linscaling.html

自动语音识别源码对非特定人的孤立词语音识别算法 进行研究。考虑到语音识别技术在嵌入式系统处理能力较弱、存储空间有限的问 题上进行算法的选择和优化

<ul style="list-style-image:url(../matlabicon.gif)">
<li><a href="#_sub1" class="code">function selfdemo</a></li></ul>
<h2><a name="_source"></a>SOURCE CODE <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2>
<div class="fragment"><pre>0001 <a name="_sub0" href="#_subfunctions" class="code">function [minDist1, shiftedPitch1, allDist1]=linScaling(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType)</a>
0002 <span class="comment">% linScaling: Linear scaling for melody recognition</span>
0003 <span class="comment">%    Usage: [minDist1, shiftedPitch1, allDist1]=linScaling(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType)</span>
0004 <span class="comment">%</span>
0005 <span class="comment">%    Example:</span>
0006 <span class="comment">%        inputPitch=[48.044247 48.917323 49.836778 50.154445 50.478049 50.807818 51.143991 51.486821 51.486821 51.486821 51.143991 50.154445 50.154445 50.154445 49.218415 51.143991 51.143991 50.807818 49.524836 49.524836 49.524836 49.524836 51.143991 51.143991 51.143991 51.486821 51.836577 50.807818 51.143991 52.558029 51.486821 51.486821 51.486821 51.143991 51.143991 51.143991 51.143991 51.143991 51.143991 51.143991 51.143991 51.143991 49.218415 50.807818 50.807818 50.154445 50.478049 48.044247 49.524836 52.193545 51.486821 51.486821 51.143991 50.807818 51.486821 51.486821 51.486821 51.486821 51.486821 55.788268 55.349958 54.922471 54.922471 55.349958 55.349958 55.349958 55.349958 55.349958 55.349958 55.349958 55.349958 53.699915 58.163541 59.213095 59.762739 59.762739 59.762739 59.762739 58.163541 57.661699 58.163541 58.680365 58.680365 58.680365 58.163541 55.788268 54.505286 55.349958 55.788268 55.788268 55.788268 54.922471 54.505286 56.237965 55.349958 55.349958 55.349958 55.349958 54.505286 54.505286 55.349958 48.917323 50.478049 50.807818 51.143991 51.143991 51.143991 50.807818 50.807818 50.478049 50.807818 51.486821 51.486821 51.486821 51.486821 51.486821 51.486821 52.558029 52.558029 52.558029 52.558029 52.193545 51.836577 52.193545 53.310858 53.310858 53.310858 52.930351 52.930351 53.310858 52.930351 52.558029 52.193545 52.930351 53.310858 52.930351 51.836577 52.558029 53.699915 52.930351 52.930351 52.558029 52.930351 52.930351 52.558029 52.558029 52.558029 53.310858 53.310858 53.310858 53.310858 52.930351 52.930351 52.930351 52.558029 52.930351 52.930351 52.930351 52.930351 52.930351 52.930351 52.930351 53.310858 53.310858 53.310858 52.193545 52.193545 52.193545 54.097918 52.930351 52.930351 52.930351 52.930351 52.930351 51.143991 51.143991 51.143991 48.917323 49.524836 49.524836 49.836778 49.524836 48.917323 49.524836 49.218415 48.330408 48.330408 48.330408 48.330408 48.330408 49.524836 49.836778 53.310858 53.310858 53.310858 52.930351 52.930351 52.930351 53.310858 52.930351 52.930351 52.558029 52.558029 51.143991 52.930351 49.218415 49.836778 50.154445 49.836778 49.524836 48.621378 48.621378 48.621378 49.836778 49.836778 49.836778 49.836778 46.680365 46.680365 46.680365 46.163541 45.661699 45.661699 45.910801 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 50.807818 51.486821 51.486821 51.143991];</span>
0007 <span class="comment">%        stdPitch =[60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000];</span>
0008 <span class="comment">%        resolution=21;</span>
0009 <span class="comment">%        lowerRatio=0.5;</span>
0010 <span class="comment">%        upperRatio=1.5;</span>
0011 <span class="comment">%        distanceType=1;        % L1-norm</span>
