Lorenz Diener, Sten Sootla, Marju Purin, Ando Saabas, Robert Aichner, Ross Cutler
Reference:
PLCMOS - a data-driven non-intrusive metric for the evaluation of packet loss concealment algorithms (Lorenz Diener, Sten Sootla, Marju Purin, Ando Saabas, Robert Aichner, Ross Cutler), at INTERSPEECH 2023 - 23nd Annual Conference of the International Speech Communication Association, August 2023
Bibtex Entry:
@inproceedings{diener2023plcmos,
title = {PLCMOS - a data-driven non-intrusive metric for the evaluation of packet loss
concealment algorithms},
author = {Diener, Lorenz and Sootla, Sten and Purin, Marju and Saabas, Ando and Aichner,
Robert and Cutler, Ross},
year = 2023,
month = aug,
booktitle = {{INTERSPEECH} 2023 - 23nd Annual Conference of the International Speech
Communication Association},
abstract = {Speech quality assessment is a problem for every researcher working on models that
produce or process speech. Human subjective ratings, the gold standard in speech quality
assessment, are expensive and time-consuming to acquire in a quantity that is sufficient to get
reliable data, while automated objective metrics show a low correlation with gold standard
ratings. This paper presents PLCMOS, a non-intrusive data-driven tool for generating a robust,
accurate estimate of the mean opinion score a human rater would assign an audio file that has
been processed by being transmitted over a degraded packet-switched network with missing packets
being healed by a packet loss concealment algorithm. Our new model shows a model-wise Pearson's
correlation of ~0.97 and rank correlation of ~0.95 with human ratings, substantially above all
other available intrusive and non-intrusive metrics. The model is released as an ONNX model for
other researchers to use when building PLC systems.},
doi = {10.21437/Interspeech.2023-1532},
code = {https://aka.ms/plcmos},
url = {https://halcy.de/cites/pdf/diener2023plcmos.pdf},
poster = {https://halcy.de/cites/pdf/diener2023plcmos_poster.pdf},
}