OpenCodePapers

speaker-diarization-on-callhome-part2-two-speaker

Speaker RecognitionSpeaker Diarization
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeDERModelNameReleaseDate
TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization✓ Link5.73TOLD (EEND-OLA + SOAP)2023-03-08
Sortformer: Seamless Integration of Speaker Diarization and ASR by Bridging Timestamps and Tokens✓ Link5.87Sortformer-Hybrid-Loss (123M, post-processing)2024-09-10
From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarization✓ Link7.28EEND-EDA (SC2 training + fine-tuning)2022-04-02
DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors✓ Link7.51DiaPer 10-attractor + CALLHOME 2-speaker FT2023-12-07
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors✓ Link8.07SA-EEND + EDA (shuffled, two-speaker training)2020-05-20
End-to-End Neural Speaker Diarization with Self-attention✓ Link10.76SA-EEND (real training, domain-adapted)2019-09-13
End-to-End Neural Speaker Diarization with Permutation-Free Objectives✓ Link23.07BLSTM-EEND (real training, domain-adapted)2019-09-12
Check out how to contribute new results. Then edit this file on GitLab or GitHub.