A Multiple Regression Model for Predicting Loudspeaker Preference Using Objective Measurements: Part I - Listening Test Results

Olive SE. A Multiple Regression Model for Predicting Loudspeaker Preference Using Objective Measurements: Part I - Listening Test Results. In: AES Convention 116. Audio Engineering Society; 2004. Paper 6113. Available from: https://aes.org/publications/elibrary-page/?id=12794

@inproceedings{Olive2004_12794,
  author = {Olive, Sean E.},
  title = {{A Multiple Regression Model for Predicting Loudspeaker Preference Using Objective Measurements: Part I - Listening Test Results}},
  booktitle = {AES Convention 116},
  note = {Paper 6113},
  year = {2004},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=12794}
}

TY  - CPAPER
TI  - A Multiple Regression Model for Predicting Loudspeaker Preference Using Objective Measurements: Part I - Listening Test Results
AU  - Olive, Sean E.
T2  - AES Convention 116
M1  - Paper 6113
PY  - 2004
DA  - 2004/05/06
UR  - https://aes.org/publications/elibrary-page/?id=12794
PB  - Audio Engineering Society
LA  - en
AB  - Part I of this paper presents the objective measurements and listening test results on 13 loudspeakers rated according to preference, spectral balance and distortion. In part II the data provides the framework for the development and verification of a multiple regression model that predicts listeners? preferences based on objective measurements. We review relevant predictive models and test one model currently used by Consumers Union (CU), a consumer product testing organization in the United States. There is no correlation between listeners? loudspeaker preference ratings and CU?s predicted accuracy scores (r = 0.05; p = .81). As the CU model is based largely on the loudspeaker?s 1/3-octave sound power response we conclude that measured sound power, alone, cannot accurately predict its perceived sound quality.
ER  -