SSBoll79.

5/9/2012

function [output,Speech]=SSBoll79(signal,fs,IS) % OUTPUT=SSBOLL79(S,FS,IS) % Spectral Subtraction based on Boll 79. Amplitude spectral subtraction % Includes Magnitude Averaging and Residual noise Reduction % % INPUT: Signal is the noisy signal, fs is the sampling frequency and IS is the initial % silence (noise only) length in seconds (default value is .25 sec) % % OUTPUT: output is enhanced speech signal; Speech is VAD vector % % April-05 % Esfandiar Zavarehei %G:\Lab3-SE\15dB\050912-090824.WAV addpath G:\Lab3-SE\15dB; % addpath %[signal,fs]=wavread('sp01VN_babble_sn15.wav'); [signal,fs]=wavread('050912-090824.WAV'); if (nargin<3 || isstruct(IS)) IS=.25; % seconds % IS is the initial silence (noise only) length in seconds ( default value is .25 sec ) end W=fix(.025*fs); %Window length is 25 ms nfft=W; SP=.4; %Shift percentage is 40% (10ms) %Overlap-Add method works good with this value(.4) wnd=hamming(W); % Dung Hamming vi giam thieu duoc side-lope va hien tuong Gibbs % se mang lai hieu suat cai thien thoai cao hon cac cua so % khac. % wnd=rectwin(W); % IGNORE THIS SECTION FOR CAMPATIBALITY WITH ANOTHER PROGRAM FROM HERE..... if (nargin>=3 && isstruct(IS))%This option is for compatibility with another programme W=IS.windowsize; SP=IS.shiftsize/W; nfft=IS.nfft; wnd=IS.window; if isfield(IS,'IS') IS=IS.IS; else IS=.25; end end % .......IGNORE THIS SECTION FOR CAMPATIBALITY WITH ANOTHER PROGRAM T0 HERE NIS=fix((IS*fs-W)/(SP*W) +1);%number of initial silence segments Gamma=1; % (1 for magnitude spectral subtraction 2 for power spectrum subtraction) disp(' Segmentation'); y=segment(signal,W,SP,wnd); % Tap hop cac mau t/h trong cung mot frame sau khi dc phan tich o dau vao % goi la mot "segment". % Voi cach thuc hien phan tich va lien ket cac frame bang phuong phap % overlap va adding thi tin hieu cua chung ta thu duoc sau khi xu ly triet % nhieu se khong bi meo dang va se khong xuat hien hien tuong "giam nhieu". disp('FFT'); Y=fft(y,nfft); YPhase=angle(Y(1:fix(end/2)+1,:)); %Noisy Speech Phase Y=abs(Y(1:fix(end/2)+1,:)).^Gamma;%Specrogram numberOfFrames=size(Y,2); FreqResol=size(Y,1); 1

SSBoll79.m %size(Y), disp(' Noise Initialization'); N=mean(Y(:,1:NIS)')'; %initial Noise Power Spectrum mean NRM=zeros(size(N));% Noise Residual Maximum (Initialization) NoiseCounter=0; NoiseLength=9;%This is a smoothing factor for the noise updating Beta=.03; % he so nen nhieu. disp(' Magnitude Averaged'); % E. Magnitude Averaging YS=Y; %Y Magnitude Averaged for i=2:(numberOfFrames-1) YS(:,i)=(Y(:,i-1)+Y(:,i)+Y(:,i+1))/3; end

5/9/2012

disp(' Spectral Subtraction'); % C. Spectral Subtraction Estimator X=zeros(FreqResol,numberOfFrames); for i=1:numberOfFrames [NoiseFlag, SpeechFlag, NoiseCounter, Dist]=vad(Y(:,i).^(1/Gamma),N.^(1/ Gamma),NoiseCounter); %Magnitude Spectrum Distance VAD Speech(i,1)=SpeechFlag; if SpeechFlag==0 N=(NoiseLength*N+Y(:,i))/(NoiseLength+1); %Update and smooth noise NRM=max(NRM,YS(:,i)-N);%Update Maximum Noise Residue X(:,i)=Beta*Y(:,i); else D=YS(:,i)-N; % Specral Subtraction if i>1 && i<numberOfFrames %Residual Noise Reduction for j=1:length(D) if D(j)<NRM(j) D(j)=min([D(j) YS(j,i-1)-N(j) YS(j,i+1)-N(j)]); end end end X(:,i)=max(D,0); % Half- Wave Rectification end end disp(' Synthesis'); output=OverlapAdd2(X.^(1/Gamma),YPhase,W,SP*W); soundview(output,fs); wavwrite(output,fs,'G:\Lab3-SE\output11.wav'); %auwrite(output,fs,'G:\Lab3-SE\output12.wav'); %%%%%%%%% RECONSTRUCTED SIGNAL %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% function ReconstructedSignal=OverlapAdd2(XNEW,yphase,windowLen,ShiftLen); %Y=OverlapAdd(X,A,W,S); %Y is the signal reconstructed signal from its spectrogram. X is a matrix %with each column being the fft of a segment of signal. A is the phase %angle of the spectrum which should have the same dimension as X. if it is %not given the phase angle of X is used which in the case of real values is %zero (assuming that its the magnitude). W is the window length of time %domain segments if not given the length is assumed to be twice as long as %fft window length. S is the shift length of the segmentation process ( for %example in the case of non overlapping signals it is equal to W and in the %case of %50 overlap is equal to W/2. if not givven W/2 is used. Y is the %reconstructed time domain signal. %Sep-04 %Esfandiar Zavarehei if nargin<2 yphase=angle(XNEW); end if nargin<3 2

