Related papers: fastabx: A library for efficient computation of AB…
Deep learning has enabled major advances in the fields of computer vision, natural language processing, and multimedia among many others. Developing a deep learning system is arduous and complex, as it involves constructing neural network…
Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…
Mean Average Precision (mAP) has been widely used for evaluating the quality of object detectors, but an efficient implementation is still absent. Current implementations can only count true positives (TP's) and false positives (FP's) for…
While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing and make it…
In this paper, we address the problem of separating individual speech signals from videos using audio-visual neural processing. Most conventional approaches utilize frame-wise matching criteria to extract shared information between…
Literature reviews are essential for any researcher trying to keep up to date with the burgeoning software engineering literature. FAST$^2$ is a novel tool for reducing the effort required for conducting literature reviews by assisting the…
The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling over a random discrete variable, yielding…
This work introduces ParamRF: a Python library for efficient, parametric modelling of radio frequency (RF) circuits. Built on top of the next-generation computational library JAX, as well as the object-oriented wrapper Equinox, the…
Bipolar Argumentation Frameworks (BAFs) admit several interpretations of the support relation and diverging definitions of semantics. Recently, several classes of BAFs have been captured as instances of bipolar Assumption-Based…
Innovations across science and industry are evaluated using randomized trials (a.k.a. A/B tests). While simple and robust, such static designs are inefficient or infeasible for testing many hypotheses. Adaptive designs can greatly improve…
This article introduces ATAB, a tool that automatically generates pairwise reachability checks for action trees. Action trees can be used to study the behaviour of real-world concurrent programs. ATAB encodes pairwise reachability checks…
Neural simulation-based inference (SBI) describes an emerging family of methods for Bayesian inference with intractable likelihood functions that use neural networks as surrogate models. Here we introduce sbijax, a Python package that…
The remarkable success of modern machine learning models on large datasets often demands extensive training time and resource consumption. To save cost, a prevalent research line, known as online batch selection, explores selecting…
We introduce a Python open-source library for $\mathcal{X}$-armed bandit and online blackbox optimization named PyXAB. PyXAB contains the implementations for more than 10 $\mathcal{X}$-armed bandit algorithms, such as HOO, StoSOO, HCT, and…
Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many "hard" primitives in these libraries such as thresholding, Boolean logic, discrete…
Attribute-Based Access Control (ABAC) provides expressiveness and flexibility, making it a compelling model for enforcing fine-grained access control policies. To facilitate the transition to ABAC, extensive research has been conducted to…
In recent years, wsj0-2mix has become the reference dataset for single-channel speech separation. Most deep learning-based speech separation models today are benchmarked on it. However, recent studies have shown important performance drops…
Many tasks in natural language processing, such as named entity recognition and slot-filling, involve identifying and labeling specific spans of text. In order to leverage common models, these tasks are often recast as sequence labeling…
Audio-visual representation learning aims to develop systems with human-like perception by utilizing correlation between auditory and visual information. However, current models often focus on a limited set of tasks, and generalization…
Due to the outstanding capability for data generation, Generative Adversarial Networks (GANs) have attracted considerable attention in unsupervised learning. However, training GANs is difficult, since the training distribution is dynamic…