BulDML at Institute of Mathematics and Informatics >
IMI Periodicals >
Serdica Journal of Computing >
2014 >
Volume 8 Number 2 >

Please use this identifier to cite or link to this item:

Title: Accent Recognition for Noisy Audio Signals
Authors: Ma, Zichen
Fokoue, Ernest
Keywords: Ill-Posed Problem
Feature Extraction
Mel-Frequency Cepstral Coefficients
Discriminant Analysis
Support Vector Machine
K-Nearest Neighbors
Autoregressive Noise
Issue Date: 2014
Publisher: Institute of Mathematics and Informatics Bulgarian Academy of Sciences
Citation: Serdica Journal of Computing, Vol. 8, No 2, (2014), 169p-182p
Abstract: It is well established that accent recognition can be as accurate as up to 95% when the signals are noise-free, using feature extraction techniques such as mel-frequency cepstral coefficients and binary classifiers such as discriminant analysis, support vector machine and k-nearest neighbors. In this paper, we demonstrate that the predictive performance can be reduced by as much as 15% when the signals are noisy. Specifically, in this paper we perturb the signals with different levels of white noise, and as the noise become stronger, the out-of-sample predictive performance deteriorates from 95% to 80%, although the in-sample prediction gives overly-optimistic results. ACM Computing Classification System (1998): C.3, C.5.1, H.1.2, H.2.4., G.3.
ISSN: 1312-6555
Appears in Collections:Volume 8 Number 2

Files in This Item:

File Description SizeFormat
sjc-vol8-num2-2014-p169-p182.pdf407.04 kBAdobe PDFView/Open


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


Valid XHTML 1.0!   Creative Commons License