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...
Main Authors: | Aleksandr Laptev, Andrei Andrusenko, Ivan Podluzhny, Anton Mitrofanov, Ivan Medennikov, Yuri Matveev |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/9/3063 |
Similar Items
-
The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving
by: Ardi Tampuu, et al.
Published: (2024-03-01) -
Improving out of vocabulary words recognition accuracy for an end-to-end Russian speech recognition system
by: Andrei Yu. Andrusenko, et al.
Published: (2022-12-01) -
A regulatory GhBPE-GhPRGL module maintains ray petal length in Gerbera hybrida
by: Rui Jiang, et al.
Published: (2022-04-01) -
FrameAugment: A Simple Data Augmentation Method for Encoder–Decoder Speech Recognition
by: Seong-Su Lim, et al.
Published: (2022-07-01) -
End-to-End High-Level Control of Lower-Limb Exoskeleton for Human Performance Augmentation Based on Deep Reinforcement Learning
by: Ranran Zheng, et al.
Published: (2023-01-01)