<h1id="Homework-Part-2:-Genre-Classification">Homework Part 2: Genre Classification<aclass="anchor-link"href="#Homework-Part-2:-Genre-Classification">¶</a></h1>
<p><ahref="index.html">← Back to Index</a></p>
<p><strong>Repeat steps 1 and 2 for another audio file:</strong></p>
<h3id="Step-2b:-Repeat-steps-1-and-2-for-another-audio-file.">Step 2b: Repeat steps 1 and 2 for another audio file.<aclass="anchor-link"href="#Step-2b:-Repeat-steps-1-and-2-for-another-audio-file.">¶</a></h3>
<divclass=" highlight hl-ipython2"><pre><span></span><spanclass="c1"># Your code here. Load the second audio file in the same manner as the first audio file.</span>
<p>Plot the time-domain waveform and spectrogram of the second audio file. In what ways does the time-domain waveform look different than the first audio file? What differences in musical attributes might this reflect? What additional insights are gained from plotting the spectrogram? <strong>Explain.</strong></p>
<p>Plot the time-domain waveform and spectrogram of the second audio file. In what ways does the time-domain waveform look different than the first audio file? What differences in musical attributes might this reflect? What additional insights are gained from plotting the spectrogram? Explain.</p>
<p><strong>[Please share your answer in this editable text cell.]</strong></p>
<p>Extract MFCCs from the second audio file. Be sure to transpose the resulting matrix such that each row is one observation, i.e. one set of MFCCs. Also be sure that the shape and size of the resulting MFCC matrix is equivalent to that for the first audio file.</p>
<p>Extract MFCCs from the second audio file. Be sure to transpose the resulting matrix such that each row is one observation, i.e. one set of MFCCs. Also be sure that the shape and size of the resulting MFCC matrix is equivalent to that for the first audio file.</p>
<p>Create a new genre classifier by repeating the steps above, but this time use different features. Consult the <ahref="http://librosa.github.io/librosa/feature.html">librosa documentation on feature extraction</a> for different choices of features. Which features work well? not well?</p>
"# Your code here. Load the second audio file in the same manner as the first audio file."
"# Your code here. Load the second audio file in the same manner as the first audio file.\n",
"# x_busta, fs_busta = "
]
},
{
...
...
@@ -349,7 +365,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Plot the time-domain waveform and spectrogram of the second audio file. In what ways does the time-domain waveform look different than the first audio file? What differences in musical attributes might this reflect? What additional insights are gained from plotting the spectrogram? **Explain.**"
"Plot the time-domain waveform and spectrogram of the second audio file. In what ways does the time-domain waveform look different than the first audio file? What differences in musical attributes might this reflect? What additional insights are gained from plotting the spectrogram? Explain."
]
},
{
...
...
@@ -401,25 +417,30 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"**[Please share your answer in this editable text cell.]**"
"Extract MFCCs from the second audio file. Be sure to transpose the resulting matrix such that each row is one observation, i.e. one set of MFCCs. Also be sure that the shape and size of the resulting MFCC matrix is equivalent to that for the first audio file."
]
},
{
"cell_type": "markdown",
"metadata": {},
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"Extract MFCCs from the second audio file. Be sure to transpose the resulting matrix such that each row is one observation, i.e. one set of MFCCs. Also be sure that the shape and size of the resulting MFCC matrix is equivalent to that for the first audio file."
"**[Explain your answer in this editable text cell.]**"
"df_busta.corr()"
]
},
{
...
...
@@ -922,7 +941,7 @@
},
"outputs": [],
"source": [
"df1.plot.scatter?"
"df_brahms.plot.scatter?"
]
},
{
...
...
@@ -940,7 +959,7 @@
},
"outputs": [],
"source": [
"df2.plot.scatter?"
"df_busta.plot.scatter?"
]
},
{
...
...
@@ -958,7 +977,7 @@
},
"outputs": [],
"source": [
"df1[0].plot.hist()"
"df_brahms[0].plot.hist()"
]
},
{
...
...
@@ -969,7 +988,7 @@
},
"outputs": [],
"source": [
"df1[11].plot.hist()"
"df_busta[11].plot.hist()"
]
},
{
...
...
@@ -999,6 +1018,13 @@
"source": [
"Create a new genre classifier by repeating the steps above, but this time use different features. Consult the [librosa documentation on feature extraction](http://librosa.github.io/librosa/feature.html) for different choices of features. Which features work well? not well?"
