One shot learning for speech separation
Journal
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Journal Volume
2021-June
Pages
5769-5773
Date Issued
2021
Author(s)
Abstract
Despite the recent success of speech separation models, they fail to separate sources properly while facing different sets of people or noisy environments. To tackle this problem, we proposed to apply meta-learning to the speech separation task. We aimed to find a meta-initialization model, which can quickly adapt to new speakers by seeing only one mixture generated by those people. In this paper, we use model-agnostic meta-learning(MAML) algorithm and almost no inner loop(ANIL) algorithm in Conv-TasNet to achieve this goal. The experiment results show that our model can adapt not only to a new set of speakers but also noisy environments. Furthermore, we found out that the encoder and decoder serve as the feature-reuse layers, while the separator is the task-specific module. ? 2021 IEEE
Subjects
ANIL
MAML
Meta-learning
Speech separation
Separation
Speech analysis
Feature reuse
Inner loops
Metalearning
Noisy environment
One-shot learning
Task-specific modules
Use-model
Source separation
Type
conference paper