Objective quality assessment of speech enhancement algorithms using bootstrap-based multiple hypotheses tests

In this paper bootstrap resampling techniques are applied to assess speech quality and thereby evaluate performance of distinct speech enhancement algorithms, under the assumption that the speech segments can be approximated by an autoregressive model. A bootstrap-based multiple hypotheses testing p...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhihua Lu, Heidenreich, Philipp, Zoubir, Abdelhak M
Format: Conference Proceeding
Language:English
Subjects:
Bootstrap
Linear predictive coding
multiple hypothesis testing
Quality assessment
Sea measurements
Signal processing
Signal processing algorithms
Speech analysis
Speech coding
Speech enhancement
Speech processing
speech signal processing
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper bootstrap resampling techniques are applied to assess speech quality and thereby evaluate performance of distinct speech enhancement algorithms, under the assumption that the speech segments can be approximated by an autoregressive model. A bootstrap-based multiple hypotheses testing procedure is constructed to test a distance measure based on linear predictive coding, which is the log-likelihood ratio distance. It is shown that the multiple hypotheses test results correlate well with conventional numerical distance measures, which suggests the applicability of the proposed procedure in assessment of speech quality as well as speech enhancement algorithms.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2010.5495741