The Impact of Label Noise on a Music Tagger

Katharina Prinz; Arthur Flexer; Gerhard Widmer

The Impact of Label Noise on a Music Tagger

Katharina Prinz, Arthur Flexer, Gerhard Widmer

Institute of Computational Perception

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

We explore how much can be learned from noisy labels in au- dio music tagging. Our experiments show that carefully annotated labels result in highest figures of merit, but even high amounts of noisy labels contain enough information for successful learning. Artificial corruption of curated data allows us to quantize this contribution of noisy labels.

Original language	English
Title of host publication	Proceedings of the 13th International Workshop on Machine Learning and Music, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020
Number of pages	4
Publication status	Published - Aug 2020

Fields of science

202002 Audiovisual media
102 Computer Sciences
102001 Artificial intelligence
102003 Image processing
102015 Information systems

JKU Focus areas

Digital Transformation

Cite this

@inproceedings{b3f4a6bfbb2544e7882c8be133dd36d6,

title = "The Impact of Label Noise on a Music Tagger",

abstract = "We explore how much can be learned from noisy labels in au- dio music tagging. Our experiments show that carefully annotated labels result in highest figures of merit, but even high amounts of noisy labels contain enough information for successful learning. Artificial corruption of curated data allows us to quantize this contribution of noisy labels.",

author = "Katharina Prinz and Arthur Flexer and Gerhard Widmer",

year = "2020",

month = aug,

language = "English",

booktitle = "Proceedings of the 13th International Workshop on Machine Learning and Music, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020",

}

The Impact of Label Noise on a Music Tagger. / Prinz, Katharina ; Flexer, Arthur ; Widmer, Gerhard.
Proceedings of the 13th International Workshop on Machine Learning and Music, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020. 2020.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

TY - GEN

T1 - The Impact of Label Noise on a Music Tagger

AU - Prinz, Katharina

AU - Flexer, Arthur

AU - Widmer, Gerhard

PY - 2020/8

Y1 - 2020/8

N2 - We explore how much can be learned from noisy labels in au- dio music tagging. Our experiments show that carefully annotated labels result in highest figures of merit, but even high amounts of noisy labels contain enough information for successful learning. Artificial corruption of curated data allows us to quantize this contribution of noisy labels.

AB - We explore how much can be learned from noisy labels in au- dio music tagging. Our experiments show that carefully annotated labels result in highest figures of merit, but even high amounts of noisy labels contain enough information for successful learning. Artificial corruption of curated data allows us to quantize this contribution of noisy labels.

UR - https://arxiv.org/pdf/2008.06273.pdf

M3 - Conference proceedings

BT - Proceedings of the 13th International Workshop on Machine Learning and Music, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020

ER -

The Impact of Label Noise on a Music Tagger

Abstract

Fields of science

JKU Focus areas

Other files and links

Cite this