Acoustic fingerprinting in research
Joren Six - IPEM, Ghent University - firstname.lastname@example.org
Presentation on: 0110.be/a/berlin
Applications of acoustic fingerprinting
||The daughter Mandega
||Shona / Zezuru
Improve listening experiences
- 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
- 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
Might be patented.
- Audio decoded via ffmpeg
- Constant-Q based - using TarsosDSP
- MapDB storage
- Portable Java
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- Code remains unpublished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
A case for reproducibility in MIR.
Replication of ‘a highly robust audio fingerprinting system’
- Checks described method (code or text)
- Checks evaluation (data and procedure)
- Checks 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