A study of decodable breathing patterns for augmentative and alternative communication

Abstract People who use high-tech augmentative and alternative communication (AAC) solutions still face restrictions in terms of practical utilization present AAC devices, especially when speech impairment is compounded with motor disabilities. This study aims to explore an effective way decode breathing patterns for by the means a breath activated dynamic air pressure detection system (DAPDS) supervised machine learning (ML). The aim detect user’s modulated (MBPs) turn them into synthesized messages conversation outside world. MBPs are processed using one-nearest neighbor (1-NN) algorithm variations time warping (DTW) produce spoken words (SMSW) at managed complexities speeds. An ethical approved protocol was conducted participation 25 healthy subjects create library 1500 corresponding four different classes. A mean systematic classification accuracy 91.97 % obtained current configuration. implications from indicate that improved solution speaking biometrics decoding could be undertaken future.