{
 "metadata": {
  "name": "",
  "signature": "sha256:ffe9bd0d88be9549f042be42f3735f37a986bd220bfce8d245bb081f638cf3f3"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Melody analysis - MusicBricks Tutorial"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "Introduction"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "This tutorial will guide you through some tools for Melody Analysis using the Essentia library (http://www.essentia.upf.edu). Melody analysis tools will extract a pitch curve from a monophonic or polyphonic audio recording [1]. It  outputs a time series (sequence of values) with the instantaneous pitch value (in Hertz) of the perceived melody. \n",
      "We provide two different operation modes: \n",
      "   1) using executable binaries; \n",
      "   2) Using Python wrappers.  \n",
      "   \n",
      "   \n",
      "References:\n",
      "\n",
      "[1] J. Salamon and E. G\u00f3mez, \"Melody extraction from polyphonic music signals using pitch contour characteristics,\" IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 6, pp. 1759\u20131770, 2012.   \n"
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "1-Using executable binaries"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "You can download the executable binaries for Linux (Ubuntu 14) and OSX in this link: http://tinyurl.com/melody-mbricks\n",
      "To execute the binaries you need to specify the input audio file and an output YAML file, where the melody values will be stored."
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Extracting melody from monophonic audio"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Locate an audio file to be processed in WAV format (input_audiofile)."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Usage: ./streaming_pitchyinfft input_audiofile output_yamlfile "
     ]
    },
    {
     "cell_type": "heading",
     "level": 4,
     "metadata": {},
     "source": [
      "Extracting melody from polyphonic audio"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Usage: ./streaming_predominantmelody input_audiofile output_yamlfile "
     ]
    },
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": [
      "2-Using Python wrappers"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "You should first install the Essentia library with Python bindings. Installation instructions are detailed here: http://essentia.upf.edu/documentation/installing.html . \n"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# import essentia in standard mode\n",
      "import essentia\n",
      "import essentia.standard\n",
      "from essentia.standard import *"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "After importing Essentia library, let's import other numerical and plotting tools"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# import matplotlib for plotting\n",
      "import matplotlib.pyplot as plt\n",
      "import numpy"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Load an audio file"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# create an audio loader and import audio file\n",
      "loader = essentia.standard.MonoLoader(filename = 'predom.wav', sampleRate = 44100)\n",
      "audio = loader()\n",
      "print(\"Duration of the audio sample [sec]:\")\n",
      "print(len(audio)/44100.0)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Duration of the audio sample [sec]:\n",
        "14.2285941043\n"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Extract the pitch curve from the audio example"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# PitchMelodia takes the entire audio signal as input - no frame-wise processing is required here...\n",
      "pExt = PredominantPitchMelodia(frameSize = 2048, hopSize = 128)\n",
      "pitch, pitchConf = pExt(audio)\n",
      "time=numpy.linspace(0.0,len(audio)/44100.0,len(pitch) )"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Plot extracted pitch contour"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# plot the pitch contour and confidence over time\n",
      "f, axarr = plt.subplots(2, sharex=True)\n",
      "axarr[0].plot(time,pitch)\n",
      "axarr[0].set_title('estimated pitch[Hz]')\n",
      "axarr[1].plot(time,pitchConf)\n",
      "axarr[1].set_title('pitch confidence')\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "<img src=\"./figure_1.png\" width=\"600\">"
     ]
    }
   ],
   "metadata": {}
  }
 ]
}