Discriminative feature domains for reverberant acoustic environments

File Description SizeFormat 
20160908043424_682890_1059_Final.pdfAccepted version355.89 kBAdobe PDFView/Open
Title: Discriminative feature domains for reverberant acoustic environments
Authors: Papayiannis, C
Evers, C
Naylor, PA
Item Type: Conference Paper
Abstract: Several speech processing and audio data-mining applications rely on a description of the acoustic environment as a feature vector for classification. The discriminative properties of the feature domain play a crucial role in the effectiveness of these methods. In this work, we consider three environment iden- tification tasks and the task of acoustic model selection for speech recognition. A set of acoustic parameters and Ma- chine Learning algorithms for feature selection are used and an analysis is performed on the resulting feature domains for each task. In our experiments, a classification accuracy of 100% is achieved for the majority of tasks and the Word Er- ror Rate is reduced by 20.73 percentage points for Automatic Speech Recognition when using the resulting domains. Ex- perimental results indicate a significant dissimilarity in the parameter choices for the composition of the domains, which highlights the importance of the feature selection process for individual applications.
Issue Date: 19-Jun-2017
Date of Acceptance: 18-Dec-2016
URI: http://hdl.handle.net/10044/1/43617
DOI: https://dx.doi.org/10.1109/ICASSP.2017.7952257
ISSN: 2379-190X
Publisher: IEEE
Journal / Book Title: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)
Copyright Statement: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Commission of the European Communities
Funder's Grant Number: 609465
Conference Name: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Keywords: Science & Technology
Engineering, Electrical & Electronic
Feature Selection
Machine Learning
Environment Identification
Reverberant speech recognition
Publication Status: Published
Start Date: 2017-03-05
Finish Date: 2017-03-09
Conference Place: New Orleans, LA
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons