Content-Based Music Structure Analysis Using Vector Quantization

Tsipas N, Vrysis L, Dimoulas CA, Papanikolaou G. Content-Based Music Structure Analysis Using Vector Quantization. In: AES Convention 138. Audio Engineering Society; 2015. Paper 9269. Available from: https://aes.org/publications/elibrary-page/?id=17693

@inproceedings{Tsipas2015_17693,
  author = {Tsipas, Nikolaos and Vrysis, Lazaros and Dimoulas, Charalampos A. and Papanikolaou, George},
  title = {{Content-Based Music Structure Analysis Using Vector Quantization}},
  booktitle = {AES Convention 138},
  note = {Paper 9269},
  year = {2015},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17693}
}

TY  - CPAPER
TI  - Content-Based Music Structure Analysis Using Vector Quantization
AU  - Tsipas, Nikolaos
AU  - Vrysis, Lazaros
AU  - Dimoulas, Charalampos A.
AU  - Papanikolaou, George
T2  - AES Convention 138
M1  - Paper 9269
PY  - 2015
DA  - 2015/05/06
UR  - https://aes.org/publications/elibrary-page/?id=17693
PB  - Audio Engineering Society
LA  - en
AB  - Music structure analysis has been one of the challenging problems in the field of music information retrieval during the last decade. Past years advances in the field have contributed toward the establishment and standardization of a framework covering repetition, homogeneity, and novelty based approaches. With this paper an optimized fusion algorithm for transition points detection in musical pieces is proposed, as an extension to existing state-of-the-art techniques. Vector-Quantization is introduced as an adaptive filtering mechanism for time-lag matrices while a structure-features based self-similarity matrix is proposed for novelty detection. The method is evaluated against 124 pop songs from the INRIA Eurovision dataset and performance results are presented in comparison with existing state-of-the-art implementations for music structure analysis.
ER  -