@inproceedings{Papayiannis:2017:10.1109/ICASSP.2017.7952257,
author = {Papayiannis, C and Evers, C and Naylor, PA},
doi = {10.1109/ICASSP.2017.7952257},
publisher = {IEEE},
title = {Discriminative feature domains for reverberant acoustic environments},
url = {http://dx.doi.org/10.1109/ICASSP.2017.7952257},
year = {2017}
}

Download

TY  - CPAPER
AB  - Several speech processing and audio data-mining applicationsrely on a description of the acoustic environment as a featurevector for classification.  The discriminative properties of thefeature domain play a crucial role in the effectiveness of thesemethods.  In this work, we consider three environment iden-tification tasks and the task of acoustic model selection forspeech  recognition.   A  set  of  acoustic  parameters  and  Ma-chine Learning algorithms for feature selection are used andan analysis is performed on the resulting feature domains foreach  task.   In  our  experiments,  a  classification  accuracy  of100% is achieved for the majority of tasks and the Word Er-ror Rate is reduced by 20.73 percentage points for AutomaticSpeech Recognition when using the resulting domains.  Ex-perimental  results  indicate  a  significant  dissimilarity  in  theparameter choices for the composition of the domains, whichhighlights the importance of the feature selection process forindividual applications.
AU  - Papayiannis,C
AU  - Evers,C
AU  - Naylor,PA
DO  - 10.1109/ICASSP.2017.7952257
PB  - IEEE
PY  - 2017///
SN  - 2379-190X
TI  - Discriminative feature domains for reverberant acoustic environments
UR  - http://dx.doi.org/10.1109/ICASSP.2017.7952257
UR  - http://hdl.handle.net/10044/1/43617
ER  - 

Download