Unsupervised Musical Object Discovery from Audio
Not on the map. Why?
Abstract (arXiv)
Current object-centric learning models such as the popular SlotAttention architecture allow for unsupervised visual scene decomposition. Our novel MusicSlots method adapts SlotAttention to the audio domain, to achieve unsupervised music decomposition. Since concepts of opacity and occlusion in vision have no auditory analogues, the softmax normalization of alpha masks in the decoders of visual object-centric models is not well-suited for decomposing audio objects. MusicSlots overcomes this problem. We introduce a spectrogram-based multi-object music dataset tailored to evaluate object-centric learning on western tonal music. MusicSlots achieves good performance on unsupervised note discovery and outperforms several established baselines on supervised note property prediction tasks.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 13 Nov 2023.
Builds on
29 of 46 references.
References · 29
- 2017Attention Is All You Needcited by 59,932
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
- 2020Object-Centric Learning with Slot Attentioncited by 865
- 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
- 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
- 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
- 2021Conditional Object-Centric Learning from Videocited by 247
- 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
- 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
- 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
- 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
- 2017Neural Expectation Maximizationcited by 123
17 more
- 2019Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEscited by 116
- 2018Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactionscited by 100
- 2021Contrastive Learning of Musical Representationscited by 81
- 2016Tagger: Deep Unsupervised Perceptual Groupingcited by 69
- 2021Towards Learning Universal Audio Representationscited by 51
- 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
- 2022Supervised and Unsupervised Learning of Audio Representations for Music Understandingcited by 34
- 2022MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learningcited by 22
- 2019R-SQAIR: Relational Sequential Attend, Infer, Repeatcited by 21
- 2022Unsupervised Learning of Temporal Abstractions with Slot-based Transformerscited by 14
- 2021Learning music audio representations via weak language supervisioncited by 13
- 2022Modularity through Attention: Efficient Training and Transfer of Language-Conditioned Policies for Robot Manipulationcited by 12
- 2017Representation Learning of Music Using Artist Labelscited by 7
- 2022Towards Proper Contrastive Self-supervised Learning Strategies For Music Audio Representationcited by 5
- 2023Learning Music Sequence Representation from Text Supervisioncited by 5
- 2023AudioSlots: A slot-centric generative model for audio separationcited by 4
- 2023jazznet: A Dataset of Fundamental Piano Patterns for Music Audio Machine Learning Researchcited by 3
Built on by
Citing papers per year: 2024: 2.
2 papers.