Incremental learning for end-to-end automatic speech recognition

L Fu, X Li, L Zi, Z Zhang, Y Wu, X He… - 2021 IEEE Automatic …, 2021 - ieeexplore.ieee.org
In this paper, we propose an incremental learning method for end-to-end Automatic Speech
Recognition (ASR) which enables an ASR system to perform well on new tasks while …

Decoupling recognition and transcription in mandarin asr

J Yuan, X Cai, D Gao, R Zheng… - 2021 IEEE Automatic …, 2021 - ieeexplore.ieee.org
Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end
approach. Unlike English where the writing system is closely related to sound, Chinese …

[PDF][PDF] Multilingual speech recognition based on the end-to-end framework

S Liang, W Yan - Multimedia Tools and Applications, 2022 - cerv.aut.ac.nz
Speech recognition is an important field in natural language processing. In this paper, the
end-to-end framework for speech recognition with multilingual datasets is proposed. The …

On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR

Z Yang, D Ng, X Fu, L Han, W Xi, R Wang… - arXiv preprint arXiv …, 2022 - arxiv.org
End-to-end automatic speech recognition (ASR) has achieved promising results. However,
most existing end-to-end ASR methods neglect the use of specific language characteristics …

A high-performance brain-sentence communication designed for logosyllabic language

C Feng, L Cao, D Wu, E Zhang, T Wang, X Jiang… - bioRxiv, 2023 - biorxiv.org
Many severe neurological diseases, such as stroke and amyotrophic lateral sclerosis, can
impair or destroy the ability of verbal communication. Recent advances in brain-computer …

Multi-language datasets for speech recognition based on the end-to-end framework

S Liang - 2021 - openrepository.aut.ac.nz
In this thesis, the end-to-end framework for speech recognition is probed with multilanguage
datasets. The focus of this thesis is on the end-to-end framework. Our objective is to improve …