Timestamp-aligning and keyword-biasing end-to-end ASR front-end for a KWS system

Abstract Many end-to-end approaches have been proposed to detect predefined keywords. For scenarios of multi-keywords, there are still two bottlenecks that need to be resolved: (1) the distribution of important data that contains keyword(s) is sparse, and (2) the timestamps of the detected keywords...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Gui-Xin Shi, Wei-Qiang Zhang, Guan-Bo Wang, Jing Zhao, Shu-Zhou Chai, Ze-Yu Zhao
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	SpringerOpen 2021-07-01
Цуврал:	EURASIP Journal on Audio, Speech, and Music Processing
Нөхцлүүд:	OpenSAT20 End-to-end ASR End-to-end KWS Force alignment Biased loss
Онлайн хандалт:	https://doi.org/10.1186/s13636-021-00212-9
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!