Unsupervised learning and refinement of rhythmic patterns for beat and downbeat tracking. Krebs, F., Korzeniowski, F., Grachten, M., & Widmer, G. In 2014 22nd European Signal Processing Conference (EUSIPCO), pages 611-615, Sep., 2014.
Paper abstract bibtex In this paper, we propose a method of extracting rhythmic patterns from audio recordings to be used for training a probabilistic model for beat and downbeat extraction. The method comprises two stages: clustering and refinement. It is able to take advantage of any available annotations that are related to the metrical structure (e.g., beats, tempo, downbeats, dance style). Our evaluation on the Ballroom dataset showed that our unsupervised method achieves results comparable to those of a supervised model. On another dataset, the proposed method performs as well as one of two reference systems in the beat tracking task, and achieves better results in downbeat tracking.
@InProceedings{6952181,
author = {F. Krebs and F. Korzeniowski and M. Grachten and G. Widmer},
booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},
title = {Unsupervised learning and refinement of rhythmic patterns for beat and downbeat tracking},
year = {2014},
pages = {611-615},
abstract = {In this paper, we propose a method of extracting rhythmic patterns from audio recordings to be used for training a probabilistic model for beat and downbeat extraction. The method comprises two stages: clustering and refinement. It is able to take advantage of any available annotations that are related to the metrical structure (e.g., beats, tempo, downbeats, dance style). Our evaluation on the Ballroom dataset showed that our unsupervised method achieves results comparable to those of a supervised model. On another dataset, the proposed method performs as well as one of two reference systems in the beat tracking task, and achieves better results in downbeat tracking.},
keywords = {audio recording;hidden Markov models;learning (artificial intelligence);extracting rhythmic patterns;beat tracking;probabilistic model;Ballroom dataset;refinement;clustering;audio recordings;downbeat tracking;unsupervised learning;Hidden Markov models;Viterbi algorithm;Training;Measurement;Computational modeling;Maximum likelihood decoding;Rhythm;Hidden Markov model;Viterbi training;beat tracking;downbeat tracking;clustering},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569925187.pdf},
}
Downloads: 0
{"_id":"8Amd3ABFXtwwZeAMs","bibbaseid":"krebs-korzeniowski-grachten-widmer-unsupervisedlearningandrefinementofrhythmicpatternsforbeatanddownbeattracking-2014","authorIDs":[],"author_short":["Krebs, F.","Korzeniowski, F.","Grachten, M.","Widmer, G."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["F."],"propositions":[],"lastnames":["Krebs"],"suffixes":[]},{"firstnames":["F."],"propositions":[],"lastnames":["Korzeniowski"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Grachten"],"suffixes":[]},{"firstnames":["G."],"propositions":[],"lastnames":["Widmer"],"suffixes":[]}],"booktitle":"2014 22nd European Signal Processing Conference (EUSIPCO)","title":"Unsupervised learning and refinement of rhythmic patterns for beat and downbeat tracking","year":"2014","pages":"611-615","abstract":"In this paper, we propose a method of extracting rhythmic patterns from audio recordings to be used for training a probabilistic model for beat and downbeat extraction. The method comprises two stages: clustering and refinement. It is able to take advantage of any available annotations that are related to the metrical structure (e.g., beats, tempo, downbeats, dance style). Our evaluation on the Ballroom dataset showed that our unsupervised method achieves results comparable to those of a supervised model. On another dataset, the proposed method performs as well as one of two reference systems in the beat tracking task, and achieves better results in downbeat tracking.","keywords":"audio recording;hidden Markov models;learning (artificial intelligence);extracting rhythmic patterns;beat tracking;probabilistic model;Ballroom dataset;refinement;clustering;audio recordings;downbeat tracking;unsupervised learning;Hidden Markov models;Viterbi algorithm;Training;Measurement;Computational modeling;Maximum likelihood decoding;Rhythm;Hidden Markov model;Viterbi training;beat tracking;downbeat tracking;clustering","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569925187.pdf","bibtex":"@InProceedings{6952181,\n author = {F. Krebs and F. Korzeniowski and M. Grachten and G. Widmer},\n booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},\n title = {Unsupervised learning and refinement of rhythmic patterns for beat and downbeat tracking},\n year = {2014},\n pages = {611-615},\n abstract = {In this paper, we propose a method of extracting rhythmic patterns from audio recordings to be used for training a probabilistic model for beat and downbeat extraction. The method comprises two stages: clustering and refinement. It is able to take advantage of any available annotations that are related to the metrical structure (e.g., beats, tempo, downbeats, dance style). Our evaluation on the Ballroom dataset showed that our unsupervised method achieves results comparable to those of a supervised model. On another dataset, the proposed method performs as well as one of two reference systems in the beat tracking task, and achieves better results in downbeat tracking.},\n keywords = {audio recording;hidden Markov models;learning (artificial intelligence);extracting rhythmic patterns;beat tracking;probabilistic model;Ballroom dataset;refinement;clustering;audio recordings;downbeat tracking;unsupervised learning;Hidden Markov models;Viterbi algorithm;Training;Measurement;Computational modeling;Maximum likelihood decoding;Rhythm;Hidden Markov model;Viterbi training;beat tracking;downbeat tracking;clustering},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569925187.pdf},\n}\n\n","author_short":["Krebs, F.","Korzeniowski, F.","Grachten, M.","Widmer, G."],"key":"6952181","id":"6952181","bibbaseid":"krebs-korzeniowski-grachten-widmer-unsupervisedlearningandrefinementofrhythmicpatternsforbeatanddownbeattracking-2014","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569925187.pdf"},"keyword":["audio recording;hidden Markov models;learning (artificial intelligence);extracting rhythmic patterns;beat tracking;probabilistic model;Ballroom dataset;refinement;clustering;audio recordings;downbeat tracking;unsupervised learning;Hidden Markov models;Viterbi algorithm;Training;Measurement;Computational modeling;Maximum likelihood decoding;Rhythm;Hidden Markov model;Viterbi training;beat tracking;downbeat tracking;clustering"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2014url.bib","creationDate":"2021-02-13T17:43:41.623Z","downloads":0,"keywords":["audio recording;hidden markov models;learning (artificial intelligence);extracting rhythmic patterns;beat tracking;probabilistic model;ballroom dataset;refinement;clustering;audio recordings;downbeat tracking;unsupervised learning;hidden markov models;viterbi algorithm;training;measurement;computational modeling;maximum likelihood decoding;rhythm;hidden markov model;viterbi training;beat tracking;downbeat tracking;clustering"],"search_terms":["unsupervised","learning","refinement","rhythmic","patterns","beat","downbeat","tracking","krebs","korzeniowski","grachten","widmer"],"title":"Unsupervised learning and refinement of rhythmic patterns for beat and downbeat tracking","year":2014,"dataSources":["A2ezyFL6GG6na7bbs","oZFG3eQZPXnykPgnE"]}