Related papers: Generalizing AUC Optimization to Multiclass Classi…

The deployment of machine listening algorithms in real-life applications is often impeded by a domain shift caused for instance by different microphone characteristics. In this paper, we propose a novel domain adaptation strategy based on…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification. Most audio source separation approaches focus only on separating sources belonging to a restricted domain of…

Current audio pre-training seeks to learn unified representations for broad audio understanding tasks, but it remains fragmented and is fundamentally bottlenecked by its reliance on weak, noisy, and scale-limited labels. Drawing lessons…

In this paper, we propose systematic and efficient gradient-based methods for both one-way and two-way partial AUC (pAUC) maximization that are applicable to deep learning. We propose new formulations of pAUC surrogate objectives by using…

Accurately localizing audible objects based on audio-visual cues is the core objective of audio-visual segmentation. Most previous methods emphasize spatial or temporal multi-modal modeling, yet overlook challenges from ambiguous…

We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating $4+$ sources with 2 microphones) they assume a known or fixed…

The Area Under the ROC Curve (AUC) is a widely used performance measure for imbalanced classification arising from many application domains where high-dimensional sparse data is abundant. In such cases, each $d$ dimensional sample has only…

We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical…

Multiple binary responses arise in many modern data-analytic problems. Although fitting separate logistic regressions for each response is computationally attractive, it ignores shared structure and can be statistically inefficient,…

Classification of audio samples is an important part of many auditory systems. Deep learning models based on the Convolutional and the Recurrent layers are state-of-the-art in many such tasks. In this paper, we approach audio classification…

Top-k error has become a popular metric for large-scale classification benchmarks due to the inevitable semantic ambiguity among classes. Existing literature on top-k optimization generally focuses on the optimization method of the top-k…

Audio features have been proven useful for increasing the performance of automated topic segmentation systems. This study explores the novel task of using audio embeddings for automated, topically coherent segmentation of radio shows. We…

While deep learning has been incredibly successful in modeling tasks with large, carefully curated labeled datasets, its application to problems with limited labeled data remains a challenge. The aim of the present work is to improve the…

In recent years, the need for semantic segmentation has arisen across several different applications and environments. However, the expense and redundancy of annotation often limits the quantity of labels available for training in any…

Dialogue acts (DAs) can represent conversational actions of tutors or students that take place during tutoring dialogues. Automating the identification of DAs in tutoring dialogues is significant to the design of dialogue-based intelligent…

Machine learning (ML) is increasingly employed in real-world applications like medicine or economics, thus, potentially affecting large populations. However, ML models often do not perform homogeneously, leading to underperformance or,…

Pseudo-labeling is a cornerstone of Unsupervised Domain Adaptation (UDA), yet the scarcity of High-Confidence Pseudo-Labeled Target Domain Samples (\textbf{hcpl-tds}) often leads to inaccurate cross-domain statistical alignment, causing DA…

Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based…

Model evaluation is of crucial importance in modern statistics application. The construction of ROC and calculation of AUC have been widely used for binary classification evaluation. Recent research generalizing the ROC/AUC analysis to…