There have been significant recent advances in Virtual Personal Assistants (VPAs) such as Google Assistant, Siri, and Alexa. However, development of these assistant systems is expensive and difficult (often requiring multiple skilled PhDs). And further, current systems are capable of limited "conversations", with most actions consisting of a single interaction in limited domains to perform simple tasks ("set a timer", "play music", etc...). The goal of this research is to develop research to enable a future conversational search systems that can help solve complex information tasks. Examples of these types of information tasks could be "Teach me about the causes of climate change." or "Help me write the literature survey for this paper." These require complex discussion and long-running modelling of the user and their information task. We propose building on recent advances in machine learning to adapt a general purpose information agent for specialized domains (like health, law, finance) by "machine reading" of text (such documents from a website) to learn a domain model and to discover information tasks automatically from existing interaction data such as search logs, existing conversations, or help tickets. The result of this work will be information agents that can effectively work with the user (including asking questions back and forth) and explain their reasoning more effectively than current information assistants.

How to effectively and efficiently search for content from large video archives such as BBC TV programmes is a significant challenge. Search is typically done via keyword queries using pre-defined metadata such as titles, tags and viewer's notes. However, it is difficult to use keywords to search for specific moments in a video where a particular speaker talks about a specific topic at a particular location. Most videos have little or no metadata about content in the video, and automatic metadata extraction is not yet sufficiently reliable. Furthermore, metadata may change over time and cannot cover all content. Therefore, search by keyword is not a desirable approach for a comprehensive and long-lasting video search solution. Video search by examples is a desirable alternative as it allows search for content by one or more examples of the interested content without having to specify interest in keyword. However, video search by examples is notoriously challenging, and its performance is still poor. To improve search performance, multiple modalities should be considered - image, sound, voice and text, as each modality provides a separate search cue so multiple cues should identify more relevant content. This is multimodal video search by examples (MVSE). This is an emerging area of research, and the current state of the art is far from desirable so there is a long way to go. There is no commercial service for MVSE. This proposal has been co-created with BBC R&D through the BBC Data Science Partnership via a number of online meetings and one face to face meeting involving all partners. The proposal has been informed by recent unpublished ethnographic research on how current BBC staff (producers, journalists, archivists) search for media content. It was found that they were very interested in knowledge retrieval from archives or other sources but they required richer metadata and cataloguing of non-verbal data. In this proposal we will study efficient, effective, scalable and robust MVSE where video archives are large, historical and dynamic; and the modalities are person (face or voice), context, and topic. The aim is to develop a framework for MVSE and validate it through the development of a prototype search tool. Such a search tool will be useful for organisations such as the BBC and British Library, who maintain large collections of video archives and want to provide a search tool for their own staff as well as for the public. It will also be useful for companies such as Youtube who host videos from the public and want to enable video search by examples. We will address key challenges in the development of an efficient, effective, scalable and robust MVSE solution, including video segmentation, content representation, hashing, ranking and fusion. This proposal is planned for three years, involving three institutions (Cambridge, Surrey, Ulster) and one partner (the BBC) who will contribute significant resources (estimated at £128.4k) to the project (see Letter of Support from the BBC).

Cultures of fear can be spread, either deliberately or otherwise, by a wide range of agents including the media, government, science, the arts, industry and politics. The ease of which fear can be generated means that today's society remains inordinately fearful of improbable harms and dangers. A good deal of societal fear stems from mistrust of 'the Other': a term used to describe individuals or groups that are, quite simply, 'not like us'. In this project, we explicitly explore this notion of 'Othering' as it occurs in situations where 'the Other' are seen as "anomalous," "peculiar," or "deviant" and hence negatively perceived, stigmatised, excluded, marginalised and discriminated against. Recent high-profile examples of practices of Othering in the UK include the exclamation that "tens of thousands of eastern Europeans" would enter the UK when immigration restrictions were lifted at the beginning of 2014 resulting in, for instance, a "crime wave", and the "poverty-porn" portrayal on broadcast television of seemingly whole communities of "benefit claimants living off of taxpayers' earnings". Such practices can lead to a lack of tolerance, respect and inclusion, as well as actual fear, mistrust and marginalisation of whole communities; these effects have severe and well-known implications for local communities as well as for national social cohesion. There are significant unanswered questions regarding how acts of Othering translates into effects on real populations and in real contexts, and what role online digital media can have in propagating cultures of fear and mistrust. With online social media, no longer is fear delivered exclusively in a top down manner, (e.g. from government and the mainstream media). Instead it is now also delivered from the grassroots level and therefore insidiously present in the user-generated social data streams that we absorb from our encounters with the web, and, in particular, with platforms such as Twitter and Facebook. Recent observations of social media discussions of the Channel 4 documentary Benefits Street have, for instance, highlighted the high levels of antipathy, anger and abuse directed at the community portrayed within the programme. Fear may also be unwittingly, yet pervasively, propagated by the plethora of emerging digital apps, data and services that promise to improve our lives; for instance, the release of open crime data is meant to increase confidence in our law enforcement agencies, yet its actual effect is to increase fear of crime and, yet again, stigmatise communities. The focus of this project are the cultures of fear that are propagated through online Othering and how this leads to subsequent mistrust of groups or communities. Our research will generate an understanding of how the deliberate design of online media services and platforms can influence and oppose cultures of fear and result in cultures of empathy that can actively, and strategically, reduce or eliminate mistrust and negative consequences of Othering. We will actively collaborate with stakeholders to co-design new digital services that facilitate wide-scale empathy with specifically chosen often-Othered groups. This will include active collaboration with broadcast media organisations to develop a range of interactive, digital online experiences delivered alongside traditional media. We will also undertake online ethnographies and data collection, where prior or existing activities have portrayed a group in ways that actively provoke Othering as evidenced through discourse on social and traditional media; in this instance we will design and deliver a set of digital services to counter this in a deliberate manner.

