AudioDataTutorial.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Audio Tutorial using Scipy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Audio channels can be separated into multiple locatities to give the impression on the viewer of a two or three dimensional space. For instance, most cars have multiple speakers to surround the passengers with sound. This reduces listening fatigue and makes for a more immersive experience. In machine learning, it can be useful to separate audio files into multiple channels so they can be more useful features for locating labels more closely tied to a certain channel. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Adapted from https://publish.illinois.edu/augmentedlistening/tutorials/music-processing/tutorial-1-introduction-to-audio-processing-in-python/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install jupyterthemes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install wavio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from scipy.io.wavfile import read, write\n",
    "from IPython.display import Audio\n",
    "from jupyterthemes import jtplot\n",
    "import wavio\n",
    "\n",
    "jtplot.style()\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Download Multichannel .wav file"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Download audio file *6_Channel_ID.wav* from http://www-mmsp.ece.mcgill.ca/Documents/AudioFormats/WAVE/Samples/Microsoft/6_Channel_ID.wav"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "\n",
    "url = 'http://www.mmsp.ece.mcgill.ca/Documents/AudioFormats/WAVE/Samples/Microsoft/6_Channel_ID.wav'\n",
    "file='6_Channel_ID.wav'\n",
    "r = requests.get(url, allow_redirects=True)\n",
    "open(file, 'wb').write(r.content)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Read file and split channels"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Read .wav file and print frequency"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "Fs, data = read('6_Channel_ID.wav')\n",
    "print(\"Sampling Frequency is\", Fs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Listen to full audio file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Audio('6_Channel_ID.wav')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Split audio channels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "FL = data[:,0]\n",
    "FR = data[:,1]\n",
    "C = data[:,2]\n",
    "LF = data[:,3]\n",
    "BL = data[:,4]\n",
    "BR = data[:,5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Play audio in Notebook"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Front Left**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Audio(FL, rate=Fs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Front Right**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "Audio(FR, rate=Fs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Center**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Audio(C, rate=Fs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Low-frequency effects**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Audio(LF, rate=Fs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Back Left**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Audio(BL, rate=Fs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Back Right**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Audio(BR, rate=Fs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plot the Wave form"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure()\n",
    "plt.plot(data)\n",
    "plt.xlabel('Sample Index')\n",
    "plt.ylabel('Amplitude')\n",
    "plt.title('Waveform of Test Audio')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### References"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- http://www-mmsp.ece.mcgill.ca/Documents/AudioFormats/WAVE/Samples.html\n",
    "- https://publish.illinois.edu/augmentedlistening/tutorials/music-processing/tutorial-1-introduction-to-audio-processing-in-python/"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}