Few-shot continual learning for audio classification
Supervised learning for audio classification typically imposes a fixed class vocabulary,
which can be limiting for real-world applications where the target class vocabulary is not …
which can be limiting for real-world applications where the target class vocabulary is not …
Few-shot class-incremental audio classification using dynamically expanded classifier with self-attention modified prototypes
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 …
to be classified is fixed. When novel (unseen) audio classes appear, audio classification …
Few-shot class-incremental audio classification using stochastic classifier
It is generally assumed that number of classes is fixed in current audio classification
methods, and the model can recognize pregiven classes only. When new classes emerge …
methods, and the model can recognize pregiven classes only. When new classes emerge …
An incremental class-learning approach with acoustic novelty detection for acoustic event recognition
Acoustic scene analysis (ASA) relies on the dynamic sensing and understanding of
stationary and non-stationary sounds from various events, background noises and human …
stationary and non-stationary sounds from various events, background noises and human …
UCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detection
This work explores class-incremental learning (CIL) for sound event detection (SED),
advancing adaptability towards real-world scenarios. CIL's success in domains like …
advancing adaptability towards real-world scenarios. CIL's success in domains like …
Episodic memory based continual learning without catastrophic forgetting for environmental sound classification
Convolutional neural network suffers from catastrophic forgetting during continual learning.
This is one of the major obstacles for artificial intelligence, to solve new problems without …
This is one of the major obstacles for artificial intelligence, to solve new problems without …
Characterizing Continual Learning Scenarios and Strategies for Audio Analysis
Audio analysis is useful in many application scenarios. The state-of-the-art audio analysis
approaches assume that the data distribution at training and deployment time will be the …
approaches assume that the data distribution at training and deployment time will be the …
IFS-SED: Incremental Few-Shot Sound Event Detection Using Explicit Learning and Calibration
M Feng, K Xu, H Cai - Proceedings of the 31st ACM International …, 2023 - dl.acm.org
Sound event detection (SED) refers to recognizing the sound events in a continuous audio
signal, which has drawn increasing interest during recent decades. The applications of SED …
signal, which has drawn increasing interest during recent decades. The applications of SED …
An efficient incremental learning algorithm for sound classification
MA Hussain, CL Lee, TH Tsai - IEEE MultiMedia, 2022 - ieeexplore.ieee.org
This article proposes an efficient audio incremental learning method to reduce the
computational complexity and catastrophic forgetting during the incremental addition of the …
computational complexity and catastrophic forgetting during the incremental addition of the …
Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor
It's assumed that training data is sufficient in base session of few-shot class-incremental
audio classification. However, it's difficult to collect abundant samples for model training in …
audio classification. However, it's difficult to collect abundant samples for model training in …