Bird sounds and machine learning

Add to your list(s) Download to your calendar using vCal

• Dan Stowell (Queen Mary University of London)
• Thursday 05 March 2015, 11:15-12:15
• Rainbow Seminar Room (SS03), Computer Laboratory.

If you have a question about this talk, please contact Isak Herman.

Bird sound recordings contain a wealth of information – about species, individuals, and their interactions. Applying machine learning to such data has applications in conservation, animal behaviour research, and comparative linguistics. The rich structure of bird sounds is apparent to us as listeners, but how could we “decode” it?

I will describe an approach to automatic classification of bird species which is designed to fit the characteristics of bird sounds: often noisy, often fast-modulated, often more than one bird, and many candidate species. This approach is currently being deployed in our Warblr bird recognition app.

I will also describe recent work on more structured analysis of sound recordings: tracking individuals in a sound scene, and modelling bird “conversations”.

This talk is part of the Rainbow Group Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Interested Talks
• Rainbow Group Seminars
• Rainbow Seminar Room (SS03), Computer Laboratory
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.