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.
This case study describes significant health and wellbeing, and economic and social impacts deriving from a decade of MMU research into Augmentative and Alternative Communication (AAC). Impacts include the creation of www.aacknowledge.org.uk, the world's first AAC evidence base, an online source of evidence and information on AAC made accessible for lay people, families, people who use AAC service commissioners and providers, as well as other information and resources. A case study database has also been created which enables practitioners to improve the efficacy of AAC treatments. The database maintains detailed information on approaches to treatment that practitioners can interrogate. MMU research has also informed and influenced a wider political engagement with AAC issues leading to improved awareness and understanding of AAC as well as an increase of £6.5M funding for UK provision and services.
Data-to-text utilises Natural Language Generation (NLG) technology that allows computer systems to generate narrative summaries of complex data sets. These can be used by experts, professional and managers to better, and quickly, understand the information contained within large and complex data sets. The technology has been developed since 2000 by Prof Reiter and Dr Sripada at the University of Aberdeen, supported by several EPSRC grants. The Impact from the research has two dimensions.
As economic impact, a spinout company, Data2Text (www.data2text.com), was created in late 2009 to commercialise the research. As of May 2013, Data2Text had 14 employees. Much of Data2Text's work is collaborative with another UK company, Arria NLG (www.arria.com), which as of May 2013 had about 25 employees, most of whom were involved in collaborative projects with Data2Text.
As impact on practitioners and professional services, case studies have been developed in the oil & gas sector, in weather forecasting, and in healthcare, where NLG provides tools to rapidly develop narrative reports to facilitate planning and decision making, introducing benefits in terms of improved access to information and resultant cost and/or time savings. In addition the research led to the creation of simplenlg (http://simplenlg.googlecode.com/), an open-source software package which performs some basic natural language generation tasks. The simplenlg package is used by several companies, including Agfa, Nuance and Siemens as well as Data2Text and Arria NLG.
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.
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]