Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908792938037248 |
|---|---|
| author | Torres, Bernardo Moussallam, Manuel Meseguer-Brocal, Gabriel |
| author_facet | Torres, Bernardo Moussallam, Manuel Meseguer-Brocal, Gabriel |
| contents | Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introduce a simple training methodology to induce linearity in a high-compression Consistency Autoencoder (CAE) by using data augmentation, thereby inducing homogeneity (equivariance to scalar gain) and additivity (the decoder preserves addition) without altering the model's architecture or loss function. When trained with our method, the CAE exhibits linear behavior in both the encoder and decoder while preserving reconstruction fidelity. We test the practical utility of our learned space on music source composition and separation via simple latent arithmetic. This work presents a straightforward technique for constructing structured latent spaces, enabling more intuitive and efficient audio processing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23530 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization Torres, Bernardo Moussallam, Manuel Meseguer-Brocal, Gabriel Sound Artificial Intelligence Machine Learning Audio and Speech Processing Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introduce a simple training methodology to induce linearity in a high-compression Consistency Autoencoder (CAE) by using data augmentation, thereby inducing homogeneity (equivariance to scalar gain) and additivity (the decoder preserves addition) without altering the model's architecture or loss function. When trained with our method, the CAE exhibits linear behavior in both the encoder and decoder while preserving reconstruction fidelity. We test the practical utility of our learned space on music source composition and separation via simple latent arithmetic. This work presents a straightforward technique for constructing structured latent spaces, enabling more intuitive and efficient audio processing. |
| title | Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization |
| topic | Sound Artificial Intelligence Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.23530 |