SSBoll79.m

5/9/2012

windowLen=size(XNEW,1)*2; end if nargin<4 ShiftLen=windowLen/2; end if fix(ShiftLen)~=ShiftLen ShiftLen=fix(ShiftLen); disp('The shift length have to be an integer as it is the number of samples.') disp(['shift length is fixed to' num2str(ShiftLen)]) end [FreqRes FrameNum]=size(XNEW); Spec=XNEW.*exp(j*yphase); if mod(windowLen,2) %if FreqResol is odd Spec=[Spec;flipud(conj(Spec(2:end,:)))]; else Spec=[Spec;flipud(conj(Spec(2:end-1,:)))]; end sig=zeros((FrameNum-1)*ShiftLen+windowLen,1); weight=sig; for i=1:FrameNum start=(i-1)*ShiftLen+1; spec=Spec(:,i); sig(start:start+windowLen-1)=sig(start:start+windowLen-1)+real(ifft(spec, windowLen)); end ReconstructedSignal=sig; %%%%%%%%%%%%%% VOICE ACTIVITY DETECTION %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% function [NoiseFlag, SpeechFlag, NoiseCounter, Dist]=vad(signal,noise, NoiseCounter,NoiseMargin,Hangover) %[NOISEFLAG, SPEECHFLAG, NOISECOUNTER, DIST]=vad(SIGNAL,NOISE,NOISECOUNTER,NOISEMARGIN,HANGOVER) %Spectral Distance Voice Activity Detector %SIGNAL is the the current frames magnitude spectrum which is to labeld as %noise or speech, NOISE is noise magnitude spectrum template (estimation), %NOISECOUNTER is the number of imediate previous noise frames, NOISEMARGIN %(default 3)is the spectral distance threshold. HANGOVER ( default 8 )is %the number of noise segments after which the SPEECHFLAG is reset (goes to %zero). NOISEFLAG is set to one if the the segment is labeld as noise %NOISECOUNTER returns the number of previous noise segments, this value is %reset (to zero) whenever a speech segment is detected. DIST is the spectral distance. % %Saeed Vaseghi %edited by Esfandiar Zavarehei %Sep-04 if nargin<4 NoiseMargin=2; end if nargin<5 Hangover=8; end if nargin<3 NoiseCounter=0; end FreqResol=length(signal);

SSBoll79.m SpectralDist= 20*(log10(signal)-log10(noise)); % ??? SpectralDist(find(SpectralDist<0))=0; Dist=mean(SpectralDist); %DIST is the spectral distance. if (Dist < NoiseMargin) NoiseFlag=1; NoiseCounter=NoiseCounter+1; else NoiseFlag=0; NoiseCounter=0; end

5/9/2012

% Detect noise only periods and attenuate the signal if (NoiseCounter > Hangover) % HANGOVER (default 8)is the number of noise segments % after which the SPEECHFLAG is reset (goes to zero) SpeechFlag=0; else SpeechFlag=1; end %%%%%%%%% SEGMENT %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% function Seg=segment(signal,W,SP,Window) % % % % % % % % % SEGMENT chops a signal to overlapping windowed segments A= SEGMENT(X,W,SP,WIN) returns a matrix which its columns are segmented and windowed frames of the input one dimentional signal, X. W is the number of samples per window, default value W=256. SP is the shift percentage, default value SP=0.4. WIN is the window that is multiplied by each segment and its length should be W. the default window is hamming window. 06-Sep-04 Esfandiar Zavarehei

if nargin<3 SP=.4; end if nargin<2 W=256; end if nargin<4 Window=hamming(W); end Window=Window(:); %make it a column vector L=length(signal); SP=fix(W.*SP); N=fix((L-W)/SP +1); %number of segments % repmat: replicate and tile array. Index=(repmat(1:W,N,1)+repmat((0:(N-1))'*SP,1,W))'; %Indextemp=(repmat(1:W,N,1)+ repmat((0:(N-1))))'; hw=repmat(Window,1,N); Seg=signal(Index).*hw;