Class Wise Segmentation Confidence Scoring

via “confidence-scored speech segmentation with temporal boundaries”

automatic-speech-recognition model by undefined. 23,46,228 downloads.

Unique: Converts frame-level neural predictions into segment-level output with learned confidence scoring rather than simple thresholding; confidence reflects model uncertainty and can be calibrated per domain through post-hoc scaling

vs others: More interpretable than raw frame predictions and enables quality filtering; more flexible than fixed-threshold segmentation by providing confidence-based filtering options