Related papers: Hierarchical Linear Dynamical System for Represent…

Humans are able to recognize structured relations in observation, allowing us to decompose complex scenes into simpler parts and abstract the visual world in multiple levels. However, such hierarchical reasoning ability of human perception…

Modeling dynamical systems is important in many disciplines, e.g., control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional…

Prior approaches to lead instrument detection primarily analyze mixture audio, limited to coarse classifications and lacking generalization ability. This paper presents a novel approach to lead instrument detection in multitrack music audio…

Time series classification is crucial for numerous scientific and engineering applications. In this article, we present a numerically efficient, practically competitive, and theoretically rigorous classification method for distinguishing…

A variety of complex biological, natural and man-made systems exhibit non-Markovian dynamics that can be modeled through fractional order differential equations, yet, we lack sample comlexity aware system identification strategies. Towards…

In computational bioacoustics, deep learning models are composed of feature extractors and classifiers. The feature extractors generate vector representations of the input sound segments, called embeddings, which can be input to a…

Anomaly detection has many important applications, such as monitoring industrial equipment. Despite recent advances in anomaly detection with deep-learning methods, it is unclear how existing solutions would perform under…

An anomalous sound detection system to detect unknown anomalous sounds usually needs to be built using only normal sound data. Moreover, it is desirable to improve the system by effectively using a small amount of anomalous sound data,…

Dynamical systems are used to model a variety of phenomena in which the bifurcation structure is a fundamental characteristic. Here we propose a statistical machine-learning approach to derive lowdimensional models that automatically…

Clinical decision support systems (CDSSs) have been widely utilized to support the decisions made by cardiologists when detecting and classifying arrhythmia from electrocardiograms (ECGs). However, forming a CDSS for the arrhythmia…

Numerous complex real-world systems, such as those in biological, ecological, and social networks, exhibit higher-order interactions that are often modeled using polynomial dynamical systems or homogeneous polynomial dynamical systems…

Videos are multimodal in nature. Conventional video recognition pipelines typically fuse multimodal features for improved performance. However, this is not only computationally expensive but also neglects the fact that different videos rely…

Proactively and naturally guiding the dialog from the non-recommendation context (e.g., Chit-chat) to the recommendation scenario (e.g., Music) is crucial for the Conversational Recommender System (CRS). Prior studies mainly focus on…

Adapting large language models (LLMs) to specific domains often faces a critical bottleneck: the scarcity of high-quality, human-curated data. While large volumes of unchecked data are readily available, indiscriminately using them for…

Chord recognition systems depend on robust feature extraction pipelines. While these pipelines are traditionally hand-crafted, recent advances in end-to-end machine learning have begun to inspire researchers to explore data-driven methods…

Multivariate time series anomaly detection (MTSAD) aims to accurately identify and localize complex abnormal patterns in the large-scale industrial control systems. While existing approaches excel in recognizing the distinct patterns under…

Distributed acoustic sensing technology is increasingly being used to support production and well management within the oil and gas sector, for example to improve flow monitoring and production profiling. This sensing technology is capable…

Target audio source separation with natural language queries presents a promising paradigm for extracting arbitrary audio events through arbitrary text descriptions. Existing methods mainly face two challenges, the difficulty in jointly…

This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from…

Hierarchical taxonomies are common in many contexts, and they are a very natural structure humans use to organise information. In machine learning, the family of methods that use the 'extra' information is called hierarchical…