https://scholars.lib.ntu.edu.tw/handle/123456789/634359
Title: | On the Efficiency of Integrating Self-Supervised Learning and Meta-Learning for User-Defined Few-Shot Keyword Spotting | Authors: | Kao, Wei Tsung Wu, Yuan Kuei Chen, Chia Ping Chen, Zhi Sheng Tsai, Yu Pao HUNG-YI LEE |
Keywords: | Few-shot Learning | Meta-learning | Self-supervised Learning | Spotting | Issue Date: | 1-Jan-2023 | Source: | 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings | Abstract: | User-defined keyword spotting is a task to detect new spoken terms defined by users. This can be viewed as a few-shot learning problem since it is unreasonable for users to define their desired keywords by providing many examples. To solve this problem, previous works try to incorporate self-supervised learning models or apply meta-learning algorithms. But it is unclear whether self-supervised learning and meta-learning are complementary and which combination of the two types of approaches is most effective for few-shot keyword discovery. In this work, we systematically study these questions by utilizing various self-supervised learning models and combining them with a wide variety of meta-learning algorithms. Our result shows that HuBERT combined with Matching network achieves the best result and is robust to the changes of few-shot examples. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/634359 | ISBN: | 9798350396904 | DOI: | 10.1109/SLT54892.2023.10022697 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.