Updated notebook to 20*12 values.

Author: schuler-henry

code/feature_extraction/__pycache__/LPCExtractor.cpython-310.pyc

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -26,19 +26,20 @@
     "    return a[p], b[p]\n",
     "        \n",
     "def get_data_set(count, speakers):\n",
-    "    third = int(count/speakers)\n",
+    "    nn_input_chunks_per_speaker = int(count/speakers)\n",
     "    X = np.zeros((count, 12*20))\n",
     "    y = np.zeros(count, dtype='uint8')\n",
     "    \n",
-    "    coefficients_per_speaker = third * 20\n",
+    "    frames_per_speaker = nn_input_chunks_per_speaker * 20\n",
     "    \n",
     "    all_speakers = []\n",
+    "    \n",
     "    for i in range(0, speakers):\n",
     "        all_speakers.append([])\n",
     "        index = 0\n",
-    "        while (len(all_speakers[i]) < coefficients_per_speaker):\n",
+    "        while (len(all_speakers[i]) < frames_per_speaker):\n",
     "            print(index, end=\"\\r\")\n",
-    "            y_, sr = Utils.load_file(f\"C:\\\\Users\\\\SCU8BH\\\\Documents\\\\T3000\\\\Studienarbeit\\\\Data\\\\50_speakers_audio_data\\\\Speaker{i+30:04}\\\\Speaker{i+30:02}_{index:03}.wav\")\n",
+    "            y_, sr = Utils.load_file(f\"/home/henry/Downloads/archive/50_speakers_audio_data/Speaker_{10+i:04}/Speaker_{10+i:04}_{index:05}.wav\")\n",
     "        \n",
     "            y_ = AudioPreprocessor.remove_noise(y=y_, sr=sr)\n",
     "            y_ = AudioPreprocessor.remove_silence(y=y_)\n",
@@ -54,8 +55,8 @@
     "        print()\n",
     "    \n",
     "    for i in range(0, speakers):\n",
-    "        for j in range(0, third):\n",
-    "            X[i*third + j] = np.concatenate((all_speakers[i][20*j][1:13], \n",
+    "        for j in range(0, nn_input_chunks_per_speaker):\n",
+    "            X[i*nn_input_chunks_per_speaker + j] = np.concatenate((all_speakers[i][20*j][1:13], \n",
     "                                           all_speakers[i][20*j+1][1:13], \n",
     "                                           all_speakers[i][20*j+2][1:13],\n",
     "                                           all_speakers[i][20*j+3][1:13],\n",
@@ -76,25 +77,25 @@
     "                                           all_speakers[i][20*j+18][1:13],\n",
     "                                           all_speakers[i][20*j+19][1:13]\n",
     "                                         ))\n",
-    "            y[i*third + j] = i\n",
+    "            y[i*nn_input_chunks_per_speaker + j] = i\n",
     "            \n",
     "    return X, y"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "8\n",
-      "11\n",
+      "9\n",
       "9\n",
       "10\n",
-      "10\n"
+      "9\n"
      ]
     }
    ],
@@ -106,28 +107,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "[0 0 0 ... 4 4 4]\n",
-      "[4 2 3 ... 2 2 4]\n",
-      "29/29 [==============================] - 0s 1ms/step - loss: 2.1533e-05 - accuracy: 1.0000\n",
-      "Test accuracy: 1.0\n",
-      "Test loss: 2.1533451217692345e-05\n",
-      "4/4 [==============================] - 0s 1ms/step\n",
-      "[4 2 2 2 2 2 2 2 2 2 2 2 1 4 2 2 1 1 1 1 2 2 4 2 1 2 2 2 2 2 2 4 2 2 2 2 2\n",
-      " 2 2 2 2 2 2 2 2 2 2 2 0 2 2 2 2 4 1 2 2 2 2 2 1 2 3 1 1 2 2 2 4 2 4 2 2 2\n",
-      " 2 2 2 2 4 1 0 2 4 2 4 2 4 2 1 2 4 2 3 3 2 2 2 2 2 2 2 4 3 4 1 0 2 1 2 2 4\n",
-      " 2 2 4 2 2 0 0 0]\n",
-      "6\n",
-      "14\n",
-      "79\n",
-      "4\n",
-      "16\n"
+      "[2 3 2 ... 0 4 2]\n",
+      "29/29 [==============================] - 0s 1ms/step - loss: 0.8353 - accuracy: 0.6485\n",
+      "Test accuracy: 0.6484715938568115\n",
+      "Test loss: 0.8353310227394104\n",
+      "4/4 [==============================] - 0s 2ms/step\n",
+      "[2 4 2 4 4 4 4 4 2 4 0 2 2 2 1 2 2 4 2 3 4 4 3 4 2 2 3 3 2 2 2 4 4 2 3 4 4\n",
+      " 0 4 0 2 4 2 4 4 4 4 4 2 3 0 2 2 4 2 2 4 2 0 2 4 2 2 4 4 2 0 4 2 2 4 4 2 2\n",
+      " 3 0 2 4 3 2 2 2 4 2 2 0 4 0 3 4 3 2 2 0 4 2 0 2 2 4 3 2 2 4 2 0 2 2 2 4 4\n",
+      " 2 2 2 2 2 2 4]\n",
+      "12\n",
+      "1\n",
+      "54\n",
+      "11\n",
+      "40\n"
      ]
     }
    ],
@@ -154,7 +155,7 @@
     "    print(f\"Test loss: {test_loss}\")\n",
     "    \n",
     "    \n",
-    "    y_, sr = Utils.load_file(f\"C:\\\\Users\\\\SCU8BH\\\\Documents\\\\T3000\\\\Studienarbeit\\\\Data\\\\50_speakers_audio_data\\\\Speaker0032\\\\Speaker32_012.wav\")\n",
+    "    y_, sr = Utils.load_file(f\"/home/henry/Downloads/archive/50_speakers_audio_data/Speaker_0014/Speaker_0014_00020.wav\")\n",
     "        \n",
     "    y_ = AudioPreprocessor.remove_noise(y=y_, sr=sr)\n",
     "    y_ = AudioPreprocessor.remove_silence(y=y_)\n",
@@ -207,7 +208,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.10.4 64-bit",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -221,12 +222,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]"
   },
   "orig_nbformat": 4,
   "vscode": {
    "interpreter": {
-    "hash": "2fc4d7ba6602d69fe52dcf13f0361bb9556610661c910f56182baab83bdef03f"
+    "hash": "916dbcbb3f70747c44a77c7bcd40155683ae19c65e1c03b4aa3499c5328201f1"
    }
   }
  },