REVIEW 4 cited by
End-to-end learning for music audio tagging at scale
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The lack of data tends to limit the outcomes of deep learning research, particularly when dealing with end-to-end learning stacks processing raw data such as waveforms. In this study, 1.2M tracks annotated with musical labels are available to train our end-to-end models. This large amount of data allows us to unrestrictedly explore two different design paradigms for music auto-tagging: assumption-free models - using waveforms as input with very small convolutional filters; and models that rely on domain knowledge - log-mel spectrograms with a convolutional neural network designed to learn timbral and temporal features. Our work focuses on studying how these two types of deep architectures perform when datasets of variable size are available for training: the MagnaTagATune (25k songs), the Million Song Dataset (240k songs), and a private dataset of 1.2M songs. Our experiments suggest that music domain assumptions are relevant when not enough training data are available, thus showing how waveform-based models outperform spectrogram-based ones in large-scale data scenarios.
Forward citations
Cited by 4 Pith papers
-
Leave-One-EquiVariant: Alleviating invariance-related information loss in contrastive music representations
A contrastive music representation method, Leave-One-EquiVariant, keeps pitch and tempo information in separate embedding subspaces, improving key and tempo tasks without hurting tagging.
-
Vision Language Models Are Few-Shot Audio Spectrogram Classifiers
GPT-4o classifies environmental sounds from spectrogram images in a few-shot setting with 59% cross-validated accuracy on ESC-10, beating a commercial audio language model and roughly matching human experts.
-
Lukthung Classification Using Neural Networks on Lyrics and Audios
A combined bag-of-words lyrics network and spectrogram CNN classify Lukthung songs from other Thai genres with an F1 of 0.86 on a private 10,547-song dataset.
-
The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases
A dissertation synthesizing the author's papers on continuous kernel convolutions and symmetry-preserving architectures, claiming these inductive biases improve deep learning efficiency.
Discussion (0). Continue with ORCID to comment.