paper-with-me

홈 › Papers

Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning

2023-05-22 · Ruan van der Merwe, Herman Kamper

We consider the problem of few-shot spoken word classification in a setting where a model is incrementally introduced to new word classes. This would occur in a user-defined keyword system where new words can be added as the system is used. In such a continual learning scenario, a model might start to misclassify earlier words as newer classes are added, i.e. catastrophic forgetting. To address this, we propose an extension to model-agnostic meta-learning (MAML): each inner learning loop, where a model "learns how to learn'' new classes, ends with a single gradient update using stored templates from all the classes that the model has already seen (one template per class). We compare this method to OML (another extension of MAML) in few-shot isolated-word classification experiments on Google Commands and FACC. Our method consistently outperforms OML in experiments where the number of shots and the final number of classes are varied.

📄 PDF Abstract BibTeX arXiv:2305.13080

Code (1)

bytefuse/mamlcon 공식 구현 pytorch

Tasks

Continual LearningMeta-Learning

Similar Papers 제목 키워드 기반

Progressive Continual Learning for Spoken Keyword Spotting

2022-01-29 · Yizheng Huang, Nana Hou, Nancy F. Chen

Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment. To tackle such challenges, we propose a progressive continual learning strategy for small-footprint spoken keywo…

Continual LearningKeyword Spotting

The Importance of Robust Features in Mitigating Catastrophic Forgetting

2023-06-29 · Hikmat Khan, Nidhal C. Bouaynaya, Ghulam Rasoom

Continual learning (CL) is an approach to address catastrophic forgetting, which refers to forgetting previously learned knowledge by neural networks when trained on new tasks or data distributions. The adversarial robus…

Adversarial RobustnessContinual Learning

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models

2025-05-23 · Chi-Yuan Hsiao, Ke-Han Lu, Kai-Wei Chang, Chih-Kai Yang 외

End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS an…

Continual LearningQuestion Answering

PADCLIP: Pseudo-labeling with Adaptive Debiasing in CLIP for Unsupervised Domain Adaptation

2023-01-01 · ICCV 2023 1 · Zhengfeng Lai, Noranart Vesdapunt, Ning Zhou, Jun Wu 외

Traditional Unsupervised Domain Adaptation (UDA) leverages the labeled source domain to tackle the learning tasks on the unlabeled target domain. It can be more challenging when a large domain gap exists between the …

Causal InferenceDomain AdaptationUnsupervised Domain Adaptation

AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting

2025-05-17 · Yang Xiao, Tianyi Peng, Rohan Kumar Das, Yuchen Hu 외

Keyword spotting (KWS) offers a vital mechanism to identify spoken commands in voice-enabled systems, where user demands often shift, requiring models to learn new keywords continually over time. However, a major problem…

class-incremental learningClass Incremental LearningContinual LearningExemplar-Free+3