Acoustic fingerprinting in research

Joren Six - IPEM, Ghent University -
Presentation on:
  1. Applications
  2. Implementation
  3. Reproducibility
  4. Conclusions

Applications of acoustic fingerprinting

Compare meta-data


First twin Second twin
Year recorded ? 1949
Title The daughter Mandega ?
People Zezuru Shona / Zezuru
Collector Hugh Tracey Hugh Tracey

Improve listening experiences

Re-use segmentation

Synchronize sensors

Synchronize sensors

Synchronize sensors

Implementation: Panako


  • Granular
  • 'Scalable'
  • Robust to speed changes

No systems were available (or described in academic literature).


  • Acoustic fingerprinting system
  • Apply in research
  • Research platform to experiment with fingerprinting algorithms


Is inspired on
  • Published Sazam algorithm
    • Granular
    • Scalable
  • A symbolic music fingerprinter by Andreas Artz
    • Robust against time-stretching
  • Sebastien Fenet's fingerprinter
    • Robust against pitch-shifting


  • Exact hashing
  • Aligned matches
  • False positives minimized
  • Reports pitch-shift and time-stretch percentages

Panako practical

  • Audio decoded via ffmpeg
  • Constant-Q based - using TarsosDSP
  • MapDB storage
  • Portable Java
Might be patented.

Computational research and reproducibility

Papers should be reproducibile.

Papers should be reproduced.


  • Code remains unpublished
  • Copyrighted material as test-data
  • Lack of incentives

Replicating a paper

  • Checks described method (code or text)
  • Checks evaluation (data and procedure)
  • Checks results

A case for reproducibility in MIR. Replication of ‘a highly robust audio fingerprinting system



Replication results

System behaves similar as original but differences are unexplained

  • Implementation bugs?
  • Evaluation (data or procedure)


  • Acoustic finterprinting techniques have many applications
  • Panako tries to offer a practical system
  • Reproducible methods catalyze research