Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.08816 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915543362043904 |
|---|---|
| author | Burred, Juan José Cella, Carmine-Emanuele |
| author_facet | Burred, Juan José Cella, Carmine-Emanuele |
| contents | We propose the use of Non-Negative Autoencoders (NAEs) for sound deconstruction and user-guided manipulation of sounds for creative purposes. NAEs offer a versatile and scalable extension of traditional Non-Negative Matrix Factorization (NMF)-based approaches for interpretable audio decomposition. By enforcing non-negativity constraints through projected gradient descent, we obtain decompositions where internal weights and activations can be directly interpreted as spectral shapes and temporal envelopes, and where components can themselves be listened to as individual sound events. In particular, multi-layer Deep NAE architectures enable hierarchical representations with an adjustable level of granularity, allowing sounds to be deconstructed at multiple levels of abstraction: from high-level note envelopes down to fine-grained spectral details. This framework enables a wide new range of expressive, controllable, and randomized sound transformations. We introduce novel manipulation operations including cross-component and cross-layer synthesis, hierarchical deconstructions, and several randomization strategies that control timbre and event density. Through visualizations and resynthesis of practical examples, we demonstrate how NAEs can serve as flexible and interpretable tools for object-based sound editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08816 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Audible Networks: Deconstructing and Manipulating Sounds with Deep Non-Negative Autoencoders Burred, Juan José Cella, Carmine-Emanuele Sound Audio and Speech Processing We propose the use of Non-Negative Autoencoders (NAEs) for sound deconstruction and user-guided manipulation of sounds for creative purposes. NAEs offer a versatile and scalable extension of traditional Non-Negative Matrix Factorization (NMF)-based approaches for interpretable audio decomposition. By enforcing non-negativity constraints through projected gradient descent, we obtain decompositions where internal weights and activations can be directly interpreted as spectral shapes and temporal envelopes, and where components can themselves be listened to as individual sound events. In particular, multi-layer Deep NAE architectures enable hierarchical representations with an adjustable level of granularity, allowing sounds to be deconstructed at multiple levels of abstraction: from high-level note envelopes down to fine-grained spectral details. This framework enables a wide new range of expressive, controllable, and randomized sound transformations. We introduce novel manipulation operations including cross-component and cross-layer synthesis, hierarchical deconstructions, and several randomization strategies that control timbre and event density. Through visualizations and resynthesis of practical examples, we demonstrate how NAEs can serve as flexible and interpretable tools for object-based sound editing. |
| title | Audible Networks: Deconstructing and Manipulating Sounds with Deep Non-Negative Autoencoders |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.08816 |