Method for user context recognition using sound signatures

摘要

Method for user micro context recognition using sound signatures. The method includes: recording an environment sound sample from a microphone into a mobile device by a trigger stimulus; simultaneous to recording an environment sound sample, collecting hardware and software macro context data from available mobile devices; extracting a sound signature from the recorded sound sample based on sound features and spectrograms; comparing for similar patterns the recorded sound signature with reference sound signatures stored in a sound database; updating the sound database; checking if the recorded sound was recognized; performing a logical association between the sound label and the available macro context data; comparing for similar patterns the recorded context with a reference context stored in a context database; updating the context database; checking if the micro context was recognized; and returning to a mobile context-aware application the micro context label.