In this section
@article{Sharma:2016:10.1016/j.specom.2016.03.005,
author = {Sharma, D and Naylor, PA and Wang, Y and Brookes, DM},
doi = {10.1016/j.specom.2016.03.005},
journal = {Speech Communication},
pages = {84--94},
title = {A Data-Driven Non-intrusive Measure of Speech Quality and Intelligibility},
url = {http://dx.doi.org/10.1016/j.specom.2016.03.005},
volume = {80},
year = {2016}
}
TY - JOUR
AB - Speech signals are often affected by additive noiseand distortion which can degrade the perceived quality andintelligibility of the signal. We present a new measure, NISA, forestimating the quality and intelligibility of speech degraded byadditive noise and distortions associated with telecommunicationsnetworks, based on a data driven framework of feature extractionand tree based regression. The new measure is non-intrusive,operating on the degraded signal alone without the need for areference signal. This makes the measure applicable to practicalspeech processing applications operating in the single-endedmode. The new measure has been evaluated against the intrusivemeasures PESQ and STOI. The results indicate that the accuracyof the new non-intrusive method is around 90% of the accuracy ofthe intrusive measures, depending on the test scenario. The NISAmeasure therefore provides non-intrusive (single-ended) PESQand STOI estimates with high accuracy.
AU - Sharma,D
AU - Naylor,PA
AU - Wang,Y
AU - Brookes,DM
DO - 10.1016/j.specom.2016.03.005
EP - 94
PY - 2016///
SN - 0167-6393
SP - 84
TI - A Data-Driven Non-intrusive Measure of Speech Quality and Intelligibility
T2 - Speech Communication
UR - http://dx.doi.org/10.1016/j.specom.2016.03.005
UR - http://hdl.handle.net/10044/1/31932
VL - 80
ER -
Speech and Audio Processing Lab
CSP Group, EEE Department
Imperial College London
Exhibition Road, London, SW7 2AZ, United Kingdom