Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech
×
Cite This
Citation & Abstract
M. Mizumachi, "Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech," Paper 9171, (2014 October.). doi:
M. Mizumachi, "Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech," Paper 9171, (2014 October.). doi:
Abstract: Speech quality assessment is indispensable to properly design a speech enhancement algorithm. The perceptual evaluation of speech quality (PESQ) is frequently employed as an objective speech distortion measure. The PESQ is a methodology for estimating subjective assessment of speech quality assuming a slight distortion caused by speech codecs for telephony systems. In case of noise reduction, however, a degree of speech distortion is heavier than those caused by the speech codecs. In this paper applicability of the PESQ is investigated for noisy and noise-reduced speech signals under severe noisy conditions. A relationship between PESQ scores and subjective mean opinion scores reveals that the PESQ can be applicable for heavily distorted speech only under non-stationary noisy conditions.
@article{mizumachi2014applicability,
author={mizumachi, mitsunori},
journal={journal of the audio engineering society},
title={applicability of perceptual evaluation of speech quality in evaluating heavily distorted speech},
year={2014},
volume={},
number={},
pages={},
doi={},
month={october},}
@article{mizumachi2014applicability,
author={mizumachi, mitsunori},
journal={journal of the audio engineering society},
title={applicability of perceptual evaluation of speech quality in evaluating heavily distorted speech},
year={2014},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={speech quality assessment is indispensable to properly design a speech enhancement algorithm. the perceptual evaluation of speech quality (pesq) is frequently employed as an objective speech distortion measure. the pesq is a methodology for estimating subjective assessment of speech quality assuming a slight distortion caused by speech codecs for telephony systems. in case of noise reduction, however, a degree of speech distortion is heavier than those caused by the speech codecs. in this paper applicability of the pesq is investigated for noisy and noise-reduced speech signals under severe noisy conditions. a relationship between pesq scores and subjective mean opinion scores reveals that the pesq can be applicable for heavily distorted speech only under non-stationary noisy conditions.},}
TY - paper
TI - Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech
SP -
EP -
AU - Mizumachi, Mitsunori
PY - 2014
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2014
TY - paper
TI - Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech
SP -
EP -
AU - Mizumachi, Mitsunori
PY - 2014
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2014
AB - Speech quality assessment is indispensable to properly design a speech enhancement algorithm. The perceptual evaluation of speech quality (PESQ) is frequently employed as an objective speech distortion measure. The PESQ is a methodology for estimating subjective assessment of speech quality assuming a slight distortion caused by speech codecs for telephony systems. In case of noise reduction, however, a degree of speech distortion is heavier than those caused by the speech codecs. In this paper applicability of the PESQ is investigated for noisy and noise-reduced speech signals under severe noisy conditions. A relationship between PESQ scores and subjective mean opinion scores reveals that the PESQ can be applicable for heavily distorted speech only under non-stationary noisy conditions.
Speech quality assessment is indispensable to properly design a speech enhancement algorithm. The perceptual evaluation of speech quality (PESQ) is frequently employed as an objective speech distortion measure. The PESQ is a methodology for estimating subjective assessment of speech quality assuming a slight distortion caused by speech codecs for telephony systems. In case of noise reduction, however, a degree of speech distortion is heavier than those caused by the speech codecs. In this paper applicability of the PESQ is investigated for noisy and noise-reduced speech signals under severe noisy conditions. A relationship between PESQ scores and subjective mean opinion scores reveals that the PESQ can be applicable for heavily distorted speech only under non-stationary noisy conditions.
Author:
Mizumachi, Mitsunori
Affiliation:
Kyushu Institute of Technology, Kitakyushu, Fukuoka, Japan
AES Convention:
137 (October 2014)
Paper Number:
9171
Publication Date:
October 8, 2014Import into BibTeX
Subject:
Applications in Audio
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=17494