0012 <span class="comment">%        [minDist1, shiftedPitch1, allDist1]=linScaling(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType);</span>
0013 <span class="comment">%        distanceType=2;        % L2-norm</span>
0014 <span class="comment">%        [minDist1, shiftedPitch2, allDist2]=linScaling(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType);</span>
0015 <span class="comment">%        allDist2=sqrt(allDist2);    % To reduce computation, the L2-distance returned by linScaling is actually the square distance, so we need to take the square root.</span>
0016 <span class="comment">%        axisLimit=[0 370 40 80];</span>
0017 <span class="comment">%        subplot(3,1,1);</span>
0018 <span class="comment">%        plot(inputPitch); title('Input pitch'); ylabel('Semitones');</span>
0019 <span class="comment">%        axis(axisLimit);</span>
0020 <span class="comment">%        subplot(3,1,2);</span>
0021 <span class="comment">%        plot(1:length(shiftedPitch1), shiftedPitch1, 1:length(shiftedPitch2), shiftedPitch2, 1:length(stdPitch), stdPitch);</span>
0022 <span class="comment">%        title('Standard and shifted pitch'); ylabel('Semitones');</span>
0023 <span class="comment">%        axis(axisLimit);</span>
0024 <span class="comment">%        subplot(3,1,3);</span>
0025 <span class="comment">%        ratio=linspace(lowerRatio, upperRatio, resolution);</span>
0026 <span class="comment">%        plot(ratio, allDist1, '.-', ratio, allDist2, '.-');</span>
0027 <span class="comment">%        xlabel('Scaling ratios');</span>
0028 <span class="comment">%        ylabel('Distances');</span>
0029 <span class="comment">%        title('Normalized distance via L_1 &amp; L_2 norm');</span>
0030 <span class="comment">%        legend('L_1 norm', 'L_2 norm');</span>
0031 
0032 <span class="comment">%    Roger Jang, 20070531</span>
0033 
0034 <span class="keyword">if</span> nargin&lt;1, <a href="#_sub1" class="code" title="subfunction selfdemo">selfdemo</a>; <span class="keyword">return</span>; <span class="keyword">end</span>
0035 [minDist1, shiftedPitch1, allDist1]=linScalingMex(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType);
0036 
0037 <span class="comment">% ====== Self demo</span>
0038 <a name="_sub1" href="#_subfunctions" class="code">function selfdemo</a>
0039 inputPitch=[48.044247 48.917323 49.836778 50.154445 50.478049 50.807818 51.143991 51.486821 51.486821 51.486821 51.143991 50.154445 50.154445 50.154445 49.218415 51.143991 51.143991 50.807818 49.524836 49.524836 49.524836 49.524836 51.143991 51.143991 51.143991 51.486821 51.836577 50.807818 51.143991 52.558029 51.486821 51.486821 51.486821 51.143991 51.143991 51.143991 51.143991 51.143991 51.143991 51.143991 51.143991 51.143991 49.218415 50.807818 50.807818 50.154445 50.478049 48.044247 49.524836 52.193545 51.486821 51.486821 51.143991 50.807818 51.486821 51.486821 51.486821 51.486821 51.486821 55.788268 55.349958 54.922471 54.922471 55.349958 55.349958 55.349958 55.349958 55.349958 55.349958 55.349958 55.349958 53.699915 58.163541 59.213095 59.762739 59.762739 59.762739 59.762739 58.163541 57.661699 58.163541 58.680365 58.680365 58.680365 58.163541 55.788268 54.505286 55.349958 55.788268 55.788268 55.788268 54.922471 54.505286 56.237965 55.349958 55.349958 55.349958 55.349958 54.505286 54.505286 55.349958 48.917323 50.478049 50.807818 51.143991 51.143991 51.143991 50.807818 50.807818 50.478049 50.807818 51.486821 51.486821 51.486821 51.486821 51.486821 51.486821 52.558029 52.558029 52.558029 52.558029 52.193545 51.836577 52.193545 53.310858 53.310858 53.310858 52.930351 