相关论文: Do Foundational Audio Encoders Understand Music St…

The analysis of the structure of musical pieces is a task that remains a challenge for Artificial Intelligence, especially in the field of Deep Learning. It requires prior identification of structural boundaries of the music pieces. This…

Recent developments in MIR have led to several benchmark deep learning models whose embeddings can be used for a variety of downstream tasks. At the same time, the vast majority of these models have been trained on Western pop/rock music…

Foundation models (FMs) are increasingly spearheading recent advances on a variety of tasks that fall under the purview of computer audition -- the use of machines to understand sounds. They feature several advantages over traditional…

Convolutional Neural Networks have been extensively explored in the task of automatic music tagging. The problem can be approached by using either engineered time-frequency features or raw audio as input. Modulation filter bank…

Speaker verification systems have seen significant advancements with the introduction of Multi-scale Feature Aggregation (MFA) architectures, such as MFA-Conformer and ECAPA-TDNN. These models leverage information from various network…

We address the challenging open problem of learning an effective latent space for symbolic music data in generative music modeling. We focus on leveraging adversarial regularization as a flexible and natural mean to imbue variational…

Variational Autoencoders (VAEs) are essential for large-scale audio tasks like diffusion-based generation. However, existing open-source models often neglect auditory perceptual aspects during training, leading to weaknesses in phase…

In the age of music streaming platforms, the task of automatically tagging music audio has garnered significant attention, driving researchers to devise methods aimed at enhancing performance metrics on standard datasets. Most recent…

Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well. Machine listening research often suffers from limited labeled data problem, as human annotations are costly to acquire, and…

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

The expressive nature of the voice provides a powerful medium for communicating sonic ideas, motivating recent research on methods for query by vocalisation. Meanwhile, deep learning methods have demonstrated state-of-the-art results for…

Unsupervised learning methods have become increasingly important in deep learning due to their demonstrated large utilization of datasets and higher accuracy in computer vision and natural language processing tasks. There is a growing trend…

Deep learning has boosted the performance of many music information retrieval (MIR) systems in recent years. Yet, the complex hierarchical arrangement of music makes end-to-end learning hard for some MIR tasks - a very deep and flexible…

Our study investigates an approach for understanding musical performances through the lens of audio encoding models, focusing on the domain of solo Western classical piano music. Compared to composition-level attribute understanding such as…

This paper evaluates the impact of training undergraduate students to improve their audio deepfake discernment ability by listening for expert-defined linguistic features. Such features have been shown to improve performance of AI…

Although many models exist to detect singing voice deepfakes (SingFake), how these models operate, particularly with instrumental accompaniment, is unclear. We investigate how instrumental music affects SingFake detection from two…

Neural networks that map between low dimensional spaces are ubiquitous in computer graphics and scientific computing; however, in their naive implementation, they are unable to learn high frequency information. We present a comprehensive…

Foundation Models (FMs) display exceptional performance in tasks such as natural language processing and are being applied across a growing range of disciplines. Although typically trained on large public datasets, FMs are often fine-tuned…

There has been a growing interest in using deep learning models for processing long surgical videos, in order to automatically detect clinical/operational activities and extract metrics that can enable workflow efficiency tools and…

Learning hierarchical features in Sparse Autoencoders (SAEs) is essential for capturing the structured nature of real-world data and mitigating issues like feature absorption or splitting. Existing works attempt to identify hierarchical…