In this paper we explore the potential of qualitiative, visual inspection to help understanding audio data for Unsupervised Anomaly Detection under Domain-Shift Conditions (UAD-S). In UAD-S, anomalous data is not known beforehand, and detectors must identify anomalies just from knowledge of non-anomalous (i.e. normal) data.
Emily Corrigan-Kavanagh presents poster on "Exploring Sound Sensing to Improve Quality of Life in Urban Living" at the Urban Sound Symposium
This virtual poster reports on the initial findings from a pilot of “virtual world Cafés” we are organising to explore with residents how they feel about sounds in their locality, how they might change them, and how AI for sound technology could help.
The sounds around us, “soundscapes”, have a major impact on how people feel about their urban environment. At the University of Surrey, we are beginning to build sound sensing AI technology that can automatically recognise these sound events and soundscapes.
In March 2021, the Turing is hosting its unique two-day online event, AI UK, to showcase the very best of UK academic work in artificial intelligence (AI); bringing together leading thinkers, innovative businesses and specialist third sector bodies.
In this talk, I will discuss some of the techniques and approaches that we have been using to analyze and recognize different types of sounds, including independent component analysis, nonnegative matrix factorization, sparse representations and deep learning.
Emily Corrigan-Kavanagh and Mark Plumbley give invited talk at #LboroAppliedAI seminar series on Applied AI
In this talk, we will explore some of the work going on in this rapidly expanding research area and discuss some of the potential applications emerging for sound recognition, from home security and assisted living to environmental noise and sound archives.
DCASE 2020 Challenge offers awards for open-source and innovative methods. These awards are meant to encourage open science and reproducibility, and therefore the Reproducible system award is directly based on these criteria.
The Engineering and Physical Sciences Research Council (EPSRC) has given a prestigious Fellowship Award to the University of Surrey’s Professor Mark Plumbley, who will use it to further improve how machines listen to the world around us.