Speaker verification and anti-spoofing

Improving Transformer-Based Networks with Locality for Automatic Speaker Verification

Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline

Predictive SkiM: Contrastive Predictive Coding for Low-Latency Online Speech Separation

Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit

GRAPH-BASED SPECTRO-TEMPORAL DEPENDENCY MODELING FOR ANTI-SPOOFING

Leveraging Positional-Related Local-Global Dependency for Synthetic Speech Detection

UNIVERSAL SPEAKER RECOGNITION ENCODERS FOR DIFFERENT SPEECH SEGMENTS DURATION

High-resolution embedding extractor for speaker diarisation

Waveform Boundary Detection for Partially Spoofed Audio

Simultaneous Acoustic Echo Sorting and 3-D Room Geometry Inference

ASSD: SYNTHETIC SPEECH DETECTION IN THE AAC COMPRESSED DOMAIN

ROBUST SELF-GUIDED DEEP IMAGE PRIOR