Feature learning of Japanese pitch accents and applications to Japanese speech education

We modeled pitch frequency by a sequential variational autoencoder to obtain the feature representations of the pitch accents of Japanese words for applications to Japanese speech education for the hearing impaired and Japanese-language learners. In our model, the latent variables are comprised of t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2023 14th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) S. 188 - 193
1. Verfasser:	Masuda-Katsuse, Ikuyo
Format:	Tagungsbericht
Sprache:	Englisch Japanisch
Veröffentlicht:	IEEE 08.07.2023
Schlagworte:	Auditory system deep learning Education Feeds Focusing Japanese speech education latent variables Linguistics pitch accent Representation learning speech perception Time-frequency analysis VAE
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!