Using Context to Correct Phone Recognition Errors

Cox, S. J. (2004) Using Context to Correct Phone Recognition Errors. In: 8th International Conference on Spoken Language Processing (Interspeech 2004), 2004-10-04 - 2004-10-08.

Full text not available from this repository. (Request a copy)


There are many circumstances in which it is useful or necessary to recognise phones rather than words, but phone recognition is inherently less accurate than word recognition. We describe here a post-recognition method for "translating" an errorful phone string output by a speech recogniser into a string that more closely matches the transcription. The technique owes something to Kohonen's idea of "dynamically expanding context" in that it learns from the errors made by the recogniser in a particular context, but it uses many contexts rather than a single context to estimate the "translation" of a recognised phone. The weights given to the different contexts in estimating the translation are determined discriminatively. On the WSJCAM0 database, the technique gives a 19.2% relative improvement in phone errors (including insertions) over the baseline, compared with a 6.2% improvement obtained using dynamically expanding context.

Item Type: Conference or Workshop Item (Paper)
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Interactive Graphics and Audio
Faculty of Science > Research Groups > Smart Emerging Technologies
Depositing User: Vishal Gautam
Date Deposited: 14 Jun 2011 18:15
Last Modified: 22 Apr 2023 02:46

Actions (login required)

View Item View Item