1 模型
本文提出了一种语音增强算法,该算法以基于先验信噪比估计的维纳滤波法为基础。通过计算无声段的统计平均得到初始噪声功率谱,并平滑处理初始噪声功率谱和带噪语音功率谱,更新了噪声功率谱;最后,考虑了某频率点处噪声急剧增大的情况,做了相关验证,该算法能有效地抑制变化范围不大或是稳定的噪声,但是对实际中的变化范围很广的噪声效果不是很好。
1.1?语音增强的相关概念
嵌在语音系统中,语音信号不可避免的会受到周围噪声的干扰,从而影响语音的质量与可懂度。
????语音增强:其实就是带噪语音中提取尽可能纯净的语音,改善语音质量和可懂度,提高噪声环境下语音通信系统的性能。
噪声都随机产生的,不可能完全消除。语音增强的目标是:减弱噪声、消除背景噪声、改进语音质量、使听着乐于接受,提高语音可懂度。
1.2?语音增强的相关算法
由于噪声来源众多,特性各不相同。语音增强处理系统的应用场合千差万别。
因此,不存在一种可以通用于各种噪声环境的语音增强算法。针对不同的环境,采取不同的语音增强算法。
语音增强算法按处理方式可以分为:基于语音周期性的增强算法,基于全极点模型的增强算法,基于短时谱估计的增强算法,基于信号子空间的增强算法和
基于HMM的增强算法。
从目前的发展来看,基于短时谱估计的方法是最有效的方法。具体包括谱减法、维纳滤波、最小均方误差短时谱幅度估计法(MMSE-STSA)和最小均方误差对数谱幅度估计法(MMSE-LSA)。本文主要讨论使用维纳滤波器实现语音的增强处理。
?2 部分代码
function?varargout?=?adsp_project(varargin)
% ADSP_PROJECT MATLAB code for adsp_project.fig
% ? ? ADSP_PROJECT, by itself, creates a new ADSP_PROJECT or raises the existing
% ? ? singleton*.
%
% ? ? H = ADSP_PROJECT returns the handle to a new ADSP_PROJECT or the handle to
% ? ? the existing singleton*.
%
% ? ? ADSP_PROJECT('CALLBACK',hObject,eventData,handles,...) calls the local
% ? ? function named CALLBACK in ADSP_PROJECT.M with the given input arguments.
%
% ? ? ADSP_PROJECT('Property','Value',...) creates a new ADSP_PROJECT or raises the
% ? ? existing singleton*. Starting from the left, property value pairs are
% ? ? applied to the GUI before adsp_project_OpeningFcn gets called. An
% ? ? unrecognized property name or invalid value makes property application
% ? ? stop. All inputs are passed to adsp_project_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 adsp_project
% Last Modified by GUIDE v2.5 15-Dec-2014 18:26:21
% Begin initialization code - DO NOT EDIT
gui_Singleton?=?1;
gui_State?=?struct('gui_Name', ? ? ??mfilename,?...
? ? ? ? ? ? ? ? ??'gui_Singleton', ?gui_Singleton,?...
? ? ? ? ? ? ? ? ??'gui_OpeningFcn',?@adsp_project_OpeningFcn,?...
? ? ? ? ? ? ? ? ??'gui_OutputFcn', ?@adsp_project_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 adsp_project is made visible.
function?adsp_project_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 adsp_project (see VARARGIN)
% Choose default command line output for adsp_project
handles.output?=?hObject;
% Update handles structure
guidata(hObject,?handles);
% UIWAIT makes adsp_project wait for user response (see UIRESUME)
% uiwait(handles.figure1);
% --- Outputs from this function are returned to the command line.
