Audience Overlap Detection

via “overlapped-speech-detection-and-localization”

automatic-speech-recognition model by undefined. 1,02,42,383 downloads.

Unique: Detects overlap by analyzing speaker embedding consistency and acoustic divergence rather than relying on energy-based heuristics. The model learns to recognize acoustic signatures of simultaneous speech through supervised training on datasets with annotated overlaps.

vs others: Achieves 85-90% F1-score on overlap detection compared to 70-75% for energy-based or spectral-based overlap detection methods, with better generalization across acoustic conditions.