the extraction of structure from a musical piece
play

The Extraction of Structure from a Musical Piece Kasper.Souren @ - PowerPoint PPT Presentation

The Extraction of Structure from a Musical Piece Kasper.Souren @ ircam.fr http://www.ircam.fr/anasyn/souren/ Musical Structure related to human perception rather from the listener's standpoint than from the composer's standpoint Finding


  1. The Extraction of Structure from a Musical Piece Kasper.Souren @ ircam.fr http://www.ircam.fr/anasyn/souren/

  2. Musical Structure  related to human perception  rather from the listener's standpoint than from the composer's standpoint

  3. Finding structure  audio, no MIDI or symbolic information  audio descriptors  not (yet) limited to one style  looking for similarity and borders

  4. Most significant spectrum variations raw audio (11025 Hz) musical piece (ogg, wav, mp3)  log FFT power spectrogram log FFT spectrum band variation information EOF principal components most significant spectrum band variations

  5. Most significant spectrum variations frequency spectrogram 100 feature vectors per second PC of “log FFT” of frames from every band most significant spectrum band variations time about 1 feature vector per second

  6. EOF based on SVD  Empirical Orthogonal Functions, based on Singular Value Decomposition  popular in climate research  type of Principal Component Analysis  useful for reducing number of dimensions while explaining large part of variance

  7. Similarity matrix J. Foote, 1999 1) the audio descriptors are N-dimensional space 2) calculate mutual distances: distance matrix 3) rescale: similarity matrix

  8. Similarity matrix most significant spectrum variations time Similarity Matrix Chardonnay Says by Nood/Banana time time

  9. Finding similar parts step 1: calculate lag matrix similarity matrix lag matrix ` time time time delay time

  10. Finding similar parts step 2: apply 2D FIR filter to blur lag matrix blurred lag matrix time time delay time delay time

  11. Finding similar parts step 3: find vertical local maxima its local maxima blurred lag matrix (values from non-blurred matrix) time time delay time delay time

  12. Finding similar parts step 4: post-processing 0) forget first column (diagonal of similarity matrix) 1) localize sufficiently long contiguous parts 2) remove overlaps 3) remove diagonal parts local maxima similar parts

  13. Finding borders step 1: convolution, kernels of different sizes filtered matrices similarity matrix

  14. Finding borders step 2: diagonals => columns diagonals of filtered matrices filtered matrices time kernel size

  15. Finding borders step 3: find local maxima in columns diagonals of filtered matrices local maxima time

  16. Finding borders step 4: post-processing 1) localize contiguous parts 2) sum their values 3) throw away positions with too low values time 4) refine the positions using the spectrogram

  17. Structural Information Theory  formal calculus for Gestalt laws  focus on visual patterns  experimented with Genetic Programming  problem: need for much higher description, musical objects, thus source seperation, classification, ...

  18. Framework for Audio Analysis  functionality interesting for audio and music research  integrating research could be fruitful  finding musical structure  audio signal separation  sound classification  ...

  19. Python  scripting language, interpreted  object-oriented  flexible, extensible, easy to embed  modular  free software (BSD style license)

  20. FfAA modes  Scientific analysis environment  stand-alone application: QtFfAA  GUI + command line, object viewer, visualisation  Embeddable in free audio software  for audio editors and recorders  for music players, DJ tools

  21. FfAA right now  versatile interface  MDI GUI (PyQt)  commandline (IPython)  load and analyse sound files  database  visualisation  easily extensible

  22. The Extraction of Structure from a Musical Piece Kasper.Souren @ ircam.fr http://www.ircam.fr/anasyn/souren/

Recommend


More recommend