function?varargout?=?adsp_project_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)
global?xk;
global?fs;
global?noise_type;
noise_type=1;
[FileName,PathName] =?uigetfile('*.wav','Select the voice-file');
[x,fs]=wavread(FileName);
ls=length(x);
xk=x(1:ls);
set(handles.text_fs,'string',num2str(fs));
set(handles.text_ls,'string',num2str(ls));
axes(handles.axes_freq);
%xaxis1=linspace(0,0.5,250);
plot(abs(fft(xk))); ?%xk 音频的句柄 用来做按键响应函数
axis([0,14000,0,300]) ;
axes(handles.axes_wave);
%xaxis1=linspace(0,0.5,250);
h_xk=plot(xk); ?%xk 音频的句柄 用来做按键响应函数
axis([0,30000,-1.5,1.5]) ;
set(h_xk,'ButtonDownFcn',@axes_waveCallback);
%grid on;
%set(gca,'xtick',(0:0.02:0.5),'ytick',[0:100:500]);
%axis([0.25 0.45 0 500]);
% 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)
global?xk;
global?SNR;
global?fs;
global?xs;
global?noise_type;
noise_type=1;%高斯噪声
SNR_slider=get(handles.slider_SNR,'value');
SNR_slider=floor(SNR_slider);
SNR=num2str(SNR_slider);
set(handles.text_snr,'string',SNR);
xs=awgn(xk,SNR_slider,0);%加入高斯白噪声,信噪比30
axes(handles.axes_freq);
plot(abs(fft(xs))); ?%xk 音频的句柄 用来做按键响应函数
axis([0,14000,0,300]) ;
axes(handles.axes_noise);
h_xs=plot(xs);
axis([0,30000,-1.5,1.5]) ;
set(h_xs,'ButtonDownFcn',@axes_noiseCallback);
% 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.
% 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)
% --- Executes on selection change in popupmenu1.
function?popupmenu1_Callback(hObject,?eventdata,?handles)
% hObject ? handle to popupmenu1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
% Hints: contents = cellstr(get(hObject,'String')) returns popupmenu1 contents as cell array
% ? ? ? contents{get(hObject,'Value')} returns selected item from popupmenu1
% --- Executes during object creation, after setting all properties.
function?popupmenu1_CreateFcn(hObject,?eventdata,?handles)
% hObject ? handle to popupmenu1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? empty - handles not created until after all CreateFcns called
% Hint: popupmenu controls usually have a white background on Windows.
% ? ? ? See ISPC and COMPUTER.
if?ispc?&&?isequal(get(hObject,'BackgroundColor'),?get(0,'defaultUicontrolBackgroundColor'))
? ?set(hObject,'BackgroundColor','white');
end
% --- Executes on key press with focus on pushbutton1 and none of its controls.
function?pushbutton1_KeyPressFcn(hObject,?eventdata,?handles)
% hObject ? handle to pushbutton1 (see GCBO)
% eventdata structure with the following fields (see UICONTROL)
%Key: name of the key that was pressed, in lower case
%Character: character interpretation of the key(s) that was pressed
%Modifier: name(s) of the modifier key(s) (i.e., control, shift) pressed
% handles ? structure with handles and user data (see GUIDATA)
% --- If Enable == 'on', executes on mouse press in 5 pixel border.
% --- Otherwise, executes on mouse press in 5 pixel border or over pushbutton1.
function?pushbutton1_ButtonDownFcn(hObject,?eventdata,?handles)
% 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 slider movement.
function?slider2_Callback(hObject,?eventdata,?handles)
% hObject ? handle to slider2 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
% Hints: get(hObject,'Value') returns position of slider
% ? ? ? get(hObject,'Min') and get(hObject,'Max') to determine range of slider
% --- Executes during object creation, after setting all properties.
function?slider2_CreateFcn(hObject,?eventdata,?handles)
% hObject ? handle to slider2 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? empty - handles not created until after all CreateFcns called
% Hint: slider controls usually have a light gray background.
if?isequal(get(hObject,'BackgroundColor'),?get(0,'defaultUicontrolBackgroundColor'))
? ?set(hObject,'BackgroundColor',[.9?.9?.9]);
end
% --- Executes on slider movement.
function?slider_SNR_Callback(hObject,?eventdata,?handles)
global?xk;
global?SNR;
global?xs;
global?noise_type;
global?realtime_filter_flag;
if?noise_type==1
SNR_slider=get(handles.slider_SNR,'value');
SNR_slider=floor(SNR_slider);
SNR=num2str(SNR_slider);
set(handles.text_snr,'string',SNR);
xs=awgn(xk,SNR_slider,0);%加入高斯白噪声,信噪比30
axes(handles.axes_freq);
plot(abs(fft(xs))); ?%xk 音频的句柄 用来做按键响应函数
axis([0,14000,0,300]) ;
axes(handles.axes_noise);
h_xs=plot(xs);
axis([0,30000,-1.5,1.5]) ;
set(h_xs,'ButtonDownFcn',@axes_noiseCallback);
else?
xs=xk;
SNR_slider=get(handles.slider_SNR,'value');
SNR_slider=floor(SNR_slider);
SNR=num2str(SNR_slider);
set(handles.text_snr,'string',SNR);
step=2500;
lenth=800;
xs(1:2000)=awgn(xk(1:2000),SNR_slider,0);?%最前面的底噪 不然segment出错
for?i=3:8
xs(i*step:i*step+lenth)=awgn(xk(i*step:i*step+lenth),SNR_slider,0);%加入高斯白噪声,信噪比30
end
axes(handles.axes_freq);
plot(abs(fft(xs))); ?%xk 音频的句柄 用来做按键响应函数
axis([0,14000,0,300]) ;
axes(handles.axes_noise);
h_xs=plot(xs);
axis([0,30000,-1.5,1.5]) ;
set(h_xs,'ButtonDownFcn',@axes_noiseCallback);
end
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%维纳滤波
global?fs;
global?filtered;
global?flen;
global?freq_uf;
global?freq_f;
global?filtered_flag;
if??realtime_filter_flag==1;
? ?
flen=get(handles.f_lenth_slider,'value');?%每帧长度
FLEN=num2str(flen);
set(handles.text_f_lenth,'string',FLEN);
%?
[filtered,freq_uf,freq_f]=WienerScalart96m(xs,fs,0.25,flen);%freq_uf 滤波前 freq_f 滤波后
filtered_flag=1;
axes(handles.axes_freq);
plot(abs(fft(filtered))); ?%xk 音频的句柄 用来做按键响应函数
axis([0,14000,0,300]) ;
axes(handles.axes_cleaned);
h_filtered=plot(filtered);
axis([0,30000,-1.5,1.5]) ;
set(h_filtered,'ButtonDownFcn',@axes_filteredCallback);
end
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%维纳滤波
% hObject ? handle to slider_SNR (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
% Hints: get(hObject,'Value') returns position of slider
% ? ? ? get(hObject,'Min') and get(hObject,'Max') to determine range of slider
% --- Executes during object creation, after setting all properties.
function?slider_SNR_CreateFcn(hObject,?eventdata,?handles)
% hObject ? handle to slider_SNR (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? empty - handles not created until after all CreateFcns called
% Hint: slider controls usually have a light gray background.
if?isequal(get(hObject,'BackgroundColor'),?get(0,'defaultUicontrolBackgroundColor'))
? ?set(hObject,'BackgroundColor',[.9?.9?.9]);
end
% --- Executes on slider movement.
function?slider5_Callback(hObject,?eventdata,?handles)
% hObject ? handle to slider5 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
% Hints: get(hObject,'Value') returns position of slider
% ? ? ? get(hObject,'Min') and get(hObject,'Max') to determine range of slider
% --- Executes during object creation, after setting all properties.
function?slider5_CreateFcn(hObject,?eventdata,?handles)
% hObject ? handle to slider5 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? empty - handles not created until after all CreateFcns called
% Hint: slider controls usually have a light gray background.
if?isequal(get(hObject,'BackgroundColor'),?get(0,'defaultUicontrolBackgroundColor'))
? ?set(hObject,'BackgroundColor',[.9?.9?.9]);
end
% --- Executes on slider movement.
function?pre_noice_slider_Callback(hObject,?eventdata,?handles)
global?fs;
global?xs;
global?filtered;
global?flen;
global?pre_noice;
global?filtered_flag;
pre_noice=get(handles.pre_noice_slider,'value');%前导噪声
flen=get(handles.f_lenth_slider,'value');?%每帧长度
FLEN=num2str(flen);
PRE_NOICE=num2str(pre_noice);
set(handles.text_f_lenth,'string',FLEN);
set(handles.pre_noice_text,'string',PRE_NOICE);
%?
