9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Using Syllable Nuclei Locations to Improve Automatic Speech Recognition in the Presence of Burst Noise

Chris D. Bartels, Jeff A. Bilmes

University of Washington, USA

In this work we combine a conventional phone-based automatic speech recognizer with a classifier that detects syllable locations. This is done using a dynamic Bayesian network. Using oracle syllable detections we achieve a 17% relative reduction in word error rate on the 500 word task of the SVitchboard corpus. Using estimated locations we achieve a 2.1% relative reduction which is significant at the 0.02 level. The improvement in the estimated case is from reducing insertions caused by burst noise.

Full Paper

Bibliographic reference.  Bartels, Chris D. / Bilmes, Jeff A. (2008): "Using syllable nuclei locations to improve automatic speech recognition in the presence of burst noise", In INTERSPEECH-2008, 2406-2409.