Cargando…

Dynamic Acoustic Unit Augmentation with BPE-Dropout for Low-Resource End-to-End Speech Recognition

With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. For on-device speech recognition tasks, researchers and industry prefer end-to-end ASR systems as they can be made resource-efficient while ma...

Descripción completa

Detalles Bibliográficos
Autores principales: Laptev, Aleksandr, Andrusenko, Andrei, Podluzhny, Ivan, Mitrofanov, Anton, Medennikov, Ivan, Matveev, Yuri
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8124527/
https://www.ncbi.nlm.nih.gov/pubmed/33924798
http://dx.doi.org/10.3390/s21093063