A Machine Learning approach to modal control in small rooms

Bolla C, Cox T, Fazenda B. A Machine Learning approach to modal control in small rooms. In: 2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio. Audio Engineering Society; 2025. Paper 26. Available from: https://aes.org/publications/elibrary-page/?id=23015

@inproceedings{Bolla2025_23015,
  author = {Bolla, Carlo and Cox, Trevor and Fazenda, Bruno},
  title = {{A Machine Learning approach to modal control in small rooms}},
  booktitle = {2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio},
  note = {Paper 26},
  year = {2025},
  month = sep,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23015}
}

TY  - CPAPER
TI  - A Machine Learning approach to modal control in small rooms
AU  - Bolla, Carlo
AU  - Cox, Trevor
AU  - Fazenda, Bruno
T2  - 2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio
M1  - Paper 26
PY  - 2025
DA  - 2025/09/02
UR  - https://aes.org/publications/elibrary-page/?id=23015
PB  - Audio Engineering Society
LA  - en
AB  - Reducing the decay time of low-frequency resonances in small rooms remains a critical challenge in audio engineering, as these resonances can degrade sound quality, leading to a "boomy" or "muddy" audio experience. Traditional equalization methods, while effective in certain contexts, rely heavily on static equalization filters, making them suboptimal for complex scenarios. This paper explores a novel machine learning-based approach to suppress low-frequency resonances by leveraging a modified Wave-U-Net architecture. The model incorporates psychoacoustic principles, specifically perceptual modal thresholds, to ensure that resonance suppression is guided by human auditory perception while preserving the natural characteristics of the audio. A large dataset of synthetic Room Impulse Responses was generated using a physically informed parametric model for cuboid rooms with randomized dimensions and absorption profiles. The model was trained on amplitude-modulated white noise bursts to simulate broadband excitation. Evaluation on unseen synthetic data demonstrates effective suppression of low-frequency resonances below perceptual thresholds. Limitations in generalization are discussed, along with future directions that include retraining on musical stimuli and incorporating perceptual loss metrics.
ER  -