Audio-visual keyword transformer for unconstrained sentence-level keyword spotting

Li, YD; Ren, JL; Wang, YW; Wang, GQ; Li, X; Liu, H

Ren, JL (通讯作者),Peking Univ, Shenzhen Grad Sch, Key Lab Machine Percept, Shenzhen, Peoples R China.

CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2023; ():

Abstract

As one of the most effective methods to improve the accuracy and robustness of speech tasks, the audio-visual fusion approach has recently been introd......

Full Text Link