说话人语音识别

原始能量谱4000 350045040030003502500300zH/率2000250频15002001501000100500500 00.511.522.5时间/s通过mel倒谱修正后的能量谱20 700186001614500目12400数器10波滤83006200421000 00.511.522.5时间/s

附录2

function M3 = blockFrames(s, fs, m, n) % blockFrames:

% Puts the signal into frames 分帧函数 % Inputs:

% s contains the signal to analize 语音信号

% fs is the sampling rate of the signal 语音采样频率

% m is the distance between the beginnings of two frames 两帧之间的距离

% n is the number of samples per frame 每帧的采样点数 % Output:

% M3 is a matrix containing all the frames 数组形式，包含了所有的帧 l = length(s); %语音信号的长度

nbFrame = floor((l - n) / m) + 1; %帧数 for i = 1:n for j = 1:nbFrame

M(i, j) = s(((j - 1) * m) + i); %逐帧扫描 end end

h = hamming(n);

M2 = diag(h) * M; %加汉明窗 for i = 1:nbFrame

M3(:, i) = fft(M2(:, i)); %短时傅立叶变换 End

function code = train(traindir, n) % 计算wav文件的VQ码码本

% Speaker Recognition: Training Stage % Input:

% traindir : string name of directory contains all train sound files % n : number of train files in traindir % Output:

% code : trained VQ codebooks, code{i} for i-th speaker % Note:

% Sound files in traindir is supposed to be: % s1.wav, s2.wav, ..., sn.wav % Example:

% >> code = train('C:\\data\\train\\', 8);

k = 16; % number of centroids required

for i = 1:n % train a VQ codebook for each speaker file = sprintf('%ss%d.wav', traindir, i); disp(file);

[s, fs] = wavread(file);

v = mfcc(s, fs); % Compute MFCC's code{i} = vqlbg(v, k); % Train VQ codebook end

function d = disteu(x, y)

% DISTEU Pairwise Euclidean distances between columns of two matrices 测试失真度 % Input:

% x, y: Two matrices whose each column is an a vector data. % Output:

% d: Element d(i,j) will be the Euclidean distance between two column vectors X(:,i) and Y(:,j) % Note:

% The Euclidean distance D between two vectors X and Y is: % D = sum((x-y).^2).^0.5 [M, N] = size(x); [M2, P] = size(y); if (M ~= M2) error('不匹配！') end

d = zeros(N, P); if (N < P)

copies = zeros(1,P); for n = 1:N

d(n,:) = sum((x(:, n+copies) - y) .^2, 1); end else

copies = zeros(1,N); for p = 1:P

d(:,p) = sum((x - y(:, p+copies)) .^2, 1)'; end end

d = d.^0.5;

function m = melfb(p, n, fs)

% MELFB Determine matrix for a mel-spaced filterbank % Inputs: p number of filters in filterbank 滤波器数 % n length of fft FFT变换的点数

% fs sample rate in Hz 采样频率 % Outputs: x a (sparse) matrix containing the filterbank amplitudes % size(x) = [p, 1+floor(n/2)]

% Usage: For example, to compute the mel-scale spectrum of a

% colum-vector signal s, with length n and sample rate fs: %

% f = fft(s);

% m = melfb(p, n, fs); % n2 = 1 + floor(n/2); % z = m * abs(f(1:n2)).^2; %

% z would contain p samples of the desired mel-scale spectrum %

% To plot filterbanks e.g.: %

% plot(linspace(0, (12500/2), 129), melfb(20, 256, 12500)'), % title('Mel-spaced filterbank'), xlabel('Frequency (Hz)');

f0 = 700 / fs; fn2 = floor(n/2);

lr = log(1 + 0.5/f0) / (p+1);

% convert to fft bin numbers with 0 for DC term bl = n * (f0 * (exp([0 1 p p+1] * lr) - 1));

b1 = floor(bl(1)) + 1; b2 = ceil(bl(2)); b3 = floor(bl(3));

b4 = min(fn2, ceil(bl(4))) - 1;

pf = log(1 + (b1:b4)/n/f0) / lr; fp = floor(pf); pm = pf - fp;

r = [fp(b2:b4) 1+fp(1:b3)]; c = [b2:b4 1:b3] + 1;

v = 2 * [1-pm(b2:b4) pm(1:b3)];

m = sparse(r, c, v, p, 1+fn2);

function r = mfcc(s, fs) % s声音信号的向量 fs取样频率 % MFCC

% Inputs: s contains the signal to analize % fs is the sampling rate of the signal % Output: r contains the transformed signal m = 100; n = 256;