Events

Interactive Agri-Robotics and Machine Learning for Machine Listening

Date: 22 November 2019 12:30 - 15:00

Location: ArtsOne, Room 1.28

Interactive Agri-Robotics and Machine Learning for Machine Listening

by Philip Noman, Ross Robotics, UK

and Dr Emmanouil Benetos, Queen Mary University of London, UK

Interactive Agri-Robotics: Philip Norman will present a case study of modular robot for poultry farming, with potential implications for other sectors. The talk will focus on interactivity in data collection, analytics and better informed decision-making for improved animal welfare/commercial outcomes and animal/robot interactions to modify individual and group behaviour for improved welfare/commercial outcomes.

Machine Learning for Machine Listening: Audio analysis -also called machine listening- involves the development of algorithms capable of extracting meaningful information from audio signals such as speech, music, or environmental sounds, typically drawing knowledge from the fields of digital signal processing and artificial intelligence. Machine listening applications are numerous, including but not limited to smart homes/smart cities, ambient assisted living, biodiversity assessment, security/surveillance and audio archive management amongst others. The talk will outline recent research carried out at QMUL that focuses on sound recognition in complex acoustic environments, inspired by and proposing new methods in the area of machine learning. Topics covered will include designing new learning objectives for audio analysis, domain and context adaptation for audio, methods for interpretability in machine listening, and studies on the robustness of machine listening methods.