Please use this identifier to cite or link to this item:
|Title:||Automatic detection and removal of disfluencies from spontaneous speech|
|Citation:||Proceedings of the 13th Australasian International Conference on Speech Science and Technology held in Melbourne, Victoria 14-16 December 2010 / M. Tabain, J. Fletcher, D. Grayden, J. Hajek and A. Butcher (eds.): pp.98-101|
|Conference Name:||Australasian International Conference on Speech Science and Technology (13th : 2010 : Melbourne, Victoria)|
|Mayank Kaushik, Matthew Trinkle and Ahmad Hashemi-Sakhtsari|
|Abstract:||Unlike rehearsed and prepared speech, spontaneous speech contains high occurrence of disfluencies, like repetitions, filled pauses, and hesitations. Disfluencies can seriously hamper the word recognition accuracy of an Automatic Speech Recogniser (ASR), by increasing word insertion and deletion and rejection rates. In this paper we introduce signal processing algorithms to automatically identify and remove repetitions and filled pauses from spontaneous speech before passing it to an ASR for transcription. The algorithms are tested with Dragon NaturallySpeaking Speech Recogniser and show significant improvements in the word recognition accuracy, and ensuing reductions in substitution and deletion and insertion errors.|
|Keywords:||Automatic Speech Recognition|
|Rights:||Copyright 2010 ASSTA|
|Appears in Collections:||Aurora harvest 5|
Electrical and Electronic Engineering publications
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.