Paper: Analysing Recognition Errors in Unlimited-Vocabulary Speech Recognition

ACL ID N09-2049
Title Analysing Recognition Errors in Unlimited-Vocabulary Speech Recognition
Venue Human Language Technologies
Session Short Paper
Year 2009
Authors

We analyze the recognition errors made by a morph-based continuous speech recognition system, which practically allows an unlim- ited vocabulary. Examining the role of the acoustic and language models in erroneous regions shows how speaker adaptive training (SAT) and discriminative training with mini- mum phone frame error (MPFE) criterion de- crease errors in different error classes. An- alyzing the errors with respect to word fre- quencies and manually classified error types reveals the most potential areas for improving the system.