Finding the Right Tools to Interpret Crowd Noise at Sporting Events with AI

Jason Bickmore – jbickmore17@gmail.com

Instagram: @jason.bickmore
Brigham Young University, Department of Physics and Astronomy, Provo, Utah, 84602, United States

Popular version of 1aCA4 – Feature selection for machine-learned crowd reactions at collegiate basketball games
Presented at the 188th ASA Meeting
Read the abstract at https://eppro01.ativ.me/appinfo.php?page=Session&project=ASAICA25&id=3868450&server=eppro01.ativ.me

–The research described in this Acoustics Lay Language Paper may not have yet been peer reviewed–

A mixture of traditional and custom tools is enabling AI to make meaning in an unexplored frontier: crowd noise at sporting events.

The unique link between a crowd’s emotional state and its sound makes crowd noise a promising way to capture feedback about an event continuously and in real-time. Transformed into feedback, crowd noise would help venues improve the experience for fans, sharpen advertisements, and support safety.

To capture this feedback, we turned to machine learning, a popular strategy for making tricky connections. While the tools required to teach AI to interpret speech from a single person are well-understood (think Siri), the tools required to make sense of crowd noise are not.

To find the best tools for this job, we began with a simpler task: teaching an AI model to recognize applause, chanting, distracting the other team, and cheering at college basketball and volleyball games (Fig. 1).

Figure 1: Machine learning identifies crowd behaviors from crowd noise. We helped machine learning models recognize four behaviors: applauding, chanting, cheering, and distracting the other team. Image courtesy of byucougars.com.

We began with a large list of tools, called features, some drawn from traditional speech processing and others created using a custom strategy. After applying five methods to eliminate all but the most powerful features, a blend of traditional and custom features remained. A model trained with these features recognized the four behaviors with at least 70% accuracy.

Based on these results, we concluded that, when interpreting crowd noise, both traditional and custom features have a place. Even though crowd noise is not the situation the traditional tools were designed for, they are still valuable. The custom tools are useful too, complementing the traditional tools and sometimes outperforming them. The tools’ success at recognizing the four behaviors indicates that a similar blend of traditional and custom tools could enable AI models to navigate crowd noise well enough to translate it into real-time feedback. In future work, we will investigate the robustness of these features by checking whether they enable AI to recognize crowd behaviors equally well at events other than college basketball and volleyball games.

The sounds of March Madness

As March Madness sweeps across the nation, basketball enthusiasts eagerly anticipate the exhilarating clashes on the court. Yet, amidst the thunderous roars of the crowd and the rhythmic bounce of the basketball, there lies a hidden symphony of sound that influences both players and spectators alike. Research sheds light on the intricate relationship between sound and the game, unveiling the fascinating dynamics at play within basketball arenas.

March Madness - crowd noise

You have probably noticed how the crowd’s energy during March Madness games ebbs and flows. Researchers meticulously analyzed the acoustic signatures of basketball crowds to classify behavior based on various emotional states expressed through sound. From the jubilant cheer of a successful shot to the collective groan of a missed opportunity, each acoustic cue provides insight into the emotional pulse of the audience. Understanding these nuances not only enriches our appreciation of the game but also offers valuable insights for enhancing spectator experiences. Read “Classifying crowd behavior at collegiate basketball games using acoustic data” in POMA at https://doi.org/10.1121/2.0001061.

march madness - bounce

While spectators contribute to the symphony of sound in basketball arenas, players themselves are attuned to a different sound—the bounce of the basketball. A study published in the Journal of the Acoustical Society of America (JASA) explores how listeners utilize auditory cues to anticipate the trajectory of a ball. Remarkably, individuals demonstrate an ability to predict the timing of a bounce. Read “Predicting the timing of dynamic events through sound: Bouncing balls” at https://doi.org/10.1121/1.4923020.

March madness - reverberation

While basketball arenas resonate with the fervor of March Madness, these spaces are not confined solely to sporting events. In a thought-provoking article featured in Acoustics Today, the complexities of converting arenas for alternate purposes are unveiled. From transforming a raucous sporting venue into a serene place of worship, acousticians navigate a myriad of challenges to optimize sound quality and ensure a seamless transition between functions. The meticulous orchestration of sound within these dynamic spaces underscores the profound impact of acoustics on human experiences, transcending the boundaries between sports and spirituality. Read “From sprots arena to sanctuary – Taming a Texas-sized reverberations time” at https://bit.ly/3D7ypVM.

While you immerse yourself in the excitement of March Madness, take a moment to listen closely—you just might discover the hidden sounds that enrich the game beyond the final buzzer.