreq, sampling_rate)
foo = melbank(30,minFreq,maxFreq,Fs);
% create frames
frames = create_frames(y, Fs, 0.025, 0.010);
% calculate periodogram of each frame
NF = length(frames(1,:));
[P,F] = periodogram(frames(:,1),[], 1024, Fs);
% apply mel filters to the power spectra
P = foo.*P(1:512);
% sum the energy in each filter and take the logarithm
P = log(sum(P));
% take the DCT of the log filterbank energies
% discard the first coeff 'cause it'll be -Inf after taking log
L = length(P);
P = dct(P(2:L));
PXX = P;
for i = 2:NF
P = periodogram(frames(:,i),[], 1024, Fs);
% apply mel filters to the power spectra
P = foo.*P(1:512);
% sum the energy in each filter and take the logarithm
P = log(sum(P));
% take the DCT of the log filterbank energies
% discard the first coeff 'cause it'll be -Inf after taking log
P = dct(P(2:L));
% coeffients are stacked row wise for each frame
PXX = [PXX; P];
endfor
% stack the coeffients column wise
PXX = PXX';
plot(PXX);