一、案例简介

主要介绍的是的语音信号的简单处理。本论文针对以上问题,运用数字信号学基本原理实现语音信号的处理,在matlab7.0环境下综合运用信号提取,幅频变换以及傅里叶变换、滤波等技术来进行语音信号处理。我所做的工作就是在matlab7.0软件上编写一个处理语音信号的程序,能对语音信号进行采集,并对其进行各种处理,达到简单语音信号处理的目的。
对语音信号的研究,本论文采用了设计两种滤波器的基本研究方法来达到研究语音信号去噪的目的,最终结合图像以及对语音信号的回放,通过对比,得出结论。
本课题的研究基本步骤如下:
1、语音信号的录制。
2、在MATLAB平台上读入语音信号。
3、绘制频谱图并回放原始语音信号。
4、利用MATLAB编程加入一段正弦波噪音,设计滤波器去噪。
5、利用MATLAB编程加入一段随机噪音信号,设计FIR和IIR滤波器去噪,并分别绘制频谱图、回放语音信号。
6 通过仿真后的图像以及对语音信号的回放,对比两种去噪方式的优缺点。

二、部分源代码

function varargout = zaosheng(varargin)
% ZAOSHENG MATLAB code for zaosheng.fig
%      ZAOSHENG, by itself, creates a new ZAOSHENG or raises the existing
%      singleton*.
%
%      H = ZAOSHENG returns the handle to a new ZAOSHENG or the handle to
%      the existing singleton*.
%
%      ZAOSHENG('CALLBACK',hObject,eventData,handles,...) calls the local
%      function named CALLBACK in ZAOSHENG.M with the given input arguments.
%
%      ZAOSHENG('Property','Value',...) creates a new ZAOSHENG or raises the
%      existing singleton*.  Starting from the left, property value pairs are
%      applied to the GUI before zaosheng_OpeningFcn gets called.  An
%      unrecognized property name or invalid value makes property application
%      stop.  All inputs are passed to zaosheng_OpeningFcn via varargin.
%
%      *See GUI Options on GUIDE's Tools menu.  Choose "GUI allows only one
%      instance to run (singleton)".
%
% See also: GUIDE, GUIDATA, GUIHANDLES

% Edit the above text to modify the response to help zaosheng

% Last Modified by GUIDE v2.5 09-Jun-2015 02:09:47

% Begin initialization code - DO NOT EDIT
gui_Singleton = 1;
gui_State = struct('gui_Name',       mfilename, ...
                   'gui_Singleton',  gui_Singleton, ...
                   'gui_OpeningFcn', @zaosheng_OpeningFcn, ...
                   'gui_OutputFcn',  @zaosheng_OutputFcn, ...
                   'gui_LayoutFcn',  [] , ...
                   'gui_Callback',   []);
if nargin && ischar(varargin{1})
    gui_State.gui_Callback = str2func(varargin{1});
end

if nargout
    [varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});
else
    gui_mainfcn(gui_State, varargin{:});
end
% End initialization code - DO NOT EDIT


% --- Executes just before zaosheng is made visible.
function zaosheng_OpeningFcn(hObject, eventdata, handles, varargin)
% This function has no output args, see OutputFcn.
% hObject    handle to figure
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)
% varargin   command line arguments to zaosheng (see VARARGIN)

% Choose default command line output for zaosheng
handles.output = hObject;

% Update handles structure
guidata(hObject, handles);

% UIWAIT makes zaosheng wait for user response (see UIRESUME)
% uiwait(handles.figure1);


% --- Outputs from this function are returned to the command line.
function varargout = zaosheng_OutputFcn(hObject, eventdata, handles) 
% varargout  cell array for returning output args (see VARARGOUT);
% hObject    handle to figure
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)

% Get default command line output from handles structure
varargout{1} = handles.output;


% --- Executes on button press in pushbutton1.
function pushbutton1_Callback(hObject, eventdata, handles)
%%选择语音信号,画出波形图与频谱
global y;
global fs;
global bits;
global N;
global t;
global x;
global x1;
global y1;
global y2;
global y3;
global a;
global b;
global d;


