The paper introduces a domain‑specific parameter‑isolation architecture for domain‑incremental learning (DIL) in audio classification, aiming to preserve knowledge from earlier domains without accessing their data. By employing data‑free generative replay and cross‑domain feature generation, the method constructs new experts conditioned on all previously frozen models, thereby mitigating catastrophic forgetting. Applied to the DCASE 2026 Challenge Task 7, the approach achieves micro and macro accuracies of 78.4 % and 78.9 %, outperforming the baseline by 33 and 25 percentage points, respectively, with ablation studies confirming the contribution of each component.
By Jongyeon Park, Do-Hyeon Lim, Sang-won Park, Hong Kook Kim, Kyungdeuk Ko, Hyeongcheol Geum, Jeong Eun Lim
Fully few-shot class-incremental audio classification (FFCAC) requires recognizing new sound classes from only a handful of labeled examples per session, without forgetting previously learned classes...
arXiv:2607. 12569v1 Announce Type: cross Abstract: Fake speech detectors are increasingly challenged by the development of new and more accurate generative models.
By Enrico Gottardis, Mattia Tamiazzo, Simone Milani
arXiv:2606. 14459v1 Announce Type: cross Abstract: Modern Automatic Speech Recognition (ASR) systems have made remarkable progress on standard benchmarks, yet performance gaps have emerged under real-world distribution shifts, caused by recording conditions, accents, speech impairments, and noise.
By Theresa Pekarek Rosin, Matthias Kerzel, Stefan Wermter
arXiv:2607. 06179v1 Announce Type: cross Abstract: There are some datasets of varying scales for audio classification (AC) applied to different tasks.
By Hong Lyu, Mingru Yang, Qianhua He, Yanxiong Li, Jinxin Huang, Zhengyu Pei
Fake speech detectors are increasingly challenged by the development of new and more accurate generative models. To cope with this problem, continual learning techniques are nowadays widely considered feasible strategies for updating models to new datasets, but they also lead to decreased performance on previously seen samples (catastrophic forgetting).
Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. While recent CIL advances have spurred significant interest across various modalities, the audio-visual setting remains underexplored.
arXiv:2605. 13075v3 Announce Type: replace-cross Abstract: Few-shot spoken word classification has largely been developed for applications where a small number of classes is considered, and so the potential of larger-scale few-shot spoken word classification remains untapped.
By Louise Beyers, Batsirayi Mupamhi Ziki, Ruan van der Merwe
arXiv:2602. 18528v2 Announce Type: replace Abstract: Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online cross-modal learning and eventually leads to poor accuracy.
By Sarthak Kumar Maharana, Akshay Mehra, Bhavya Ramakrishna, Yunhui Guo, Guan-Ming Su
arXiv:2404.07729v2 Announce Type: replace
Abstract: Continual learning (CL) evaluates adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forg...
By Nadia Nasri, Carlos Guti\'errez-\'Alvarez, Sergio Lafuente-Arroyo, Saturnino Maldonado-Basc\'on, Roberto J. L\'opez-Sastre
arXiv:2606. 17775v1 Announce Type: cross Abstract: Efficient processing of continuous audio streams remains a key challenge for real-time and resource-constrained systems.
By Benjamin Hatton, Oliver Rhodes, Luca Peres
arXiv:2603. 12658v2 Announce Type: replace-cross Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting, a critical limitation of the static pre-training paradigm inherent to modern LLMs.
By Hongyang Chen, Zhongwu Sun, Hongfei Ye, Kunchi Li, Xuemin Lin