Crowd sourcing for tempo estimation
Upcoming SlideShare
Loading in...5

Like this? Share it with your network


Crowd sourcing for tempo estimation



Slides for presentation at ISMIR 2011 of the paper "Improving perceptual tempo estimation with crowd-source annotations".

Slides for presentation at ISMIR 2011 of the paper "Improving perceptual tempo estimation with crowd-source annotations".



Total Views
Views on SlideShare
Embed Views



37 Embeds 1,169 484 247 101 57 51 23 20 17 15 15 14 14 14 12 11 8 8 6 6 6 5 5 5 4 3 3 2 2 2 2 1 1 1 1 1 1 1



Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
Post Comment
Edit your comment

Crowd sourcing for tempo estimation Presentation Transcript

  • 1. Improving perceptual tempo estimation with crowd-sourced annotations Mark Levy, 26 October 2011
  • 2. Tempo EstimationTerminology: tempo = beats per minute = bpm
  • 3. Tempo EstimationUse crowd-sourcing: quantify influence of metrical ambiguity on tempo perception improve evaluation improve algorithms
  • 4. Perceived TempoMetrical ambiguity: listeners don’t agree about bpm typically in two camps perceived values differ by factor of 2 or 3McKinney and Moelants: 24-40 subjects released experimental data
  • 5. Perceived Tempo Metrical ambiguity:listeners listeners bpm bpm McKinney and Moelants, 2004
  • 6. Machine-Estimated TempoAlso affected by metrical ambiguity: makes estimation difficult natural to see multiple bpm values estimated values often out by factor of 2 or 3 (“octave error”)
  • 7. Crowd SourcingWeb-based questionnaire: capture label choices capture bpm from mean tapping interval capture comparative judgements
  • 8. Crowd Sourcing
  • 9. Crowd Sourcing Music:  over 4000 songs  30-second clips• rock, country, pop, soul, funk and rnb, jazz, latin, reggae, disco, rap, punk, electronic, trance, industrial, house, folk, ...• recent releases back to 60s
  • 10. ResponseFirst week (reported/released): 4k tracks annotated by 2k listeners 20k labels and bpm estimatesTo date: 6k tracks annotated by 27k listeners 200k labels and bpm estimates
  • 11. Analysis: ambiguityWhen people tap to a song at different bpm do they really disagree about whether it’s slow or fast?Investigation: inspect labels from people who tap differently quantify disagreement for ambiguous songs
  • 12. Analysis: ambiguitySubset of slow/fast songs: labelled by at least five listeners majority label “slow” or “fast”
  • 13. Analysis: ambiguitybpm vs speed labelall estimates for slow/fast songs
  • 14. Analysis: ambiguitybpm vs speed label people can tap slowly to fast songsall estimates for slow/fast songs
  • 15. Analysis: ambiguityLabels for fast songs from slow-tappers
  • 16. Analysis: ambiguityQuantify disagreement over labels: model conflict, extremity of tempo conflict coefficient min(Ls , L f ) Ls Lf C max(Ls , L f ) L Ls, Lf, L: number of slow, fast, all labels for a song
  • 17. Analysis: ambiguityDistribution of conflict coefficient C C > 0 means slow and fastall songs with at least five labels
  • 18. Analysis: ambiguitySubset of metrically ambiguous songs: at least 30% of listeners tap at half/twice the majority estimateCompared to the rest: no significant difference in C
  • 19. Evaluation metricsMIREX: capture metrical ambiguity replicate human disagreementAmbiguity considered unhelpful: automatic playlisting DJ tools, production tools jogging
  • 20. Evaluation metricsApplication-oriented : compare with majority* human estimate (*median in most popular bin) categorise machine estimates  same as humans  twice as fast  twice as slow  three times as fast  and so on  unrelated to humans
  • 21. Analysis: evaluationSources: BPM List (DJ kit, human-moderated) Donny Brusca, 7th edition, 2011 EchoNest/MSD (closed-source algorithm) maybe Jehan et al,? VAMP (open-source algorithm) Davies and Landone, 2007-
  • 22. Analysis: machine vs human 80% 70% 60% 50% BPM List 40% VAMP 30% EchoNest 20% 10% 0% x2 same /2 unrelated other
  • 23. Analysis: controlled testControlled comparison: exploit experience from website A/B testing use this to improve algorithm iterativelyResult is independent of any quality metric
  • 24. Analysis: controlled testWhen visitor arrives at the page: choose a source S at random choose a bpm value at random choose two songs given that value by S display them togetherThen ask which sounds faster!
  • 25. Analysis: controlled testNull Hypothesis: there will be presentation effects listeners will attend to subtle differencesbut these effects are independent of the source of bpm estimates if the quality of the sources is the same
  • 26. Analysis: controlled test 100% 90% 80% 70% 60% 50% different 40% same 30% 20% 10% 0% BPM List VAMP EchoNest
  • 27. Analysis: improving estimatesAdjust bpm based on class: imagine an accurate slow/fast classifier Hockmann and Fujinaga, 2010 adjust as follows: bpm:= bpm/2 if slow and bpm > 100 bpm:= bpm*2 if fast and bpm < 100 otherwise don’t adjust simulation: accept majority human label
  • 28. Analysis: adjusted vs human 80% 70% 60% 50% BPM List 40% VAMP 30% EchoNest 20% 10% 0% x2 same /2 unrelated other
  • 29. ConclusionsCrowd sourcing: gather thousands of data points in a few days, half a million over time humans agree over slow/fast labels, even when they tap at different bpmImproving machine estimates: use controlled testing exploit a slow/fast classifier
  • 30. Thanks! @gamboviolhttp://mir-in-action.blogspot.com are looking for interns/research fellows!