SCANDLE: acoustic SCene ANalysis for Detecting Living Entities

The SCANDLE Project is an EU FP7 funded project within the Cognitive Systems, Interaction, Robotics challenge. It is an exciting collaboration between five leading European institutions, for developing a system that will be able to identify and distinguish living beings from inanimate objects, on the basis of sound alone: a cognitive acoustic scene analysis system. SCANDLE has now finished; however you can find a repository of all our work, tutorials and links to all the project partners on this website. We will also be streaming the proceedings from the SCANDLE workshop (Making Sense of Sound 2012).

 

The SCANDLE team                Salvador Dura Bernal & Martin Coath                SCANDLE Team at dinner

 

The final review meeting for the SCANDLE project took place in Nicosia, Cyprus on the 12th April. The meeting was a great success, with the reviewers very happy with amount of research and technology produced by the SCANDLE project.

 

 

MSOS 12                    Poster Session                         Demonstration                          Proceedings cover



SCANDLE hosted a workshop in Plymouth (Feb 20-21, 2012) entitled: Making Sense of Sounds: How much can we learn about what is going on in the world simply by listening. The conference was a great success and talks will be available for download or streaming soon. For a list of topics, speakers and the proceedings please look here

In the meantime the programme is available here

Newsletter Thumb
Latest Newsletter

     







    The SCANDLE project had produced several newsletters:

     

     

     

     

     

     





      

     

     

     

     

     




    From Parliament Magazine's Research Review

     

     

             

    The SCANDLE Project is an exciting collaboration between five leading European institutions.Over the next three years we will be developing a system that will be able to identify and distinguish living beings from inanimate objects, on the basis of sound alone: a cognitive acoustic scene analysis system.
     
    This system will be able to construct composite representations of living beings exclusively through the use of information derived from sounds.
    This will happen in two ways:
    1. in a passive way, to detect sounds generated or caused by living beings;
    2. in an active way, using a newly developed microsonar device. This device will emit sounds that bounce off objects. The system will learn to recognise patterns in the sounds that bounce off living beings are returned.

    To understand the Doppler effect, click here.
    More detailed explanations of these two types of detection are available here. For a more detailed explanation of biosonar, click here.
     

    Click here to learn more about our work on Auditory Scene Analysis:

     

    Click here to learn more about our work on modelling auditory processing:

     

     

     

     

     

     

    Cognitive: Relating to the process of thoughts and, more precisely, the process of being aware, knowing, thinking, learning and judging.
    Acoustic Scene Analysis: The process of analyzing a complex mixture of sounds to isolate the information relating to different sound sources.
    Composite representations: Combining information about the sounds being made, patterns of movement, position to recognise patterns of behaviour.
    Information derived from sounds: A great deal of information can be gleaned from the sounds generated by living beings, for instance emotional state, gender and state of health.
    Sounds generated or caused by living beings: By this, we mean not only calls and voices, but the sounds made by their bodies as they move. For example, as we talk, our lips, mouths and jaws move in patterns that are correlated with the sounds coming out of our mouths.
    Microsonar device: This device utilises the Doppler effect, detecting differences in the frequency of sound waves, which gives information about movement of living beings through space.

                                               

     

    Document Actions