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 or Report/Conference proceedingConference Proceedingpeer-review

15 Citations (Scopus)

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 publication21th Annual Conference of the International Speech Communication Association (INTERSPEECH)
Pages2582-2586
DOIs
Publication statusPublished - 2020
Externally publishedYes

Fingerprint

Dive into the research topics of 'An investigation of few-shot learning in spoken term classification'. Together they form a unique fingerprint.

Cite this