Youngki Kwon

speaker verification (3) self-supervised learning (3) speaker recognition (2) speaker diarisation (2) speaker diarization (2) speech detection (1) convolutional neural network (1) recurrent neural network (1) cross-domain evaluation (1) equal error rate (1) overlapped speech (1) active speaker detection (1) raw waveform (1) face tracking (1) dimensionality reduction (1) relational mask prediction (1) semi-supervised learning (1) face detection (1) attention mechanism (1) speaker embedding (1)