Advanced

Using cepstral coefficients for Inhalation pause detection in spontaneous speech

Sjöström, Anders LU ; Frid, Johan LU and Horne, Merle LU (2005) SPECOM 2005 In Proceedings of SPECOM 2005 1. p.143-146
Abstract
A method for recognizing inhalations in spontaneous speech is presented. It is similar to the template matching technique; a distance measure is calculated between a reference sound and an equally long portion of the same sound being tracked. A feature representation consisting of the standard Mel Frequency Cepstral Coefficients (MFCC), obtained by performing a discrete Cosine Transform of the mel-scaled filterbank spectrum is used. MFCC's are calculated every 5 ms. The comparison is then done by computing the euclidian distance between the cepstral coefficients of each frame of the two sounds. A low distance value means that the two compared inhalations are likely to be similar. The method can detect inhalations in both male and female... (More)
A method for recognizing inhalations in spontaneous speech is presented. It is similar to the template matching technique; a distance measure is calculated between a reference sound and an equally long portion of the same sound being tracked. A feature representation consisting of the standard Mel Frequency Cepstral Coefficients (MFCC), obtained by performing a discrete Cosine Transform of the mel-scaled filterbank spectrum is used. MFCC's are calculated every 5 ms. The comparison is then done by computing the euclidian distance between the cepstral coefficients of each frame of the two sounds. A low distance value means that the two compared inhalations are likely to be similar. The method can detect inhalations in both male and female spontaneous speech. The method is most suited for signals with low noise and high average intensity (studio recording) but can also be used on noisier recordings with lower average intensity, albeit with poorer results. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
breathing pauses, inhalations, inhalation pause, cepstral coefficient, pause, spontaneous speech
in
Proceedings of SPECOM 2005
editor
Kokkinakis, G.; Fakotakis, N.; Dermatas, E. and Potapova, R.
volume
1
pages
143 - 146
publisher
University of Patras
conference name
SPECOM 2005
ISBN
5-7452-0110-x
project
The role of function words in spontaneous speech processing
language
English
LU publication?
yes
id
00d5c301-2936-459b-b010-ac810a221d57 (old id 534544)
date added to LUP
2007-09-20 11:44:23
date last changed
2016-04-16 10:01:22
@inproceedings{00d5c301-2936-459b-b010-ac810a221d57,
  abstract     = {A method for recognizing inhalations in spontaneous speech is presented. It is similar to the template matching technique; a distance measure is calculated between a reference sound and an equally long portion of the same sound being tracked. A feature representation consisting of the standard Mel Frequency Cepstral Coefficients (MFCC), obtained by performing a discrete Cosine Transform of the mel-scaled filterbank spectrum is used. MFCC's are calculated every 5 ms. The comparison is then done by computing the euclidian distance between the cepstral coefficients of each frame of the two sounds. A low distance value means that the two compared inhalations are likely to be similar. The method can detect inhalations in both male and female spontaneous speech. The method is most suited for signals with low noise and high average intensity (studio recording) but can also be used on noisier recordings with lower average intensity, albeit with poorer results.},
  author       = {Sjöström, Anders and Frid, Johan and Horne, Merle},
  booktitle    = {Proceedings of SPECOM 2005},
  editor       = {Kokkinakis, G. and Fakotakis, N. and Dermatas, E. and Potapova, R.},
  isbn         = {5-7452-0110-x},
  keyword      = {breathing pauses,inhalations,inhalation pause,cepstral coefficient,pause,spontaneous speech},
  language     = {eng},
  pages        = {143--146},
  publisher    = {University of Patras},
  title        = {Using cepstral coefficients for Inhalation pause detection in spontaneous speech},
  volume       = {1},
  year         = {2005},
}