Speech detection models for effective communicable disease risk assessment in air travel environments

In environments characterized by elevated noise levels, such as airports or aircraft cabins, travelers often find themselves involuntarily speaking loudly and drawing closer to one another in an effort to enhance communication and speech intelligibility. Unfortunately, this unintentional behaviour increases the risk of respiratory particles dispersion, potentially carrying infectious agents like bacteria which makes the contagion control more challenging. The accurate characterization of the risk associated to speaking, in such a challenging noise environment with multiple overlapping speech sources, is therefore of outmost importance. Among the most advanced signal processing strategies that can be used to accurately determine who spoke when and with whom and for how long but most importantly how loudly, at one location, artificial intelligence-based speaker diarization approaches were considered and adapted for this task. The speaker diarization algorithms implementation, specifically adapted in this study to provide the relevant speaker and speech parameters without revealing what was spoken are described in this article. Moreover, the validation and preliminary studies’ results are presented. By extracting pertinent features from participants' speech, the developed algorithms facilitate the calculation of speech duration and overall sound pressure level associated to each sentence and speaker, which are crucial metrics for assessing potential viral contaminant spread. The paper explores the application of speaker diarization algorithms in noisy environments, emphasizing its relevance in multi-participant speaker scenarios within confined spaces. The insights gained from this research contribute to the development of proactive measures, enhancing our ability to effectively contain and manage communicable diseases in air travel settings.