Probabilistic approaches to understanding bird conversations
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Dr R.E. Turner.
Bird sound recordings contain a wealth of information – about species, individuals, and their interactions. Multiple sound sources are typically active at a time, and each one is governed by incompletely understood processes with rich temporal structure. Applying machine learning to such data has applications in conservation, animal behaviour research, and comparative linguistics.
I will describe some inference problems pertinent to bird sounds, from classification to more structured analysis. I will then describe recent work modelling bird “conversations” as collections of Markov renewal processes, as a basis for working towards general-purpose machine listening for birds.
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|