An Investigation of Few-Shot Learning in Spoken Term Classification

Yangbin Chen, Tom Ko, Lifeng Shang, Xiao Chen, Xin Jiang, Qing Li

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

In this paper, we investigate the feasibility of applying few-shot learning algorithms to a speech task. We formulate a user-defined scenario of spoken term classification as a few-shot learning problem. In most few-shot learning studies, it is assumed that all the N classes are new in a N-way problem. We suggest that this assumption can be relaxed and define a N+M-way problem where N and M are the number of new classes and fixed classes respectively. We propose a modification to the Model-Agnostic Meta-Learning (MAML) algorithm to solve the problem. Experiments on the Google Speech Commands dataset show that our approach outperforms the conventional supervised learning approach and the original MAML.
Original languageEnglish
Title of host publicationProc. Interspeech 2020
Place of PublicationShanghai (Virtual)
Pages2582-2586
Number of pages5
Publication statusPublished - 25 Oct 2020

Cite this