Speaker recognition/identification/diarization

MULTI-SPEAKER AND WIDE-BAND SIMULATED CONVERSATIONS AS TRAINING DATA FOR END-TO-END NEURAL DIARIZATION

Improving learning objectives for speaker verification from the perspective of score comparison

Short-segment speaker verification using ECAPA-TDNN with multi-resolution encoder

Frame-wise and overlap-robust speaker embeddings for meeting diarization

EFFECTIVE GRAPH-BASED MODELING OF ARTICULATION TRAITS FOR MISPRONUNCIATION DETECTION AND DIAGNOSIS

Can spoofing countermeasure and speaker verification systems be jointly optimised?

Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activity

SAN: a robust end-to-end ASR model architecture