A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition

Zheying HUANG; Ji XU; Qingwei ZHAO; Pengyuan ZHANG

doi:10.1587/transinf.2022EDL8036

Regular Section

A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition

Zheying HUANG, Ji XU, Qingwei ZHAO, Pengyuan ZHANG

Author information

Keywords: code-switching, speech recognition, low-resource, two-fold cross-validation, meta-learning

JOURNAL FREE ACCESS

2022 Volume E105.D Issue 9 Pages 1639-1642

DOI https://doi.org/10.1587/transinf.2022EDL8036

Details

Abstract

Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.

Corresponding author

Register with J-STAGE for free!