… , GAL network [25] and a novel incremental supervised neural network are comparatively
examined to classify … : Bronchial sounds, bronchovesicular sounds, vesicular sounds, crackles …

… Given a verbal command from a user, the proposed incremental learning framework ranks
… the sound source and the environment. The recent advancements of Deep Neural Networks (…

… For incremental learning the traditional neural networks are … In this study, the AND was
employed in a semi-supervised … with background noise class for few-shot detection of rare sound …

… , to the noise levels in … incremental learning algorithms, such as incremental construction
of support vector machine classifiers with provable performance guarantees [21], incremental …

… a method for class-incremental learning of potentially overlapping sounds for solving a
sequence of multi-label audio classification tasks. We design an incremental learner that learns …

… explores class-incremental learning (CIL) for sound event … of diverse and complex audio
environments. Our approach … function to integrate new sound classes while preserving the …

… To address this, we propose incorporating supervised contrastive learning to refine the …
-mel spectrogram, a prevalent choice for neural network input in embedding learning tasks. …

… [28] addressed catastrophic forgetting in neural networks by training sequential … audio
and video models from self-supervised synchronization. In Proceedings of Advances in Neural …

… Besides, using classification or clustering techniques during … classification if there are some
noise examples in the streaming data. Moreover, the two-step procedure of neural networks, …

… Abstract— In this paper, we work on a sound recognition … , and the progressive growth
of neural networks to combat forgetting [13]… In particular, we are interested in the class-incremental …