An Auditory Model-Inspired Objective Speech Intelligibility Estimate for Audio Systems

Datta J, Zhou X, Begin J, Martin M. An Auditory Model-Inspired Objective Speech Intelligibility Estimate for Audio Systems. In: AES Convention 144. Audio Engineering Society; 2018. Paper 9918. Available from: https://aes.org/publications/elibrary-page/?id=19435

@inproceedings{Datta2018_19435,
  author = {Datta, Jayant and Zhou, Xinhui and Begin, Joe and Martin, Mark},
  title = {{An Auditory Model-Inspired Objective Speech Intelligibility Estimate for Audio Systems}},
  booktitle = {AES Convention 144},
  note = {Paper 9918},
  year = {2018},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19435}
}

TY  - CPAPER
TI  - An Auditory Model-Inspired Objective Speech Intelligibility Estimate for Audio Systems
AU  - Datta, Jayant
AU  - Zhou, Xinhui
AU  - Begin, Joe
AU  - Martin, Mark
T2  - AES Convention 144
M1  - Paper 9918
PY  - 2018
DA  - 2018/05/06
UR  - https://aes.org/publications/elibrary-page/?id=19435
PB  - Audio Engineering Society
LA  - en
AB  - Compared with subjective tests, objective measures save time and money. This paper presents the implementation of a new algorithm for objective speech intelligibility, based on the modified rhyme test using real speech. An auditory-model inspired signal processing framework approach gathers word selection evidence in auditory filter bank correlations and then uses an auditory attention model to perform word selection. It has been shown to outperform popular measures in terms of Pearson correlation coefficient to the human intelligibility scores. A real-time version of this approach has been integrated into a versatile audio test and measurement system supporting a number of interfaces (different combinations of devices/channels/systems). Examples and measurement results will be presented to show the advantages of this approach.
ER  -