相关论文: AFT: An Exemplar-Free Class Incremental Learning M…

As deepfake speech becomes common and hard to detect, it is vital to trace its source. Recent work on audio deepfake source tracing (ST) aims to find the origins of synthetic or manipulated speech. However, ST models must adapt to learn new…

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The classification performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds.…

Adaptive filters (AFs) are vital for enhancing the performance of downstream tasks, such as speech recognition, sound event detection, and keyword spotting. However, traditional AF design prioritizes isolated signal-level objectives, often…

Reusing recorded sounds (sampling) is a key component in Electronic Music Production (EMP), which has been present since its early days and is at the core of genres like hip-hop or jungle. Commercial and non-commercial services allow users…

Environmental Sound Classification (ESC) is a challenging field of research in non-speech audio processing. Most of current research in ESC focuses on designing deep models with special architectures tailored for specific audio datasets,…

Given the similarity between facial expression categories, the presence of compound facial expressions, and the subjectivity of annotators, facial expression recognition (FER) datasets often suffer from ambiguity and noisy labels. Ambiguous…

In this paper we propose a novel environmental sound classification approach incorporating unsupervised feature learning from codebook via spherical $K$-Means++ algorithm and a new architecture for high-level data augmentation. The audio…

We consider the problem of detecting, isolating and classifying elephant calls in continuously recorded audio. Such automatic call characterisation can assist conservation efforts and inform environmental management strategies. In contrast…

Most existing methods for audio classification assume that the vocabulary of audio classes to be classified is fixed. When novel (unseen) audio classes appear, audio classification systems need to be retrained with abundant labeled samples…

Deep neural network (DNN)-based models for environmental sound classification are not robust against a domain to which training data do not belong, that is, out-of-distribution or unseen data. To utilize pretrained models for the unseen…

Feature Transformation is crucial for classic machine learning that aims to generate feature combinations to enhance the performance of downstream tasks from a data-centric perspective. Current methodologies, such as manual expert-driven…

Class Incremental Semantic Segmentation (CISS) aims to mitigate catastrophic forgetting by maintaining a balance between previously learned and newly introduced knowledge. Existing methods, primarily based on regularization techniques like…

The two main impediments to continual learning are catastrophic forgetting and memory limitations on the storage of data. To cope with these challenges, we propose a novel, cognitively-inspired approach which trains autoencoders with Neural…

In machine learning applications, gradual data ingress is common, especially in audio processing where incremental learning is vital for real-time analytics. Few-shot class-incremental learning addresses challenges arising from limited…

In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper…

Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to…

Vision transformers (ViT) have made substantial progress for classification tasks in computer vision. Recently, Gong et. al. '21, introduced attention-based modeling for several audio tasks. However, relatively unexplored is the use of a…

This paper introduces LAFT, a novel feature transformation method designed to incorporate user knowledge and preferences into anomaly detection using natural language. Accurately modeling the boundary of normality is crucial for…

Existing methods to recover model accuracy on analog-digital hardware in the presence of quantization and analog noise include noise-injection training. However, it can be slow in practice, incurring high computational costs, even when…

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…