Multi-accent Speech Separation with One Shot Learning

Huang, Kuo-Liang; Wu, Yuan-Kuei; Lee, Hung-yi

doi:10.18653/v1/2021.metanlp-1.7

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Domain has different meanings in different NLP problems. For example, in speech processing tasks, the domains can refer to accents (Winata et al, 2020b;Huang et al, 2021) or speakers (Klejch et al, 2019;Wu et al, 2021b;Huang et al, 2022).…”

Section: Cross-domain Transfermentioning

confidence: 99%

Meta Learning and Its Applications to Natural Language Processing

Lee¹,

Vu²,

Li³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Deep learning has been the mainstream technique in natural language processing (NLP) area. However, the techniques require many labeled data and are less generalizable across domains. Meta-learning is an arising field in machine learning studying approaches to learn better learning algorithms. Approaches aim at improving algorithms in various aspects, including data efficiency and generalizability. Efficacy of approaches has been shown in many NLP tasks, but there is no systematic survey of these approaches in NLP, which hinders more researchers from joining the field. Our goal with this survey paper is to offer researchers pointers to relevant meta-learning works in NLP and attract more attention from the NLP community to drive future innovation. This paper first introduces the general concepts of meta-learning and the common approaches. Then we summarize task construction settings and application of meta-learning for various NLP problems and review the development of meta-learning in NLP community.

show abstract

Section: Cross-domain Transfermentioning

confidence: 99%

Meta Learning and Its Applications to Natural Language Processing

Lee¹,

Vu²,

Li³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

show abstract

Few-shot meta multilabel classifier for low resource accented code-switched speech

Manghat,

Schultz

2023

2023 26th Conference of the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databa

View full text Add to dashboard Cite

Meta-learning Approaches for Few-Shot Learning: A Survey of Recent Advances

Gharoun,

Momenifar,

Chen

et al. 2024

ACM Comput. Surv.

View full text Add to dashboard Cite

Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising approach that addresses these issues by adapting to new tasks with few-shot datasets. This survey first briefly introduces meta-learning and then investigates state-of-the-art meta-learning methods and recent advances in: (i) metric-based, (ii) memory-based, (iii), and learning-based methods. Finally, current challenges and insights for future researches are discussed.

show abstract

Multi-accent Speech Separation with One Shot Learning

Cited by 3 publications

References 19 publications

Meta Learning and Its Applications to Natural Language Processing

Meta Learning and Its Applications to Natural Language Processing

Few-shot meta multilabel classifier for low resource accented code-switched speech

Meta-learning Approaches for Few-Shot Learning: A Survey of Recent Advances

Contact Info

Product

Resources

About