pitch detection music physics and the brain
play

Pitch Detection: Music, Physics, and the Brain Tom Goodman - PowerPoint PPT Presentation

Pitch Detection: Music, Physics, and the Brain Tom Goodman University of Birmingham Wednesday 30 th January 2018 Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 1 / 37 Contents Aim of Pitch Detection


  1. Pitch Detection: Music, Physics, and the Brain Tom Goodman University of Birmingham Wednesday 30 th January 2018 Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 1 / 37

  2. Contents Aim of Pitch Detection Historical Background A Little Music Theory Physics of Sound Proposed Real-Time Algorithm Future Considerations Biological Inspiration for the Future Fin. Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 2 / 37

  3. Background Aim Take in an acoustic musical signal, and output the notes present. Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 3 / 37

  4. Background Aim Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 4 / 37

  5. Background A Little History history Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 5 / 37

  6. Background Pythagoras & Early Music (c. 550BC) Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 6 / 37

  7. Background Helmholtz & the Rise of Psychoacoustics (1800s) Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 7 / 37

  8. Background Some Basic Music Theory Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 8 / 37

  9. Background Categorising Notes Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 9 / 37

  10. Background Categorising Notes Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 10 / 37

  11. Background Musical Notes Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 11 / 37

  12. Background Standing Waves Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 12 / 37

  13. Background Harmonics Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 13 / 37

  14. Background Implications Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 14 / 37

  15. Background Timbre Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 15 / 37

  16. Background The Fourier Transform Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 16 / 37

  17. Real-Time Algorithm Overview Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 17 / 37

  18. Real-Time Algorithm Assumption - No Undertones Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 18 / 37

  19. Real-Time Algorithm Clustering Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 19 / 37

  20. Real-Time Algorithm “Band-Pass” Filter Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 20 / 37

  21. Real-Time Algorithm Selection Loop & α -cutoff Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 21 / 37

  22. Real-Time Algorithm Notes Reduce Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 22 / 37

  23. Real-Time Algorithm Testing Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 23 / 37

  24. Real-Time Algorithm Results Precision Recall Specificity Accuracy F-Score Test 1 78.09% 93.89% 83.00% 86.89% 84.78% Test 2 100.00% 97.22% 100.00% 97.85% 98.55% Test 3 82.46% 75.67% 77.52% 76.36% 78.85% Test 4 86.31% 82.50% 53.33% 75.83% 83.47% 65.08% 100.00% 64.29% 79.07% 78.47% Test 5 82.39% 89.86% 75.63% 83.20% 84.82% µ Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 24 / 37

  25. Real-Time Algorithm Further Considerations Adapt evaluation to use a larger & more widely-adopted dataset (eg. MAPS) Adapt ‘Notes Reduce’ to model harmonics on an instrument-to-instrument basis Apply source separation to reduce polyphonic problems to multiple monophonic problems Take temporal aspects of sound into account Take inspiration from biological systems for pitch detection in humans (such as the ear/brain) Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 25 / 37

  26. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 26 / 37

  27. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 27 / 37

  28. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 28 / 37

  29. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 29 / 37

  30. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 30 / 37

  31. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 31 / 37

  32. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 32 / 37

  33. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 33 / 37

  34. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 34 / 37

  35. Humans & Pitch Detection - A perfect solution? A Human Solution Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 35 / 37

  36. Humans & Pitch Detection - A perfect solution? Some Thoughts for the Future Do the ear and brain process monophonic and polyphonic signals in different ways? How does the brain subconsciously abstract timbre? Can we build models and solutions in similar ways? Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 36 / 37

  37. Humans & Pitch Detection - A perfect solution? Questions? Tom Goodman t.a.goodman@cs.bham.ac.uk http://tomg.io/ Office 218 School of Computer Science University of Birmingham Slides at http://tomg.io/research-skills-slides.pdf Paper at http://tomg/io/isspit-1.pdf Feel free to ask any questions! Wednesday 30 th January 2018 Tom Goodman (University of Birmingham) Research Skills 37 / 37

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend