On the automatic identification of difficult examples for beat tracking: towards building new evaluation datasets

Holzapfel, André,1976-Sound and Music Computing Group, INESC TEC, Porto, Portugal (författare)

On the automatic identification of difficult examples for beat tracking : towards building new evaluation datasets

QC 20220202
In this paper, an approach is presented that identifies music samples which are difficult for current state-of-the-art beat trackers. In order to estimate this difficulty even for examples without ground truth, a method motivated by selective sampling is applied. This method assigns a degree of difficulty to a sample based on the mutual disagreement between the output of various beat tracking systems. On a large beat annotated dataset we show that this mutual agreement is correlated with the mean performance of the beat trackers evaluated against the ground truth, and hence can be used to identify difficult examples by predicting poor beat tracking performance. Towards the aim of advancing future beat tracking systems, we demonstrate how our method can be used to form new datasets containing a high proportion of challenging music examples.

Davies, Matthew (författare)
Zapata, Jose Ricardo (författare)
Oliveira, Joao Lobato (författare)
Gouyon, Fabien (författare)
Sound and Music Computing Group, INESC TEC, Porto, Portugal (creator_code:org_t)

Ingår i:Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP): IEEE conference proceedings, s. 89-92

Av författaren/redakt...: Holzapfel, André ...; Davies, Matthew; Zapata, Jose Ric ...; Oliveira, Joao L ...; Gouyon, Fabien

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Annan teknik; och Mediateknik

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.