Added feature extraction to audio preprocessing

audio_preprocessing.ipynb

@@ -43,6 +43,53 @@
     "\n",
     "wavfilehelper = WavFileHelper()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def extract_features(file_name):\n",
+    "   \n",
+    "    try:\n",
+    "        audio_y, sample_rate = librosa.load(file_name, res_type='kaiser_best') \n",
+    "        D = (librosa.stft(audio_y, center=False, n_fft=1024))\n",
+    "        #print(D)\n",
+    "        real = np.real(D)\n",
+    "        imag = np.imag(D)\n",
+    "        D_true = np.stack([real, imag], -1)\n",
+    "        \n",
+    "        #print(D_true.shape)\n",
+    "        if(D_true.shape != (513, 341, 2)):\n",
+    "            #print(\"ALERTTT\")\n",
+    "            #print(D_true)\n",
+    "            num_of_times_to_repeat = math.ceil(341 / D_true.shape[1])\n",
+    "            D_true = np.repeat(D_true, num_of_times_to_repeat, axis=1)\n",
+    "            D_true = D_true[:, 0:341, :]\n",
+    "            #print(D_true.shape)\n",
+    "            #print(D_true)\n",
+    "        \n",
+    "        #result = np.zeros(b.shape)\n",
+    "\n",
+    "        \n",
+    "        #print(D_true.shape)\n",
+    "        \n",
+    "        #librosa.display.specshow(librosa.amplitude_to_db(D,\n",
+    "        #                                         ref=np.max),\n",
+    "        #                 y_axis='log', x_axis='time')\n",
+    "        #plt.title('Power spectrogram')\n",
+    "        #plt.colorbar(format='%+2.0f dB')\n",
+    "        #plt.tight_layout()\n",
+    "        #plt.show()\n",
+    "        \n",
+    "        \n",
+    "    except Exception as e:\n",
+    "        print(\"Error encountered while parsing file: \", file)\n",
+    "        return None \n",
+    "     \n",
+    "    return (D_true)"
+   ]
   }
  ],
  "metadata": {