Supervised machine learning for crowd noise classification at collegiate basketball games
Kolby Nottingham, Katrina Pedersen, Xin Wayne Zhao, Brooks A. Butler, Spencer Wadsworth, Blake Smith, Mark K. Transtrum, Kent L. Gee, Sean C. Warnick · The Journal of the Acoustical Society of America · 2018
Acoustical monitoring combined with machine learning (ML) may help in understanding crowd dynamics. While ML has been applied in numerous audio applications, the aim is usually to distinguish events from noise, rather than trying to characterize the noise itself. This paper comprises an initial study using ML to characterize crowd dynamics during collegiate basketball games. High-fidelity crowd noise recordings from several men’s and women’s games were synchronized with game video and used to produce a training dataset for supervised ML by linking game events (e.g., baskets, fouls) with acoustic labels (e.g., cheering, silence, and applause). Using the training dataset, a ML classifier was built to identify causal game events from acoustic crowd responses. Findings, potential improvements, and additional crowd noise applications are discussed.