Related papers: Ecologically-Constrained Task Arithmetic for Multi…

We study a recent model of collaborative PAC learning where $k$ players with $k$ different tasks collaborate to learn a single classifier that works for all tasks. Previous work showed that when there is a classifier that has very small…

Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech recognition (ASR). This alignment is inherently structured and asymmetric: while multiple…

Many animals emit vocal sounds which, independently from the sounds' function, embed some individually-distinctive signature. Thus the automatic recognition of individuals by sound is a potentially powerful tool for zoology and ecology…

Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We…

Masked Autoencoders (MAEs) learn rich semantic representations in audio classification through an efficient self-supervised reconstruction task. However, general-purpose models fail to generalize well when applied directly to fine-grained…

Machine learning from training data with a skewed distribution of examples per class can lead to models that favor performance on common classes at the expense of performance on rare ones. AudioSet has a very wide range of priors over its…

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

Certain cancer types, notably pancreatic cancer, are difficult to detect at an early stage, motivating robust biomarker-based screening. Liquid biopsies enable non-invasive monitoring of circulating biomarkers, but typical machine learning…

To address the calibration and procedural challenges inherent in remote audiogram assessment for rehabilitative audiology, this study investigated whether calibration-independent adaptive categorical loudness scaling (ACALOS) data can be…

Traditional acoustic environment classification relies on: i) classical signal processing algorithms, which are unable to extract meaningful representations of high-dimensional data; or on ii) supervised learning, limited by the…

In this technical report, we describe the SNTL-NTU team's submission for Task 1 Data-Efficient Low-Complexity Acoustic Scene Classification of the detection and classification of acoustic scenes and events (DCASE) 2024 challenge. Three…

We present a comparative evaluation of latent space organization in three Variational Autoencoders (VAEs) for musical timbre generation: an unsupervised VAE, a descriptor-conditioned VAE, and a VAE conditioned on continuous perceptual…

High-throughput sequencing has transformed microbiome research, but it also produces inherently compositional data that challenge standard statistical and machine learning methods. In this work, we propose a multinomial classification…

This monograph introduces a novel approach to polyphonic music generation by addressing the "Missing Middle" problem through structural inductive bias. Focusing on Beethoven's piano sonatas as a case study, we empirically verify the…

In this paper, we investigate the problem of classifying feature vectors with mutually independent but non-identically distributed elements. First, we show the importance of this problem. Next, we propose a classifier and derive an…

Acoustic scene classification (ASC) is one of the most popular problems in the field of machine listening. The objective of this problem is to classify an audio clip into one of the predefined scenes using only the audio data. This problem…

Acoustic scene classification identifies an input segment into one of the pre-defined classes using spectral information. The spectral information of acoustic scenes may not be mutually exclusive due to common acoustic properties across…

We extend frequency-domain blind source separation based on independent vector analysis to the case where there are more microphones than sources. The signal is modelled as non-Gaussian sources in a Gaussian background. The proposed…

Deep neural networks have recently led to promising results for the task of multiple sound source localization. Yet, they require a lot of training data to cover a variety of acoustic conditions and microphone array layouts. One can…

Zooplankton images, like many other real world data types, have intrinsic properties that make the design of effective classification systems difficult. For instance, the number of classes encountered in practical settings is potentially…