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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.21437/Interspeech.2020-2568 | INTERSPEECH |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chen Yangbin | 1 | 0 | 0.34 |
Ko Tom | 2 | 0 | 0.34 |
Lifeng Shang | 3 | 485 | 30.96 |
Chen Xiao | 4 | 2 | 0.69 |
Xin Jiang | 5 | 150 | 32.43 |
Li Qing | 6 | 0 | 0.34 |