相关论文: Designing Neural Synthesizers for Low-Latency Inte…

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…

Modern transformer models exhibit phase transitions during training, distinct shifts from memorisation to abstraction, but the mechanisms underlying these transitions remain poorly understood. Prior work has often focused on endpoint…

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Deep latent variable models have seen recent success in many data domains. Lossless compression is an application of these models which, despite having the potential to be highly useful, has yet to be implemented in a practical manner. We…

We introduce a new system for data-driven audio sound model design built around two different neural network architectures, a Generative Adversarial Network(GAN) and a Recurrent Neural Network (RNN), that takes advantage of the unique…

Network alignment has attracted widespread attention in various fields. However, most existing works mainly focus on the problem of label sparsity, while overlooking the issue of noise in network alignment, which can substantially undermine…

In this paper, we are interested in unsupervised (unknown noise) audio-visual speech enhancement based on variational autoencoders (VAEs), where the probability distribution of clean speech spectra is simulated using an encoder-decoder…

Understanding how the brain responds to sensory inputs is challenging: brain recordings are partial, noisy, and high dimensional; they vary across sessions and subjects and they capture highly nonlinear dynamics. These challenges have led…

Low latency models are critical for real-time speech enhancement applications, such as hearing aids and hearables. However, the sub-millisecond latency space for resource-constrained hearables remains underexplored. We demonstrate speech…

Non-autoregressive Transformers (NATs) reduce the inference latency of Autoregressive Transformers (ATs) by predicting words all at once rather than in sequential order. They have achieved remarkable progress in machine translation as well…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Neurodivergent people frequently experience decreased sound tolerance, with estimates suggesting it affects 50-70% of this population. This heightened sensitivity can provoke reactions ranging from mild discomfort to severe distress,…

Target Sound Extraction (TSE) focuses on the problem of separating sources of interest, indicated by a user's cue, from the input mixture. Most existing solutions operate in an offline fashion and are not suited to the low-latency causal…

Artificial neural networks (ANNs) have been extensively used for the description of problems arising from biological systems and for constructing neuromorphic computing models. The third generation of ANNs, namely, spiking neural networks…

The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we…

With the advent of data-driven statistical modeling and abundant computing power, researchers are turning increasingly to deep learning for audio synthesis. These methods try to model audio signals directly in the time or frequency domain.…

Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…

Modeling long-term dependencies for audio signals is a particularly challenging problem, as even small-time scales yield on the order of a hundred thousand samples. With the recent advent of Transformers, neural architectures became good at…

Tomorrow's robots will need to distinguish useful information from noise when performing different tasks. A household robot for instance may continuously receive a plethora of information about the home, but needs to focus on just a small…

Timbre is a set of perceptual attributes that identifies different types of sound sources. Although its definition is usually elusive, it can be seen from a signal processing viewpoint as all the spectral features that are perceived…