Establishing a Virtual Listener Panel for audio characterisation

Herlufsen M, Fuglsang NA, Pedersen B. Establishing a Virtual Listener Panel for audio characterisation. In: 2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio. Audio Engineering Society; 2025. Paper 25. Available from: https://aes.org/publications/elibrary-page/?id=23014

@inproceedings{Herlufsen2025_23014,
  author = {Herlufsen, Michelle and Fuglsang, Niels Asp and Pedersen, Benjamin},
  title = {{Establishing a Virtual Listener Panel for audio characterisation}},
  booktitle = {2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio},
  note = {Paper 25},
  year = {2025},
  month = sep,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23014}
}

TY  - CPAPER
TI  - Establishing a Virtual Listener Panel for audio characterisation
AU  - Herlufsen, Michelle
AU  - Fuglsang, Niels Asp
AU  - Pedersen, Benjamin
T2  - 2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio
M1  - Paper 25
PY  - 2025
DA  - 2025/09/02
UR  - https://aes.org/publications/elibrary-page/?id=23014
PB  - Audio Engineering Society
LA  - en
AB  - Listening test are usually time-consuming and costly. Maintaining a panel of highly trained assessors requires significant resources. This study introduces a neural network model, the Virtual Listener Panel, trained using Convolutional Neural Network to overcome these challenges. The focus in this study has been to predict expert ratings for audio characterisation using deep learning. This paper describes the architecture of the proposed model and the data collection approach that was established to achieve high prediction accuracy. The performance of the Virtual Listener Panel is compared with data from an independent listening test where seven different earbuds were characterised by 20 trained expert assessors. Five audio characterisation attributes from the timbre domain are validated: bass strength, bass depth, midrange strength, treble strength and brilliance. The result of this study demonstrates Pearson correlation coefficients between 0.80 and 0.97. The Virtual Listener Panel offers a scalable solution for audio characterisation, reducing the need for extensive listening tests and providing valuable insights for product development.
ER  -