Detail publikace

Beat Tracking: Is 44.1 kHz Really Needed?

IŠTVÁNEK, M. MIKLÁNEK, Š.

Originální název

Beat Tracking: Is 44.1 kHz Really Needed?

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Beat tracking is essential in music information retrieval, with applications ranging from music analysis and automatic playlist generation to beat-synchronized effects. In recent years, deep learning methods, usually inspired by well-known architectures, outperformed other beat tracking algorithms. The current state-of-the-art offline beat tracking systems utilize temporal convolutional and recurrent networks. Most systems use an input sampling rate of 44.1 kHz. In this paper, we retrain multiple versions of state-of-the-art temporal convolutional networks with different input sampling rates while keeping the time resolution by changing the frame size parameter. Furthermore, we evaluate all models using standard metrics. As the main contribution, we show that decreasing the input audio recording sampling frequency up to 5 kHz preserves most of the accuracy, and in some cases, even slightly outperforms the standard approach.

Klíčová slova

Beat tracking; music information retrieval; temporal convolutional networks; machine learning

Autoři

IŠTVÁNEK, M.; MIKLÁNEK, Š.

Vydáno

25. 4. 2023

Nakladatel

Brno University of Technology, Faculty of Elektronic Engineering and Communication

Místo

Brno

ISBN

978-80-214-6154-3

Kniha

Proceedings II of the 29th Conference STUDENT EEICT 2023 Selected Papers

Edice

1

Strany od

227

Strany do

231

Strany počet

5

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf

BibTex

@inproceedings{BUT183747,
  author="Matěj {Ištvánek} and Štěpán {Miklánek}",
  title="Beat Tracking: Is 44.1 kHz Really Needed?",
  booktitle="Proceedings II of the 29th Conference STUDENT EEICT 2023 Selected Papers",
  year="2023",
  series="1",
  pages="227--231",
  publisher="Brno University of Technology, Faculty of Elektronic Engineering and Communication",
  address="Brno",
  doi="10.13164/eeict.2023.227",
  isbn="978-80-214-6154-3",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf"
}