The top MISP 2025 systems achieve DER 8.09%, CER 9.48%, and cpCER 11.56%, far outperforming the provided audio-visual baselines.
A VSD Table 2 presents a summary of the methods and results for Track 1 (Audio-Visual Speaker Diarization) in the MISP 2025 Challenge
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition
The top MISP 2025 systems achieve DER 8.09%, CER 9.48%, and cpCER 11.56%, far outperforming the provided audio-visual baselines.