% Performance evaluation

load speakerData.mat
sidPrm=sidPrmSet;

sentenceNum=length([speakerData2.sentence]);
for p=1:length(speakerData1)
	for q=1:length(speakerData1(p).sentence)
		speakerData1(p).sentence(q).dsInput=[];
		speakerData1(p).sentence(q).dsOutput=[];
	end
end
DS.input=[];
DS.output=[];

% ====== Speaker ID by dtw1, dtw2, distLinScaling
for i=1:length(speakerData2)
	tInit=clock;
	name=speakerData2(i).name;
	fprintf('%d/%d: speaker=%s\n', i, length(speakerData2), name);
	for j=1:length(speakerData2(i).sentence)
	%	fprintf('\tsentence=%d ==> ', j);
	%	t0=clock;
		inputSentence=speakerData2(i).sentence(j);
		for p=1:length(speakerData1)
			for q=1:length(speakerData1(p).sentence)
				% === Collect DS.input
				k=size(speakerData1(p).sentence(q).dsInput, 2)+1;
				speakerData1(p).sentence(q).dsInput(1, k)=dtw1(inputSentence.fea, speakerData1(p).sentence(q).fea, 1, 1);
				speakerData1(p).sentence(q).dsInput(2, k)=dtw2(inputSentence.fea, speakerData1(p).sentence(q).fea, 1, 1);
				speakerData1(p).sentence(q).dsInput(3, k)=distLinScaling(inputSentence.fea, speakerData1(p).sentence(q).fea);
			%	speakerData1(p).sentence(q).dsInput(4, k)=dtw1(inputSentence.vol, speakerData1(p).sentence(q).vol, 1, 1);
			%	speakerData1(p).sentence(q).dsInput(5, k)=dtw2(inputSentence.vol, speakerData1(p).sentence(q).vol, 1, 1);
			%	speakerData1(p).sentence(q).dsInput(6, k)=distLinScaling(inputSentence.vol, speakerData1(p).sentence(q).vol);
				% === Collect DS.output
				speakerData1(p).sentence(q).dsOutput(1, k)=1+strcmp(speakerData2(i).sentence(j).text, speakerData1(p).sentence(q).text);
			%	fprintf('q=%d, text1=%s, text2=%s, output=%d\n', q, speakerData2(i).sentence(j).text, speakerData1(p).sentence(q).text, speakerData1(p).sentence(q).dsOutput(1, k)); pause
			end
		end
	%	fprintf(' Name = %s, ave. time = %.2f sec\n', speakerData2(i).name, etime(clock, t0)/length(speakerData2(i).sentence));
	end
%	speakerData2(i).correct=[speakerData2(i).sentence.correct];
%	speakerData2(i).rr=sum(speakerData2(i).correct)/length(speakerData2(i).correct);
%	fprintf('\tAve. time = %.2f sec\n', etime(clock, tInit)/length(speakerData2(i).sentence));
end

allSentences=[speakerData1.sentence];
DS.input=cat(2, allSentences.dsInput);
DS.output=cat(2, allSentences.dsOutput);

DS.input(DS.input>2e9)=inf;
index1=find(isinf(DS.input(1,:)));
index2=find(isinf(DS.input(2,:)));
index=union(index1, index2);
DS.input(:,index)=[];
DS.output(:, index)=[];
%dsScatterPlot(DS);
%dsClassSize(DS, 1);
fprintf('Saving DS.mat...\n');
save DS DS

return

% ====== Linear classifier
trainPrm=lincTrainPrmSet('method', 'batchLearning', 'animation', 'yes', 'printInterval', 30);
[coef, recogRate]=lincTrain(DS, trainPrm);
fprintf('Recog. rate = %.2f%%\n', 100*recogRate);


% ====== GMM classifier
TS=DS;
DS.input(:, 2:2:end)=[];
DS.output(:,2:2:end)=[];
TS.input(:, 1:2:end)=[];
TS.output(:,1:2:end)=[];
[DS.input, mu, sigma]=inputNormalize(DS.input);		% Input normalization for DS
TS.input=inputNormalize(TS.input, mu, sigma);	% Input normalization for TS
count1=dsClassSize(DS); count2=dsClassSize(TS);
vecOfGaussianNum=1:min([count1, count2]);
covType=1;
gmmTrainPrm=gmmTrainPrmSet; gmmTrainPrm.plotOpt=1;
[gmmData, recogRate1, recogRate2]=gmmcTrainEvalWrtGaussianNum(DS, TS, vecOfGaussianNum, covType, gmmTrainPrm);