초록
영어
Confusion network (CN) is an aligned and compact representation form of word lattice that
stores median results of decoding procedure and connects the acoustic decoding and succeeding process steps. The quality of confusion network is very important for multi‐pass decoding based recognition method. Three new quality evaluation measures are proposed for confusion network in this paper. The first is called confusion network word error rate (CWER), which gives a lower bound of recognition word error rate. The second is used to measure the size of confusion set, called confusion word density (CWD). The third is word confusion probability (WCP), which can measure average distinguishability between words
in a confusion set. Based on the proposed measures, we present a new method of quality
optimization for confusion network, called as confusion probability based pruning algorithm.
The experiments, carried out on a large vocabulary Chinese continuous speech recognition
system, demonstrate that the new method leads to a significant reduction in CWD and WCP
without an increase of CWER.
목차
1. Introduction
2. Quality evaluation measure for CN
2.1 Quality evaluation measure for word lattice
2.2 Quality evaluation measure proposed for CN
3. Confusion probability based pruningalgorithm for CN
4. Experiments and evaluation
4.1 Test condition
4.2 Experimental result and analysis
5. Conclusion
References