A major operator of the national road network has launched a pilot project to enable tunnels to \u201clisten\u201d<\/strong>: to automatically recognize, based on audio from microphones, sounds that signal danger (braking, collisions, screams, car horns, sirens, tire blowouts) and alert the operations center. The main challenge was twofold: the lack of real-world recordings of tunnel accidents and a hostile acoustic environment\u2014dominated by ventilation, traffic, and reverberation\u2014in which critical events must be reliably distinguished with as few false alarms as possible.<\/p>\n\n\n\n The project involved the development of a Sound Event Detection<\/strong> solution based on deep learning models for audio. A data preparation<\/strong> engine \u201cset the scene\u201d in the tunnel for 297 event sounds, blending them with real tunnel noise and simulating their echo: this resulted in a dataset of 2,970 samples across 8 classes (crashes, braking, horns, screams, etc.). A comparison<\/strong> of three pre-trained architectures (EfficientAT, AST, CLAP) allowed us to select the model with the best balance between accuracy, false alarms, and computational efficiency. The model analyzes the audio in 5-second windows and sends alerts to the operations center; a web app allows for the management of rules, thresholds, and monitoring.<\/p>\n\n\n\n During testing, the model achieved an accuracy of over 90%<\/strong>, with good performance even for the rarest events. Calibrating the thresholds cut false alarms in half<\/strong> compared to the alternatives evaluated. The process is repeatable and scalable<\/strong>: the dataset is being enriched with real-world records, and the solution is ready for field validation and extension to other tunnels.<\/p>\n\n\n\n HUMANATIVA managed the entire lifecycle of the solution: from data preparation and signal analysis to model selection and training, and finally to the engineering of the real-time analytics service and the management web app. Thanks to the expertise of its Data Science and MLOps team, the Group delivered a documented, traceable, and reproducible solution\u2014the first step toward an intelligent infrastructure monitoring platform.<\/p>\n\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" The Challenge A major operator of the national road network has launched a pilot project to enable tunnels […]<\/p>\n","protected":false},"author":7,"featured_media":422,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[121,1],"tags":[68,118,119,120],"class_list":["post-420","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-sound-detection","category-use-case","tag-ai","tag-safety","tag-sound-detection","tag-tunnel"],"yoast_head":"\nThe Solution<\/h3>\n\n\n\n
The Benefits<\/h3>\n\n\n\n
Humanativa’s role<\/h3>\n\n\n\n