PhD Title: Birdsong Forensics for Species Identification and Separation

Studentship: Full Scholarship, including fees (EU/Non EU) plus annual stipend of €16,000.

Start Date: Sept 2

nd, 2013

PhD Supervisor: Dr. Naomi Harte, Sigmedia Group, Electronic & Electrical Engineering, Trinity College Dublin, Ireland

Collaborator: Dr. Nicola Marples, Zoology, Trinity College Dublin, Ireland.

Background:

The analysis of birdsong has increased in the speech processing community in the past 5 years. Much of the reported research has concentrated on the identification of bird species from their songs or calls. Smartphone apps have been developed that claim to automatically identify a bird species from a live recording taken by the user. A lesser reported topic is the analysis of birdsongs from subspecies of the

same bird. Among experts, bird song is considered a particularly effective way of comparing birds at species level. Differences in song may help uncover cryptic species. In many species, such as those living in the high canopy, catching the birds in order to obtain morphological (e.g. weight, bill length, wing length etc.) and genetic data may be time consuming and expensive. Identifying potentially interesting populations by the detection of song differences, allows any such effort to be better targeted.

Birdsong presents many unique challenges as a signal. The use of signal processing and machine learning techniques for birdsong analysis is at a very early stage within the ornithological research community. This PhD project seeks to lead the way in defining the state of the art for forensic birdsong analysis. Comparing birdsongs will push out the boundaries of feature analysis and classification techniques in signal processing. The research will develop new algorithms to systematically quantify levels of similarity in birdsong, transforming the comparison of birdsong in the natural sciences arena. The results will be of importance internationally for the study, monitoring, and conservation of bird populations.

Requirements:

The ideal candidate for this position will:

 Have a primary degree (first class honours) in Electronic Engineering, Electronic and Computer Engineering or a closely related discipline.

 Possess strong written and oral communication skills in English.

 Have a strong background and interest in digital signal processing (DSP)

 Be mathematically minded, and be curious about nature.