Related papers: Rehearsal with Auxiliary-Informed Sampling for Aud…

Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples,…

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…

Purpose: We previously established an open-access lung sound database, HF_Lung_V1, and developed deep learning models for inhalation, exhalation, continuous adventitious sound (CAS), and discontinuous adventitious sound (DAS) detection. The…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

A dataset is a shred of crucial evidence to describe a task. However, each data point in the dataset does not have the same potential, as some of the data points can be more representative or informative than others. This unequal importance…

The performance of deep learning models in remote sensing (RS) strongly depends on the availability of high-quality labeled data. However, collecting large-scale annotations is costly and time-consuming, while vast amounts of unlabeled…

Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…

Unsupervised anomalous sound detection aims to detect unknown anomalous sounds by training a model using only normal audio data. Despite advancements in self-supervised methods, the issue of frequent false alarms when handling samples of…

Self-supervised learning (SSL) has recently shown remarkable results in closing the gap between supervised and unsupervised learning. The idea is to learn robust features that are invariant to distortions of the input data. Despite its…

The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained…

Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner often results in label noise. We present a method for learning…

The rapid advancement of spoofing algorithms necessitates the development of robust detection methods capable of accurately identifying emerging fake audio. Traditional approaches, such as finetuning on new datasets containing these novel…

Recent results in end-to-end automatic speech recognition have demonstrated the efficacy of pseudo-labeling for semi-supervised models trained both with Connectionist Temporal Classification (CTC) and Sequence-to-Sequence (seq2seq) losses.…

The rapid advancement of speech synthesis and voice conversion technologies has raised significant security concerns in multimedia forensics. Although current detection models demonstrate impressive performance, they struggle to maintain…

Continual Learning (CL) primarily aims to retain knowledge to prevent catastrophic forgetting and transfer knowledge to facilitate learning new tasks. Unlike traditional methods, we propose a novel perspective: CL not only needs to prevent…

The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art…

Speech deepfake detection has achieved remarkable success in clean environments but faces significant challenges in complex, real-world scenarios where speech is often mixed with background music or noise. Current state-of-the-art methods…

Automatic music transcription is considered to be one of the hardest problems in music information retrieval, yet recent deep learning approaches have achieved substantial improvements on transcription performance. These approaches commonly…

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Deep neural networks have demonstrated state-of-the-art performance on many classification tasks. However, they have no inherent capability to recognize when their predictions are wrong. There have been several efforts in the recent past to…