Toward A Sound Analysis System for Telemedicine

Our work is within the framework of studying a sound analysis system in a telemedicine project. The task of this system is to detect situations of distress in a patient’s room basing on sound analysis. In this paper we present our studies on the constructions of a speech/non-speech discriminator and of a speech/scream-groan discriminator. The first discriminator’s task is to distinguish speech signal from non speech signal in a room such as sounds of broken glass, door shutting, chair falling, water in toilette, etc. The second one’s task is to detect sounds of scream-groan from speech signal. Results show that these discriminators are applicable to our sound analysis system.

@InternationalConference{NPC05a,
  author       = {NGUYEN, C. and PHAM, T. and CASTELLI, E.},
  title        = {Toward A Sound Analysis System for Telemedicine},
  booktitle    = {Fuzzy Systems and Knowledge Discovery, Lecture Notes  in Artificial Intelligence, vol. 3614},
  year         = {2005},
  url          = {/2005/NPC05a},
}