[filtered,freq_uf,freq_f]=WienerScalart96m(xs,fs,0.25,flen);%freq_uf 滤波前 freq_f 滤波后
filtered_flag=1;
axes(handles.axes_cleaned);
h_filtered=plot(filtered);
axis([0,30000,-1.5,1.5]) ;
set(h_filtered,'ButtonDownFcn',@axes_filteredCallback);
% hObject ? handle to pre_noice_slider (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
% Hints: get(hObject,'Value') returns position of slider
% ? ? ? get(hObject,'Min') and get(hObject,'Max') to determine range of slider
% --- Executes during object creation, after setting all properties.
function?pre_noice_slider_CreateFcn(hObject,?eventdata,?handles)
% hObject ? handle to pre_noice_slider (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? empty - handles not created until after all CreateFcns called
% Hint: slider controls usually have a light gray background.
if?isequal(get(hObject,'BackgroundColor'),?get(0,'defaultUicontrolBackgroundColor'))
? ?set(hObject,'BackgroundColor',[.9?.9?.9]);
end
% --- Executes on selection change in popupmenu2.
function?popupmenu2_Callback(hObject,?eventdata,?handles)
% hObject ? handle to popupmenu2 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
% Hints: contents = cellstr(get(hObject,'String')) returns popupmenu2 contents as cell array
% ? ? ? contents{get(hObject,'Value')} returns selected item from popupmenu2
% --- Executes during object creation, after setting all properties.
function?popupmenu2_CreateFcn(hObject,?eventdata,?handles)
% hObject ? handle to popupmenu2 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? empty - handles not created until after all CreateFcns called
% Hint: popupmenu controls usually have a white background on Windows.
% ? ? ? See ISPC and COMPUTER.
if?ispc?&&?isequal(get(hObject,'BackgroundColor'),?get(0,'defaultUicontrolBackgroundColor'))
? ?set(hObject,'BackgroundColor','white');
end
% --- Executes on slider movement.
function?f_lenth_slider_Callback(hObject,?eventdata,?handles)
global?fs;
global?xs;
global?filtered;
global?flen;
global?freq_uf;
global?freq_f;
global?filtered_flag;
flen=get(handles.f_lenth_slider,'value');?%每帧长度
FLEN=num2str(flen);
set(handles.text_f_lenth,'string',FLEN);
[filtered,freq_uf,freq_f]=WienerScalart96m(xs,fs,0.25,flen);%freq_uf 滤波前 freq_f 滤波后
filtered_flag=1;;%freq_uf 滤波前 freq_f 滤波后
?axes(handles.axes_freq);
plot(abs(fft(filtered))); ?%xk 音频的句柄 用来做按键响应函数
axis([0,14000,0,300]) ;
axes(handles.axes_cleaned);
h_filtered=plot(filtered);
axis([0,30000,-1.5,1.5]) ;
set(h_filtered,'ButtonDownFcn',@axes_filteredCallback);
% hObject ? handle to f_lenth_slider (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
% Hints: get(hObject,'Value') returns position of slider
% ? ? ? get(hObject,'Min') and get(hObject,'Max') to determine range of slider
% --- Executes during object creation, after setting all properties.
function?f_lenth_slider_CreateFcn(hObject,?eventdata,?handles)
% hObject ? handle to f_lenth_slider (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? empty - handles not created until after all CreateFcns called
% Hint: slider controls usually have a light gray background.
if?isequal(get(hObject,'BackgroundColor'),?get(0,'defaultUicontrolBackgroundColor'))
? ?set(hObject,'BackgroundColor',[.9?.9?.9]);
end
% --- Executes on button press in pushbutton3.
function?pushbutton3_Callback(hObject,?eventdata,?handles)
global?fs;
global?xs;
global?filtered;
global?flen;
global?freq_uf;
global?freq_f;
global?filtered_flag;
flen=get(handles.f_lenth_slider,'value');?%每帧长度
FLEN=num2str(flen);
set(handles.text_f_lenth,'string',FLEN);
%?
