Made By Machine: When AI Met The Archive

During my time at BBC R&D, Cassian Harrison, Controller of BBC Four, challenged us to produce a one-hour documentary programme, assembled from existing archive clips, entirely using machine learning techniques: This was an interesting exercise in testing the limits of computational creativity, and in the use of machine learning on media to educate a non-specialist […]

Alluvial Sharawadji

Alluvial Sharawadji was a crowdsourced interactive artwork/workshop by myself and my friend and collaborator Jakub Fiala for Eufonic festival 2018, combining collaborative field recording with low-cost, ubiquitous web technologies to communicate the experience of a local sound environment to audiences who are distant in both time and space. Drawing on Claude Shryer’s idea of ‘Sharawadji’ […]

Singing With Machines

At the tail end of 2018, Henry and I were having an idle conversation about about smart speakers and generative sound. Henry had been working on the BBC’s first experiments at producing a skill for the Amazon Alexa, and we’d been talking for ages about how the rather transactional pattern of interaction that Alexa affords […]

Public Service Personalised Radio

What does it mean for a media service to be “personalised?” In the world of the commercial streaming platforms this tends to mean that the service provides some sort of personalised recommendations – looking at your listening or watching history to identify more media that you’re likely to spend time consuming. This makes sense for […]

Cards Against Television

One of my first projects with BBC R&D as part of the Tellybox project, overseen by my incredible friend and colleague Libby Miller (who basically taught me everything I know). “Tellybox” was a speculative prototyping project investigating the ways in which people choose television programmes while watching together with others, and the social role that […]

The Secret Science of Pop

I contributed to the BBC Four documentary The Secret Science of Pop, working with a team of experts from the BBC, Imperial College London, QMUL and Oxford University to analyse the history of recorded pop music, and investigate whether data science and machine learning techniques can predict what makes a song a hit – somewhat […]

Polkaspots WiFi footfall mapping

A short investigation / prototype for Polkaspots WiFi (now CT Networks), looking into whether WiFi data can be used to provide insight for urban planning and architecture, by revealing the footfall patterns of the people inhabiting a space. We tested this approach on data from London’s National Gallery, and from the municipal WiFi network in […]

ODI Fire Station Closures Investigation

A project for the Open Data Institute investigating the potential effects at borough level of proposed policy changes to close fire stations in London. The effects can be viewed by potential change in incident attendance time (calculated from open data from the London Fire Brigade), or as a score which also takes into account the […]