A Framework for Predicting Speech Quality Using Detectability of Multiple Distortions

Lu W, Sen D. A Framework for Predicting Speech Quality Using Detectability of Multiple Distortions. In: AES Conference: 38th International Conference: Sound Quality Evaluation. Audio Engineering Society; 2010. Paper 1-4. Available from: https://aes.org/publications/elibrary-page/?id=15463

@inproceedings{Lu2010_15463,
  author = {Lu, Wenliang and Sen, D.},
  title = {{A Framework for Predicting Speech Quality Using Detectability of Multiple Distortions}},
  booktitle = {AES Conference: 38th International Conference: Sound Quality Evaluation},
  note = {Paper 1-4},
  year = {2010},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15463}
}

TY  - CPAPER
TI  - A Framework for Predicting Speech Quality Using Detectability of Multiple Distortions
AU  - Lu, Wenliang
AU  - Sen, D.
T2  - AES Conference: 38th International Conference: Sound Quality Evaluation
M1  - Paper 1-4
PY  - 2010
DA  - 2010/06/06
UR  - https://aes.org/publications/elibrary-page/?id=15463
PB  - Audio Engineering Society
LA  - en
AB  - This paper proposes a framework for predicting overall speech quality using a multi-dimensional analysis of individual distortions. The algorithm makes use of a physiologically motivated hydro-mechanical Cochlear Model to convert the speech signal into a domain that is more representative of what is perceived. Salient features are extracted and compared between the original and degraded representations to analyze the detectability of individual distortions. These are subsequently combined to predict overall quality.
ER  -