【语音识别】基于小波变换DWT 0-9数字语音识别附matlab代码

✅作者简介：热爱科研的Matlab仿真开发者，修心和技术同步精进，matlab项目合作可私信。

🍎个人主页：Matlab科研工作室

🍊个人信条：格物致知。

更多Matlab仿真内容点击👇

智能优化算法       神经网络预测       雷达通信       无线传感器        电力系统

信号处理              图像处理               路径规划       元胞自动机        无人机 

⛄ 内容介绍

语音识别是一门交叉学科,它与语音学,语言学,数字信号处理,模式识别,最优化理论,计算机科学等众多学科紧密相连,是一门既有理论价值又有实际意义的学科.语音识别发展了几十年,取得了很大的进步.语音识别在某些方面还是存在一些问题:如对自然语言的识别和理解还属于初级阶段;语音信息量大不易存储;语音的模糊性;单个字母或词,字的语音特性受上下文的影响,以致改变了重音,音调,音量和发音速度等;环境噪声和其它干扰对语音识别有严重影响,致使识别率低.因此,解决以上问题是语音识别发展的重点.

⛄ 部分代码

function [x,mn,mx]=melbankm(p,n,fs,fl,fh,w)

%MELBANKM determine matrix for a mel-spaced filterbank [X,MN,MX]=(P,N,FS,FL,FH,W)

%

% Inputs: p   number of filters in filterbank

% n   length of fft

% fs  sample rate in Hz

% fl  low end of the lowest filter as a fraction of fs (default = 0)

% fh  high end of highest filter as a fraction of fs (default = 0.5)

% w   any sensible combination of the following:

%       't'  triangular shaped filters in mel domain (default)

%       'n'  hanning shaped filters in mel domain

%       'm'  hamming shaped filters in mel domain

%

%       'z'  highest and lowest filters taper down to zero (default)

%       'y'  lowest filter remains at 1 down to 0 frequency and

%    highest filter remains at 1 up to nyquist freqency

%

%        If 'ty' or 'ny' is specified, the total power in the fft is preserved.

%

% Outputs: x     a sparse matrix containing the filterbank amplitudes

%       If x is the only output argument then size(x)=[p,1+floor(n/2)]

%       otherwise size(x)=[p,mx-mn+1]

% mn   the lowest fft bin with a non-zero coefficient

% mx   the highest fft bin with a non-zero coefficient

%

% Usage: f=fft(s); f=fft(s);

% x=melbankm(p,n,fs); [x,na,nb]=melbankm(p,n,fs);

% n2=1+floor(n/2); z=log(x*(f(na:nb)).*conj(f(na:nb)));

% z=log(x*abs(f(1:n2)).^2);

% c=dct(z); c(1)=[];

%

% To plot filterbanks e.g. plot(melbankm(20,256,8000)')

%

%      Copyright (C) Mike Brookes 1997

%      Version: $Id: melbankm.m,v 1.3 2005/02/21 15:22:13 dmb Exp $

%

%   VOICEBOX is a MATLAB toolbox for speech processing.

%   Home page: http://www.ee.ic.ac.uk/hp/staff/dmb/voicebox/voicebox.html

%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%   This program is free software; you can redistribute it and/or modify

%   it under the terms of the GNU General Public License as published by

%   the Free Software Foundation; either version 2 of the License, or

%   (at your option) any later version.

%

%   This program is distributed in the hope that it will be useful,

%   but WITHOUT ANY WARRANTY; without even the implied warranty of

%   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

%   GNU General Public License for more details.

%

%   You can obtain a copy of the GNU General Public License from

%   ftp://prep.ai.mit.edu/pub/gnu/COPYING-2.0 or by writing to

%   Free Software Foundation, Inc.,675 Mass Ave, Cambridge, MA 02139, USA.

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

if nargin < 6

  w='tz';

  if nargin < 5

    fh=0.5;

    if nargin < 4

      fl=0;

    end

  end

end

f0=700/fs;

fn2=floor(n/2);

lr=log((f0+fh)/(f0+fl))/(p+1);

% convert to fft bin numbers with 0 for DC term

bl=n*((f0+fl)*exp([0 1 p p+1]*lr)-f0);

b2=ceil(bl(2));

b3=floor(bl(3));

if any(w=='y')

  pf=log((f0+(b2:b3)/n)/(f0+fl))/lr;

  fp=floor(pf);

  r=[ones(1,b2) fp fp+1 p*ones(1,fn2-b3)];

  c=[1:b3+1 b2+1:fn2+1];

  v=2*[0.5 ones(1,b2-1) 1-pf+fp pf-fp ones(1,fn2-b3-1) 0.5];

  mn=1;

  mx=fn2+1;

else

  b1=floor(bl(1))+1;

  b4=min(fn2,ceil(bl(4)))-1;

  pf=log((f0+(b1:b4)/n)/(f0+fl))/lr;

  fp=floor(pf);

  pm=pf-fp;

  k2=b2-b1+1;

  k3=b3-b1+1;

  k4=b4-b1+1;

  r=[fp(k2:k4) 1+fp(1:k3)];

  c=[k2:k4 1:k3];

  v=2*[1-pm(k2:k4) pm(1:k3)];

  mn=b1+1;

  mx=b4+1;

end

if any(w=='n')

  v=1-cos(v*pi/2);

elseif any(w=='m')

  v=1-0.92/1.08*cos(v*pi/2);

end

if nargout > 1

  x=sparse(r,c,v);

else

  x=sparse(r,c+mn-1,v,p,1+fn2);

end

⛄ 运行结果

​⛄ 参考文献

[1] 李法强. 基于小波变换的语音识别的研究和应用[D]. 桂林理工大学, 2011.

[2] 邹蓬, 张鹏, 陈艳. 一种基于小波变换的数字水印技术[J]. 中国民航大学学报, 2005.

[3] 金小华. 基于DWT的数字视频水印技术[J]. 苏州市职业大学学报, 2009.

[4] 杨雄. 基于小波变换的数字图像水印研究[D]. 华中师范大学.

⛳️ 代码获取关注我

❤️部分理论引用网络文献，若有侵权联系博主删除

❤️ 关注我领取海量matlab电子书和数学建模资料