Taming Audio VAEs via Target-KL Regularization
Latent diffusion models have emerged as the dominant paradigm for many generation tasks including audio generation such as text-to-audio, text-to-music and text-to-speech. A key component of latent diffusion is an autoencoder (VAE) that compresses high-dimensional signals into a low frame rate continuous representation that is conducive for downstream prediction. Regularizing these VAEs is challenging, as there is a trade-off between over-regularized (poor output quality) and under-regularized (difficult to predict) latent representations. We propose a framework for studying this trade-off through compression and train Audio VAEs at specific bitrates via target-KL regularization. This allows direct comparison to well-studied discrete neural audio codec models, and the construction of rate-distortion curves for audio VAEs. We evaluate the impact of target-KL regularization on text-to-sound generation and find that sweeping compression rates is helpful in identifying the optimal generation setting.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio GenerationSimilar Papers 제목 키워드 기반
Learning Hierarchical Priors in VAEs
We propose to learn a hierarchical prior in the context of variational autoencoders to avoid the over-regularisation resulting from a standard normal prior distribution. To incentivise an informative latent representatio…
Taming under isoperimetry
In this article we propose a novel taming Langevin-based scheme called $\mathbf{sTULA}$ to sample from distributions with superlinearly growing log-gradient which also satisfy a Log-Sobolev inequality. We derive non-asym…
SepVAE: a contrastive VAE to separate pathological patterns from healthy ones
Contrastive Analysis VAE (CA-VAEs) is a family of Variational auto-encoders (VAEs) that aims at separating the common factors of variation between a background dataset (BG) (i.e., healthy subjects) and a target dataset (…
F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation
Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio encoders capture semantics but are not directly decodable. This mismat…
Prior Learning in Introspective VAEs
Variational Autoencoders (VAEs) are a popular framework for unsupervised learning and data generation. A plethora of methods have been proposed focusing on improving VAEs, with the incorporation of adversarial objectives…
Density EstimationImage GenerationRepresentation Learning