Arabic Speech Recognition Based on Encoder-Decoder Architecture of Transformer

Recognizing and transcribing human speech has become an increasingly important task. Recently, researchers have been more interested in automatic speech recognition (ASR) using End to End models. Previous choices for the Arabic ASR architecture have been time-delay neural networks, recurrent neural...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Mohanad Sameer, Ahmed Talib, Alla Hussein, Husniza Husni
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	middle technical university 2023-03-01
Цуврал:	Journal of Techniques
Нөхцлүүд:	Sequence to Sequence ASR Arabic ASR Transformer-Speech Recognition Arabic Speech to Text
Онлайн хандалт:	https://journal.mtu.edu.iq/index.php/MTU/article/view/749
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!