Log in
One of the world-leading systems for large-vocabulary Automatic Speech Recognition (ASR) has been developed by a team led from the University of Sheffield. This system, which won the international evaluation campaigns for rich speech transcription organised by the US National Institute for Standards and Technology (NIST) in 2007 and 2009, has led directly to the creation of one spin-out, been largely instrumental in the launch of a second, has had significant impact on the development and growth of three existing companies, and has made highly advanced technology available free for the first time to a broad range of individual and organisational users, with applications including language learning, speech-to-speech translation and access to education for those with reading and writing difficulties.
Research in robust speech enhancement and audio-visual processing has led to impact on a range of different fronts:
(i) Collaboration with CSR, a leading $1 billion consumer electronics company, has shaped its R&D research agenda in speech enhancement, has inspired ideas for new product improvements, and has helped establish Belfast as an audio research centre of excellence within the company.
(ii) Our technology has changed the strategic R&D direction of a company delivering healthcare monitoring systems, with potential for multi-million pound savings in NHS budgets.
(iii) Audio-visual speech processing research has led to a proof-of-concept biometric system, Liopa: a novel, robust and convenient person authentication and verification technology exploiting lip and facial movements (www.liopa.co.uk). A start-up company is in an advanced stage of being established to commercialise this product. The product and commercialisation strategy was awarded First Prize in the 2013 NISP Connect £25K entrepreneurship competition in the Digital Media and Software category. The first commercial partner for Liopa has been engaged.
(iv) A system-on-chip implementation of a version of our speech recognition engine, which was developed through an EPSRC project, was awarded first prize in the High Technology Award in the 2010 NISP £25K Awards competition, and contributed to the founding of a spin-out company, Analytics Engines (www.analyticsengines.com).
Nearly every large-vocabulary speech recognition system in current use employs outputs from fundamental research carried out in the University of Cambridge Department of Engineering (DoEng) on adaptation of Hidden Markov Models (HMMs). One example of the commercial application of these outputs is their use on the Microsoft Windows desktop for both the command and control functions and the dictation functions. Approximately one billion copies of Windows have been shipped since 2008. Other examples show the outputs used in the automatic transcription of a wide range of types of data. [text removed for publication]
Extracting information and meaning from natural language text is central to a wide variety of computer applications, ranging from social media opinion mining to the processing of patient health-care records. Sentic Computing, pioneered at the University of Stirling, underpins a unique set of related tools for incorporating emotion and sentiment analysis in natural language processing. These tools are being employed in commercial products, with performance improvements of up to 20% being reported in accuracy of textual analysis, matching or even exceeding human performance (Zoral Labs). Current applications include social media monitoring as part of a web content management system (Sitekit Solutions Ltd), personal photo management systems (HP Labs India) and patient opinion mining (Patient Opinion Ltd). Impact has also been achieved through direct collaboration with other commercial partners such as Microsoft Research Asia, TrustPilot and Abies Ltd. Moreover, international organisations such as the Brain Sciences Foundation and the A*Star Institute for High Performance Computing have realised major impact by drawing upon our research.
COnnecting REpositories (CORE) is a system for aggregating, harvesting and semantically enriching documents. As at July 2013, CORE contains 15m+ open access research papers from worldwide repositories and journals, on any topic and in more than 40 languages. In July 2013, CORE recorded 500k+ visits from 90k+ unique visitors. By processing both full-text and metadata, CORE serves four communities: researchers searching research materials; repository managers needing analytical information about their repositories; funders wanting to evaluate the impact of funded projects; and developers of new knowledge-mining technologies. The CORE semantic recommender has been integrated with digital libraries and repositories of cultural institutions, including the European Library and UNESCO. CORE has been selected to be the metadata aggregator of the UK's national open access services.
Speech Graphics Ltd is a spinout company from the University of Edinburgh, building on research into the animation of talking heads during 2006-2011. Speech Graphics' technology is the first high fidelity lip-sync solution driven by audio. Speech Graphics market a multi-lingual, scalable solution to audio-driven animation that uses acoustic analysis and muscle dynamics to drive the faces of computer game characters accurately matching the words and emotion in the audio. The industry-leading technology developed by Speech Graphics has been used to animate characters in computer games developed by Supermassive games in 2012 and in music videos for artists such as Kanye West in 2013.
This impact case study provides evidence of economic impacts of our research because:
i) a spin-out company, Speech Graphics Ltd, has been created, established its viability, and gained international recognition;
ii) the computer games industry and the music video industry have adopted a new technology founded on University of Edinburgh research into a novel technique to synthesize lip motion trajectories using Trajectory Hidden Markov Models; and
iii) this led to the improvement of the process of cost-effective creation of computer games which can be sold worldwide because their dialogue can be more easily specialised into different human languages with rapid creation of high-quality facial animation replacing a combination of motion capture and manual animation.
Edinburgh's research in multilingual speech synthesis has had clinical and commercial impact, and has resulted in a large and diverse community of users.
Clinical applications: Our research has enabled the construction of natural-sounding, personalised synthetic voices from recordings of speech from people with disordered speech due to conditions such as Parkinson's disease or Motor Neurone Disease. These synthetic voices are used in assistive technology devices that allow sufferers of these conditions to communicate more easily and effectively.
Commercial take-up: Our research has achieved commercial impact through the licensing of technology components, and through the activities of start-up companies.
Community of users: The Festival Speech Synthesis System (v2.1 released in November 2010) is a complete open-source text-to-speech system released under an unrestrictive X11-type license, and is distributed as part of many major Linux distributions.
GATE (a General Architecture for Text Engineering—see http://gate.ac.uk/) is an experimental apparatus, R&D platform and software suite with very wide impact in society and industry. There are many examples of applications: the UK National Archive uses it to provide sophisticated search mechanisms over its .gov.uk holdings; Oracle includes it in its semantics offering; Garlik Ltd. uses it to mine the web for data that might lead to identity theft; Innovantage uses it in intelligent recruiting products; Fizzback uses it for customer feedback analysis; the British Library uses it for environmental science literature indexing; the Stationery Office for value-added services on top of their legal databases. It has been adopted as a fundamental piece of web infrastructure by major organisations like the BBC, Euromoney and the Press Association, enabling them to integrate huge volumes of data with up-to-the-minute currency at an affordable cost, delivering cost savings and new products.