In [1]:
import numpy, scipy, IPython.display as ipd

← Back to Index

Why Music Information Retrieval?

While you listen to these excerpts, name as many of its musical characteristics as you can:

In [2]:
ipd.display( ipd.YouTubeVideo("ajCYQL8ouqw") )

(Chords)

Another:

In [3]:
ipd.display( ipd.YouTubeVideo("PrVu9WKs498", start=8) )

One more:

In [4]:
ipd.display( ipd.YouTubeVideo("Cxj8vSS2ELU", start=540) )

What is MIR?

  • fingerprinting
  • cover song detection
  • genre recognition
  • transcription
  • recommendation
  • symbolic melodic similarity
  • mood
  • source separation
  • instrument recognition
  • pitch tracking
  • tempo estimation
  • score alignment
  • song structure/form
  • beat tracking
  • key detection
  • query by humming

Why MIR?

  • discover, organize, monetize media collections
  • search ("find me something that sounds like this") songs, loops, speech, environmental sounds, sound effects
  • workflows in consumer products through machine hearing
  • automatic control of software and mobile devices

Commercial Applications

Example: RiffStation

In [5]:
ipd.display( ipd.YouTubeVideo("ECvinPjmBVE", start=6) )

Example: Melodyne

In [6]:
ipd.display( ipd.YouTubeVideo("DiW6XVFeFgo", start=60))

Example: Auto-Tune

In [7]:
ipd.display( ipd.YouTubeVideo("YDjsoZKlG04", start=155))

Example: Key Detection and Auto-harmonization with iZotope Nectar 2

In [8]:
ipd.display( ipd.YouTubeVideo("TG-ivjyyYhM", start=35))

Example: Humtap

In [9]:
ipd.display( ipd.VimeoVideo("96140435") )

← Back to Index