A confidence-guided dynamic pruning approach - utilization of confidence measurement in speech recognition

@inproceedings{Fbin2005ACD,
  title={A confidence-guided dynamic pruning approach - utilization of confidence measurement in speech recognition},
  author={Tibor F{\'a}bi{\'a}n and Robert Lieb and G{\"u}nther Ruske and Matthias Thomae},
  booktitle={INTERSPEECH},
  year={2005}
}
Improved efficiency of pruning accelerates the search process and leads to a more time efficient speech recognition system. The goal of this work was to develop a new pruning technique which optimizes the well known probability-based pruning (beam width) by utilization of confidence measurement. We use normalized hypotheses scores to guide the beam width of… CONTINUE READING