Towards a Virtual Listener Panel for Car Audio System Evaluation

Vlasov R, Shishalov I, Filimonov A, Johansson M. Towards a Virtual Listener Panel for Car Audio System Evaluation. In: 2026 AES 6th International Automotive Audio Conference. Audio Engineering Society; 2026. Paper 26. Available from: https://aes.org/publications/elibrary-page/?id=23419

@inproceedings{Vlasov2026_23419,
  author = {Vlasov, Roman and Shishalov, Ivan and Filimonov, Andrey and Johansson, Mathias},
  title = {{Towards a Virtual Listener Panel for Car Audio System Evaluation}},
  booktitle = {2026 AES 6th International Automotive Audio Conference},
  note = {Paper 26},
  year = {2026},
  month = jul,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23419}
}

TY  - CPAPER
TI  - Towards a Virtual Listener Panel for Car Audio System Evaluation
AU  - Vlasov, Roman
AU  - Shishalov, Ivan
AU  - Filimonov, Andrey
AU  - Johansson, Mathias
T2  - 2026 AES 6th International Automotive Audio Conference
M1  - Paper 26
PY  - 2026
DA  - 2026/07/29
UR  - https://aes.org/publications/elibrary-page/?id=23419
PB  - Audio Engineering Society
LA  - en
AB  - We propose a machine-learning method that predicts trained-listener panel ratings of vehicle audio systems from in-situ microphone-array measurements. Using a dataset collected over more than 10 years from 1177 vehicle audio systems, the model is trained to predict listener-score distributions, not only mean scores, for subjective sound-quality attributes on a 110 scale. In this paper we focus on the timbral/spectral attribute and evaluate performance on a held-out set of 237 systems. Results show that prediction accuracy improves consistently with dataset size and that distribution-aware modelling captures not only expected score level but also listener disagreement and uncertainty. The study highlights both the feasibility of virtual listener panels and the importance of large-scale, reliable benchmarking data.
ER  -