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

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-resou...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEICE Transactions on Information and Systems 2022/09/01, Vol.E105.D(9), pp.1639-1642
Hauptverfasser:	HUANG, Zheying, XU, Ji, ZHAO, Qingwei, ZHANG, Pengyuan
Format:	Artikel
Sprache:	eng
Schlagworte:	code-switching Learning low-resource meta-learning Speech recognition Training two-fold cross-validation
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!