Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech

Mizumachi M. Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech. In: AES Convention 137. Audio Engineering Society; 2014. Paper 9171. Available from: https://aes.org/publications/elibrary-page/?id=17494

@inproceedings{Mizumachi2014_17494,
  author = {Mizumachi, Mitsunori},
  title = {{Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech}},
  booktitle = {AES Convention 137},
  note = {Paper 9171},
  year = {2014},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17494}
}

TY  - CPAPER
TI  - Applicability of Perceptual Evaluation of Speech Quality in Evaluating Heavily Distorted Speech
AU  - Mizumachi, Mitsunori
T2  - AES Convention 137
M1  - Paper 9171
PY  - 2014
DA  - 2014/10/06
UR  - https://aes.org/publications/elibrary-page/?id=17494
PB  - Audio Engineering Society
LA  - en
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.
ER  -