loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Seventh IEEE/ACIS International Conference on Computer and Information Science (icis 2008)
A Novel Detection Method of Filled Pause in Mandarin Spontaneous Speech
May 14-May 16
ISBN: 978-0-7695-3131-1
ASCII Text
x 
 
Yan-Xiong Li, Qian-Hua He, Tao Li, "A Novel Detection Method of Filled Pause in Mandarin Spontaneous Speech," Computer and Information Science, ACIS International Conference on, pp. 217-222, Seventh IEEE/ACIS International Conference on Computer and Information Science (icis 2008), 2008.
 
 
BibTex
x
 
@article{ 10.1109/ICIS.2008.26,
author = {Yan-Xiong Li and Qian-Hua He and Tao Li},
title = {A Novel Detection Method of Filled Pause in Mandarin Spontaneous Speech},
journal ={Computer and Information Science, ACIS International Conference on},
volume = {0},
year = {2008},
isbn = {978-0-7695-3131-1},
pages = {217-222},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICIS.2008.26},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Computer and Information Science, ACIS International Conference on
TI - A Novel Detection Method of Filled Pause in Mandarin Spontaneous Speech
SN - 978-0-7695-3131-1
SP217
EP222
A1 - Yan-Xiong Li,
A1 - Qian-Hua He,
A1 - Tao Li,
PY - 2008
KW - spontaneous speech recognition
KW - filled pause detection
KW - non-speech events
VL - 0
JA - Computer and Information Science, ACIS International Conference on
ER -
 
Filled pause is one of the hesitation phenomena that current speech recognizers can not effectively handle. Detecting filled pauses is important in spontaneous speech dialogue systems because they play valuable roles, such as helping a speaker keep a conversational turn, in oral communication. In this paper, a novel detection method for filled pause is proposed based on a strategy of two-level decisions. Firstly, hypothetical filled pauses are extracted from non-silence signal segments. Then HMMs are trained and employed to recognize filled pauses from hypothetical filled pauses. Experiment results show that the average precision and recall rate of filled pauses are 80.66% and 92.59% respectively. Moreover, this filled pause detector can distinguish filled pauses from elongated words, which are not achieved in the previous works.
Index Terms:
spontaneous speech recognition, filled pause detection, non-speech events
Citation:
Yan-Xiong Li, Qian-Hua He, Tao Li, "A Novel Detection Method of Filled Pause in Mandarin Spontaneous Speech," icis, pp.217-222, Seventh IEEE/ACIS International Conference on Computer and Information Science (icis 2008), 2008
Usage of this product signifies your acceptance of the Terms of Use.