{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy, scipy, librosa, IPython.display"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[← Back to Index](index.html)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pitch Transcription Exercise"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Load an audio file."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"x, fs = librosa.load('zigeunerweisen.wav')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Play the audio file."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"IPython.display.Audio(x, rate=fs)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Goal**: to identify the pitch of each note and replace each note with a pure tone of that pitch."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Detect onsets:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"def get_onset_times(x, fs):\n",
" onset_frames = librosa.onset.onset_detect(x, fs)\n",
" return librosa.frames_to_time(onset_frames, fs)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Estimate pitch using the autocorrelation method:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def estimate_pitch(segment, fs, fmin=50.0, fmax=2000.0):\n",
" i_min = fs/fmax\n",
" i_max = fs/fmin\n",
" r = librosa.autocorrelate(segment)\n",
" r[:i_min] = 0\n",
" r[i_max:] = 0\n",
" i = r.argmax()\n",
" f0 = float(fs)/i\n",
" return f0"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Try it out on one frame:"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"196.875\n"
]
}
],
"source": [
"f0 = estimate_pitch(x[:2048], fs)\n",
"print f0"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Create a function to generate a pure tone at the specified frequency:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"def generate_sine(f0, fs, n_duration):\n",
" n = numpy.arange(n_duration)\n",
" return 0.2*numpy.sin(2*numpy.pi*f0*n/float(fs))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Finally, write a function that puts it all together:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"def transcribe_pitch(signal_in, fs):\n",
" \n",
" # initialize output signal\n",
" signal_out = numpy.zeros(len(signal_in))\n",
" \n",
" # get onsets\n",
" onsets = get_onset_times(signal_in, fs)\n",
" \n",
" # get pitches\n",
" for i in range(len(onsets)-1):\n",
" n0 = int(onsets[i]*fs)\n",
" n1 = int(onsets[i+1]*fs)\n",
" pitch = estimate_pitch(signal_in[n0:n1], fs, fmin=60, fmax=4000)\n",
" \n",
" signal_out[n0:n1] = generate_sine(pitch, fs, n1-n0)\n",
" \n",
" return signal_out\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Try it out on the input signal:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"signal_out = transcribe_pitch(x, fs)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Play the synthesized transcription."
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"IPython.display.Audio(signal_out, rate=fs)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[← Back to Index](index.html)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 0
}