In [1]:
import numpy, scipy, matplotlib.pyplot as plt, pandas, librosa
We will mainly use three libraries for audio acquisition and playback:
Introduced in IPython 2.0, IPython.display.Audio lets you play audio directly in an IPython notebook.
librosa is a Python package for music and audio processing by Brian McFee. A large portion was ported from Dan Ellis's Matlab audio processing examples.
Essentia is an open-source library for audio analysis and music information retrieval from the Music Technology Group at Universitat Pompeu Fabra. Although Essentia is written in C++, we will use the Python bindings for Essentia.
To download a file onto your local machine (or Vagrant box) in Python, you can use urllib.urlretrieve:
In [2]:
import urllib
urllib.urlretrieve(
'http://audio.musicinformationretrieval.com/simpleLoop.wav',
filename='simpleLoop.wav'
)
Out[2]:
To check that the file downloaded successfully, list the files in the working directory:
In [3]:
%ls *.wav
Visit https://ccrma.stanford.edu/workshops/mir2014/audio/ for more audio files.
If you only want to listen to, and not manipulate, a remote audio file, use IPython.display.Audio instead. (See Playing Audio.)
In [4]:
x, fs = librosa.load('simpleLoop.wav')
print x.shape
print fs
In [5]:
plt.plot(x)
Out[5]:
MonoLoader reads (and downmixes, if necessary) an audio file into a single channel (as will often be the case during this workshop). MonoLoader also resamples the audio to a sampling frequency of your choice (default = 44100 Hz):
In [6]:
from essentia.standard import MonoLoader
audio = MonoLoader(filename='simpleLoop.wav')()
audio.shape
Out[6]:
In [7]:
N = len(audio)
t = numpy.arange(0, N)/44100.0
plt.plot(t, audio)
plt.xlabel('Time (seconds)')
Out[7]:
For more control over the audio acquisition process, you may want to use AudioLoader instead.
Using IPython.display.Audio, you can play a local audio file or a remote audio file:
In [8]:
from IPython.display import Audio
# load a remote WAV file
Audio('https://ccrma.stanford.edu/workshops/mir2014/audio/CongaGroove-mono.wav')
Out[8]:
In [9]:
# load a local WAV file
Audio('simpleLoop.wav')
Out[9]:
Audio can also accept a NumPy array:
In [10]:
fs = 44100 # sampling frequency
T = 1.5 # seconds
t = numpy.linspace(0, T, int(T*fs), endpoint=False) # time variable
x = numpy.sin(2*numpy.pi*440*t) # pure sine wave at 440 Hz
# load a NumPy array
Audio(x, rate=fs)
Out[10]:
To play or record audio from the command line, we recommend SoX (included in the stanford-mir Vagrant box).
$ rec test.wav
$ play test.wavplot is the simplest way to plot time-domain signals:
In [11]:
T = 0.001 # seconds
fs = 44100 # sampling frequency
t = numpy.linspace(0, T, int(T*fs), endpoint=False) # time variable
x = numpy.sin(2*numpy.pi*3000*t)
# Plot a sine wave
plt.plot(t, x)
plt.xlabel('Time (seconds)')
Out[11]:
specgram is a Matplotlib tool for computing and displaying spectrograms.
In [12]:
S, freqs, bins, im = plt.specgram(x, NFFT=1024, Fs=fs, noverlap=512)
# Plot a spectrogram
plt.xlabel('Time')
plt.ylabel('Frequency')
Out[12]:
librosa.output.write_wav also saves a NumPy array to a WAV file. This is a bit easier to use.
In [13]:
noise = 0.1*scipy.randn(44100)
# Write an array to a wav file
librosa.output.write_wav('noise2.wav', noise, 44100)
%ls *.wav