Wolfram 语言™

基于频谱特性的音频聚类

用频谱特性查找音频对象列表中的聚类.

In[1]:=

a = ExampleData[{"Audio", "Drums"}, "Audio"]

Out[1]=

在瞬态处将录音分割.

In[2]:=

samples = Select[AudioSplit[a, FindPeaks[AudioLocalMeasurements[a, "Novelty"]]["Times"]], Duration@# > Quantity[50, "ms"] &]; samples = Audio[#, Appearance -> "Minimal"] & /@ samples

Out[2]=

在由其频谱质心和扩频定义的位置处绘制结果采样.

In[3]:=

ListPlot[Partition[ AudioMeasurements[#, {"SpectralCentroid", "SpectralSpread"}, "List"] & /@ samples, 1], PlotMarkers -> (Audio[#, Appearance -> "Minimal"] & /@ samples), AxesLabel -> {Style["Centroid", Italic], Style["Spread", Italic]}, ImageSize -> Medium]

Out[3]=

用 "SpectralCentroid" 和 "SpectralSpread" 度量找出相同音频.

In[4]:=

FindClusters[ AudioMeasurements[#, {"SpectralCentroid", "SpectralSpread"}, "List"] & /@ samples -> samples]

Out[4]=