The aim of this project is to utilise the video digitisation suites that the East Anglian Film Archive (EAFA) acquired in our previous Capability for Collections grant (AH/V011952/1) to actively engage new and, particularly, youth audiences in collections-based research and digital engagement. These activities will make use of and preserve valuable, under-studied and at-risk parts of our collections that are of local, national and international significance. We will achieve the engagement strategies through partnership with the BBC who will collaborate on the selection of content and the digital outputs, and make use of the generated digital content for their 'BBC at 100' celebrations (2022). EAFA's extensive collections of film, video and born-digital content, covering the 1890s to the present, are a valuable resource for academics and educators working across a range of disciplines. EAFA is a thriving research centre, collaborating on a range of funded research projects and educational initiatives. These projects reflect the strengths of our collections in amateur filmmaking and regional television (BBC East / ITV-Anglia), but also EAFA's cutting-edge digital expertise and infrastructure. In 2020, EAFA was successful in securing funding for seven video digitisation kits from Capability for Collections. This consisted of: - 7 x FSI DM240 (professional 'reference' video monitor with waveform displays, legal levels and vectorscopes) - 7 x HP EliteDesk PC's The new equipment, in combination with Leitch Timebase Correctors, Vrecord (open source video digitisation software) and Blackmagic video capture cards make up seven video digitisation workstations that can digitise a wide range of formats and are able to be operated by student volunteers (following a short training programme). The BBC collection includes a number of 'at-risk' video formats as well as film titles. EAFA's proposal is that the archive will digitise a range of BBC videos and films alongside selections from other valuable EAFA collections to meet the objectives of the research and engagement strategies. This grant will fund digitisation of approximately 550+ hours of video and film content. Some of this will be undertaken by the technical team in EAFA but we will also train a small group of UEA students to: digitise BBC and other EAFA tapes; to catalogue the material; to assist in selecting material for EAFA's annual Mash up filmmaking competition; and curating a selection of BBC content online and programmed at a live event. The material will also be viewed and interacted with by the public as part of the BBC's 100th Anniversary, within their flagship 'Story of Us' online platform. The qualitative and quantitative research undertaken at the end of the project with the archive volunteers and Mash Up competition entrants will be used to produce an open-access report aimed at key stakeholder organisations we consulted (BBC, BFI, National Lottery Heritage Fund, INTO Film) and the wider heritage / screen education sectors. This will address their desires to understand the values and impacts of digitisation training, online curation and creative reuse projects for engaging youth audiences and developing their future skills.

The cost of producing dynamically-updated media content - such as online video news packages - across multiple languages is very high. Maintaining substantial teams of journalists per language is expensive and inflexible. Modern media organisations like the BBC or the Financial Times need a more agile approach: they must be able to react quickly to changing world events (e.g., breaking news or emerging markets), dynamically allocating their limited resources in response to external demands. Ideally, they would like to create `pop-up' services & products in previously-unsupported languages, then to scale them up or down later. The government has set the BBC a target of reaching a global audience of 500 million people by 2022, compared with today's 308 million. The only way to reach such a huge audience is through new language services and efficient production techniques. Text-to-speech - which automatically produces speech from text - offers an attractive solution to this challenge, and the BBC have identified computer assisted translation and text-to-speech as key technologies that will provide them with new ways of creating and reversioning their content across many languages. This project's objectives are to push text-to-speech technology towards "broadcast quality" computer-generated speech (i.e., good enough for the BBC to broadcast) in many languages, and to make it cheap and easy to add more languages later. We will do this by combining and extending several distinct pieces of our previous basic research on text-to-speech. We will use the latest data-driven machine learning techniques, and extend them to produce much higher quality output speech. At the same time, we will enable the possibility of human control over the speech. This will allow the user (e.g., a BBC journalist) to adjust the speech to make sure the quality and the speaking style is right for their purposes (e.g., correcting the pronunciation of a difficult word, or putting emphasis in the right place). The technology we will create for the likes of the BBC will also enable smaller companies and other organisations, state bodies, charities, and individuals to rapidly create high-quality spoken content, in whatever language or domain they are operating. We will work with other types of organisation during the project, to make sure that the technology we create has broad appeal and will be useful to a wide range of companies and individuals.