Unsupervised Detection of Music Boundaries by Time Series Structure Features

@inproceedings{Serr2012UnsupervisedDO,
  title={Unsupervised Detection of Music Boundaries by Time Series Structure Features},
  author={Joan Serr{\`a} and Meinard Mueller and Peter Grosche and Josep Llu{\'i}s Arcos},
  booktitle={AAAI},
  year={2012}
}
Locating boundaries between coherent and/or repetitive segments of a time series is a challenging problem pervading many scientific domains. In this paper we propose an unsupervised method for boundary detection, combining three basic principles: novelty, homogeneity, and repetition. In particular, the method uses what we call structure features, a representation encapsulating both local and global properties of a time series. We demonstrate the usefulness of our approach in detecting music… CONTINUE READING

Similar Papers

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 49 CITATIONS

A multi-dimensional meter-adaptive method for automatic segmentation of music

  • 2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI)
  • 2015
VIEW 8 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Improving Music Structure Segmentation using lag-priors

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Multiple hypotheses at multiple scales for audio novelty computation within music

  • 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2013
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Learning to segment songs with ordinal linear discriminant analysis

  • 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Music segment similarity using 2D-Fourier Magnitude Coefficients

  • 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

SEGMENT SIMILARITY USING 2 D-FOURIER MAGNITUDE COEFFICIENTS

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Music Boundary Detection Based on a Hybrid Deep Model of Novelty, Homogeneity, Repetition and Duration

  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 30 REFERENCES

A comparison and evaluation of approaches to the automatic formal analysis of musical audio

J.B.L. Smith
  • MSc thesis, McGill University, Montreal, Canada.
  • 2010
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Smoothing Methods in Statistics

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Tonal Description of Polyphonic Audio for Music Content Processing

  • INFORMS Journal on Computing
  • 2006
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Signal Processing for Music Analysis

  • IEEE Journal of Selected Topics in Signal Processing
  • 2011
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Chroma Binary Similarity and Local Alignment Applied to Cover Song Identification

  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2008
VIEW 1 EXCERPT
HIGHLY INFLUENTIAL