Sciweavers

Share
ICASSP
2008
IEEE

Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments

9 years 6 months ago
Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments
Automatic Speech Recognition (ASR) systems continue to make errors during search when handling various phenomena including noise, pronunciation variation, and out of vocabulary (OOV) words. Predicting the probability that a word is incorrect can prevent the error from propagating and perhaps allow the system to recover. This paper addresses the problem of detecting errors and OOVs for read Wall Street Journal speech when the word error rate (WER) is very low. It augments a traditional confidence estimate by introducing two novel methods: phone-level comparison using Multi-String Alignment (MSA) and word-level comparison using phone-to-word transduction. We show that features from phone and word string comparisons can be added to a standard maximum entropy framework thereby substantially improving performance in detecting both errors and OOVs. Additionally we show an extension to detecting English and accented English for the Language Identification (LID) task.
Christopher M. White, Geoffrey Zweig, Lukas Burget
Added 30 May 2010
Updated 30 May 2010
Type Conference
Year 2008
Where ICASSP
Authors Christopher M. White, Geoffrey Zweig, Lukas Burget, Petr Schwarz, Hynek Hermansky
Comments (0)
books