MODELING TURN-TAKING IN HUMAN-TO-HUMAN SPOKEN DIALOGUE DATASETS USING SELF-SUPERVISED FEATURESEdmilson Da Silva MoraisMatheus Costa Damascenoet al.2023ICASSP 2023
Resource-efficient TDNN Architectures for Audio-visual Speech RecognitionAlexandros KoumparoulisGerasimos Potamianoset al.2021EUSIPCO 2021