52.930351 53.310858 52.930351 52.558029 52.193545 52.930351 53.310858 52.930351 51.836577 52.558029 53.699915 52.930351 52.930351 52.558029 52.930351 52.930351 52.558029 52.558029 52.558029 53.310858 53.310858 53.310858 53.310858 52.930351 52.930351 52.930351 52.558029 52.930351 52.930351 52.930351 52.930351 52.930351 52.930351 52.930351 53.310858 53.310858 53.310858 52.193545 52.193545 52.193545 54.097918 52.930351 52.930351 52.930351 52.930351 52.930351 51.143991 51.143991 51.143991 48.917323 49.524836 49.524836 49.836778 49.524836 48.917323 49.524836 49.218415 48.330408 48.330408 48.330408 48.330408 48.330408 49.524836 49.836778 53.310858 53.310858 53.310858 52.930351 52.930351 52.930351 53.310858 52.930351 52.930351 52.558029 52.558029 51.143991 52.930351 49.218415 49.836778 50.154445 49.836778 49.524836 48.621378 48.621378 48.621378 49.836778 49.836778 49.836778 49.836778 46.680365 46.680365 46.680365 46.163541 45.661699 45.661699 45.910801 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 46.163541 50.807818 51.486821 51.486821 51.143991];
0040 stdPitch =[60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 59.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 55.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 67.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 65.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 64.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 62.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000 60.000000];
0041 resolution=21;
0042 lowerRatio=0.5;
0043 upperRatio=1.5;
0044 distanceType=1;        <span class="comment">% L1-norm</span>
0045 [minDist1, shiftedPitch1, allDist1]=<a href="linScaling.html" class="code" title="function [minDist1, shiftedPitch1, allDist1]=linScaling(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType)">linScaling</a>(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType);
0046 distanceType=2;        <span class="comment">% L2-norm</span>
0047 [minDist1, shiftedPitch2, allDist2]=<a href="linScaling.html" class="code" title="function [minDist1, shiftedPitch1, allDist1]=linScaling(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType)">linScaling</a>(inputPitch, stdPitch, lowerRatio, upperRatio, resolution, distanceType);
0048 allDist2=sqrt(allDist2);    <span class="comment">% To reduce computation, the L2-distance returned by linScaling is actually the square distance, so we need to take the square root.</span>
0049 axisLimit=[0 370 40 80];
0050 subplot(3,1,1);
0051 plot(inputPitch); title(<span class="string">'Input pitch'</span>); ylabel(<span class="string">'Semitones'</span>);
0052 axis(axisLimit);
0053 subplot(3,1,2);
0054 plot(1:length(shiftedPitch1), shiftedPitch1, 1:length(shiftedPitch2), shiftedPitch2, 1:length(stdPitch), stdPitch);
0055 title(<span class="string">'Standard and shifted pitch'</span>); ylabel(<span class="string">'Semitones'</span>);
0056 axis(axisLimit);
0057 subplot(3,1,3);
0058 ratio=linspace(lowerRatio, upperRatio, resolution);
0059 plot(ratio, allDist1, <span class="string">'.-'</span>, ratio, allDist2, <span class="string">'.-'</span>);
0060 xlabel(<span class="string">'Scaling ratios'</span>);
0061 ylabel(<span class="string">'Distances'</span>);
0062 title(<span class="string">'Normalized distance via L_1 &amp; L_2 norm'</span>);
0063 legend(<span class="string">'L_1 norm'</span>, <span class="string">'L_2 norm'</span>);</pre></div>
<hr><address>Generated on Thu 30-Oct-2008 12:52:18 by <strong><a href="http://www.artefact.tk/software/matlab/m2html/">m2html</a></strong> &copy; 2003</address>
</body>
</html>