Related papers: A Generative-First Neural Audio Autoencoder

This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for…

This study investigates the use of non-linear unsupervised dimensionality reduction techniques to compress a music dataset into a low-dimensional representation which can be used in turn for the synthesis of new sounds. We systematically…

This paper introduces a novel generative encoder (GE) model for generative imaging and image processing with applications in compressed sensing and imaging, image compression, denoising, inpainting, deblurring, and super-resolution. The GE…

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular…

We present an application of autoencoders to the problem of noise reduction in single-shot astronomical images and explore its suitability for upcoming large-scale surveys. Autoencoders are a machine learning model that summarises an input…

High-fidelity general audio compression at ultra-low bitrates is crucial for applications ranging from low-bandwidth communication to generative audio-language modeling. Traditional audio compression methods and contemporary neural codecs…

Purpose: Training auto-encoders on simulated signal evolution and inserting the decoder into the forward model improves reconstructions through more compact, Bloch-equation-based representations of signal in comparison to linear subspaces.…

Matched filtering for signal detection in noisy data requires template banks that capture variation in signal waveforms while minimizing computational cost. Dimensionality reduction of signal waveforms can be important for building…

Recent advances in the field of generative models and in particular generative adversarial networks (GANs) have lead to substantial progress for controlled image editing, especially compared with the pre-deep learning era. Despite their…

We propose an end-to-end differentiable architecture for tomography reconstruction that directly maps a noisy sinogram into a denoised reconstruction. Compared to existing approaches our end-to-end architecture produces more accurate…

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics of input data. However, 1-D filters on raw audio are hard to…

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…

The increasing success of audio foundation models across various tasks has led to a growing need for improved interpretability to understand their intricate decision-making processes better. Existing methods primarily focus on explaining…

In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. For high-dimensional visual data, it reduces redundancy and emphasizes key features for…

We propose a novel approach for time-scale modification of audio signals. Unlike traditional methods that rely on the framing technique or the short-time Fourier transform to preserve the frequency during temporal stretching, our neural…

A fundamental aspect of limitations in learning any computation in neural architectures is characterizing their optimal capacities. An important, widely-used neural architecture is known as autoencoders where the network reconstructs the…

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…

Neural network-based methods have recently demonstrated state-of-the-art results on image synthesis and super-resolution tasks, in particular by using variants of generative adversarial networks (GANs) with supervised feature losses.…

We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior…