The AIMS South Africa, the National Research Foundation (NRF) and the South African Radio Astronomy Observatory (SARAO) are looking to fund one Master’s student to work in the area of machine learning and bioacoustics. The student will share office space with a collaborative and energetic team of researchers in the beautiful city of Muizenberg, South Africa at AIMS.
The project will use audio soundscape data recorded in China which contains vocalisations of the world’s rarest primate, the Hainan gibbon. The student will investigate how advances in deep learning can be applied to bioacoustics problems, in particular, how can the sounds of animals be automatically detected. Using unsupervised and supervised learning algorithms, the candidate will explore auto-encoders, transformers and cluster algorithms to automatically identify/classify sound categories. The methods developed would support ecologists by providing them with easy-to-handle tools based on deep learning to facilitate their data processing. The student may also record audio data in Cape Town and use audio recordings from other locations to validate their algorithms.