H={'*.wav'};
[filename,pathname]=uigetfile(H,'请选择打开文件');
file=strcat(pathname,filename);
[y,fs,bits]=wavread(file);
y=y(:,1);
sound(y,fs);
N=length(y);
t=(0:N-1)/fs;

cla(handles.axes1);
cla(handles.axes2);
cla(handles.axes3);
cla(handles.axes4);
set(handles.axes1,'visible','on');
set(handles.axes2,'visible','on');
set(handles.axes3,'visible','off');
set(handles.axes4,'visible','off');

axes(handles.axes1);
plot(t,y);
title('原始语音信号波形');
xlabel('时间(s)');
ylabel('幅值(dB)');


y1=fft(y,1024);
f=fs*(0:511)/1024;

axes(handles.axes2);
plot(f,abs(y1(1:512)));
title('原始语音信号频谱');
xlabel('频率(Hz)'); 
ylabel('幅值(dB)');
set(gca,'xlim',[1 5000]);




% hObject    handle to pushbutton1 (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)


% --- Executes on button press in pushbutton2.
function pushbutton2_Callback(hObject, eventdata, handles)
%%噪声信号波形与频谱
global y;
global fs;
global bits;
global N;
global t;
global x;
global x1;
global y1;
global y2;
global y3;
global a;
global b;
global d;

randn('state',0);
x1=0.1*randn(N,1);%产生高斯白噪声序列即噪声信号
sound(x1,fs);%播放噪声信号

cla(handles.axes3);
cla(handles.axes4);
set(handles.axes1,'visible','on');
set(handles.axes2,'visible','on');
set(handles.axes3,'visible','on');
set(handles.axes4,'visible','on');

axes(handles.axes3);
plot(t,x1);
title('高斯随机噪声波形');
xlabel('时间(s)'); 
ylabel('幅值(dB)');

axes(handles.axes4);
y2=fft(x1,1024);
f=fs*(0:511)/1024;
plot(f,abs(y2(1:512)));
title('高斯随机噪声频谱');
xlabel('频率(Hz)'); 
ylabel('幅值(dB)');
set(gca,'xlim',[1 5000]);
% hObject    handle to pushbutton2 (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)


% --- Executes on button press in pushbutton3.
function pushbutton3_Callback(hObject, eventdata, handles)
%%加噪后语音信号波形与频谱
global y;
global fs;
global bits;
global N;
global t;
global x;
global x1;
global y1;
global y2;
global y3;
global a;
global b;
global d;




x=x1+y;
sound(x,fs);

cla(handles.axes3);
cla(handles.axes4);
set(handles.axes1,'visible','on');
set(handles.axes2,'visible','on');
set(handles.axes3,'visible','on');
set(handles.axes4,'visible','on');

axes(handles.axes3);
plot(t,x);
title('加噪后语音信号波形');
xlabel('时间(s)'); 
ylabel('幅值(dB)');

axes(handles.axes4);
y3=fft(x,1024);
f=fs*(0:511)/1024;
plot(f,abs(y3(1:512)));
title('加噪后语音信号频谱');
xlabel('频率(Hz)'); 
ylabel('幅值(dB)');
set(gca,'xlim',[1 5000]);
% hObject    handle to pushbutton3 (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)

三、运行结果

【语音去噪】基于matlab GUI语音加噪和降噪处理【含Matlab源码 473期】_去噪
【语音去噪】基于matlab GUI语音加噪和降噪处理【含Matlab源码 473期】_去噪_02
【语音去噪】基于matlab GUI语音加噪和降噪处理【含Matlab源码 473期】_语音信号_03
【语音去噪】基于matlab GUI语音加噪和降噪处理【含Matlab源码 473期】_ide_04

四、matlab版本及参考文献

1 matlab版本
2014a

2 参考文献
[1]韩纪庆,张磊,郑铁然.语音信号处理(第3版)[M].清华大学出版社,2019.
[2]柳若边.深度学习:语音识别技术实践[M].清华大学出版社,2019.