[filtered,freq_uf,freq_f]=WienerScalart96m(xs,fs,0.25,flen);%freq_uf 滤波前 freq_f 滤波后
filtered_flag=1;%freq_uf 滤波前 freq_f 滤波后
axes(handles.axes_freq);
plot(abs(fft(filtered))); ?%xk 音频的句柄 用来做按键响应函数
axis([0,14000,0,300]) ;
axes(handles.axes_cleaned);
h_filtered=plot(filtered);
axis([0,30000,-1.5,1.5]) ;
set(h_filtered,'ButtonDownFcn',@axes_filteredCallback);
% 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)
% --- Executes during object deletion, before destroying properties.
function?pushbutton1_DeleteFcn(hObject,?eventdata,?handles)
% 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 mouse press over axes background.
function?axes_wave_ButtonDownFcn(hObject,?eventdata,?handles)
% hObject ? handle to axes_wave (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
% --- Executes during object creation, after setting all properties.
function?axes_waveCallback(hObject,?eventdata,?handles)
global?fs;
global?xk;
sound(xk,fs);
function?axes_noiseCallback(hObject,?eventdata,?handles)
global?fs;
global?xs;
sound(xs,fs);
function?axes_filteredCallback(hObject,?eventdata,?handles)
global?fs;
global?filtered;
sound(filtered,fs);
% --- Executes during object creation, after setting all properties.
function?axes_wave_CreateFcn(hObject,?eventdata,?handles)
% hObject ? handle to axes_wave (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? empty - handles not created until after all CreateFcns called
% Hint: place code in OpeningFcn to populate axes_wave
% --- Executes on button press in pushbutton4.
function?pushbutton4_Callback(hObject,?eventdata,?handles)
global?xk;
global?SNR;
global?fs;
global?xs;
global?noise_type;
noise_type=2;
xs=xk;
SNR_slider=get(handles.slider_SNR,'value');
SNR_slider=floor(SNR_slider);
SNR=num2str(SNR_slider);
set(handles.text_snr,'string',SNR);
step=2500;
lenth=800;
xs(1:2000)=awgn(xk(1:2000),SNR_slider,0);
for?i=3:8
xs(i*step:i*step+lenth)=awgn(xk(i*step:i*step+lenth),SNR_slider,0);%加入高斯白噪声,信噪比30
end
axes(handles.axes_freq);
plot(abs(fft(xs))); ?%xk 音频的句柄 用来做按键响应函数
axis([0,14000,0,300]) ;
axes(handles.axes_noise);
h_xs=plot(xs);
axis([0,30000,-1.5,1.5]) ;
set(h_xs,'ButtonDownFcn',@axes_noiseCallback);
% hObject ? handle to pushbutton4 (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 pushbutton5.
function?pushbutton5_Callback(hObject,?eventdata,?handles)
global?realtime_filter_flag;
?string1='实时滤波';
? ?string2=' 开';
? ?string3=' 关';
if?realtime_filter_flag==1
? ?realtime_filter_flag=0;
??
? ?set(handles.pushbutton5,'string',[string1?string3]);
? ?
else
? ??set(handles.pushbutton5,'string',[string1?string2]);
? ?realtime_filter_flag=1;
end
% hObject ? handle to pushbutton5 (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 pushbutton6.
function?pushbutton6_Callback(hObject,?eventdata,?handles)
global?flen;
global?xk;
global?xs;
global?filtered;
global?fs;
global?freq_uf;
global?freq_f;
global?filtered_flag;
if(filtered_flag)
figure(1);
a=size(freq_uf);%获取矩阵大小
subplot(1,2,1);
imagesc(0:1:a(1),0:1:a(2),freq_uf);
title('滤波前');
subplot(1,2,2);
b=size(freq_f);%获取矩阵大小
imagesc(0:1:b(1),0:1:b(2),freq_f);
title('滤波后');
else
?errordlg('请先进行滤波','MATLAB error') ;
end
% specgram(xk,flen,fs,flen,2*flen/5);
%?
% figure(2);
% specgram(xs,flen,fs,flen,2*flen/5);
%?
% figure(3);
% specgram(filtered,flen,fs,flen,2*flen/5);
% hObject ? handle to pushbutton6 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles ? structure with handles and user data (see GUIDATA)
3 仿真结果
4 参考文献
[1]张亮, 龚卫国. 一种改进的维纳滤波语音增强算法[J]. 计算机工程与应用, 2010(26):133-135.
|