University Researchers Harnessing Online Chat to Improve Artificial Speech Technologies

document Distributed Knowledge, Open Innovation

University Researchers Harnessing Online Chat to Improve Artificial Speech Technologies
Published in the Courier : 29.09.11 Published online : 01.10.11 @ 10.41am

Experts at St Andrews University believe social media could transform the lives of people unable to talk.

Researchers say the widespread study of sites such as Twitter and Facebook could result in synthetic voice systems, such as that used by Stephen Hawking, becoming ''faster and easier.'' The work was carried out by Dr Per Ola Kristensson, of St Andrews' school of computer science. He used crowdsourcing — a new method of obtaining large amount of statistical data through the monitoring of social media sites — to inform his findings. Together with colleague Dr Keith Vertanen of the department of computer science at Princeton University in the USA, Dr Kirstensson used the sites to create a unique dataset that provides predictive text more like real speech.

Previously only small amounts of data were available for users of Augmented and Alternative Communication (AAC), a device that enables those with communication disabilities to participate in everyday conversations. Speech devices rely on statistical language models to improve text entry by offering word predictions. These can be improved if the language model is trained on data that closely reflects the style of the users' intended communications. However, until now these was no large open dataset of AAC messages available. Dr Kristensson's work at St Andrews, titled The Imagination of Crowds and published by the Association for Computational Linguistics (PDF link), demonstrated how ''crowdsourcing'' can be used to create a large set of fictional messages. He revealed the work, funded by the Engineering and Physical Sciences Research Council, was sparked by his interest in online sites dedicated to sourcing information from the public such as Amazon Mechanical Turk. The site uses online volunteers to carry out simply tasks computers can't, such as transcribing scanned documents or rating the quality of photographs. However, the tasks are often very simple and Dr Kristensson wondered if there might be greater potential. He said: ''We wondered if we could also use these services to harness the creativity of the crowd. Can we design a task for these services that provides us with a large surrogate dataset of AAC messages?'' The initial collection of crowdsourced messages was then expanded by intelligently selecting similar sentences from Twitter, blog and Usenet data. The end result is a dataset much larger and of higher quality than anything that had previously been used. Dr Kristensson and Dr Vertanen have released the data collection, word lists and best performing models for free.

The hope is to use these models to design and test new interfaces that enable faster communication for users with communication difficulties. ''The work demonstrates that we can tap the creativity of users of social media and crowdsourcing technologies to help improve the lives of people unable to speak," say the researchers.

Summary
Researchers say the widespread study of sites such as Twitter and Facebook could result in synthetic voice systems, such as that used by Stephen Hawking, becoming ''faster and easier.''

Description
According to the researchers, ''the work demonstrates that they can tap the creativity of users of social media and crowdsourcing technologies to help improve the lives of people who are unable to speak".

Tags: Alternative communication, Artificial Speech Techonologies, Crowdsourcing, social media sites, St. Andrews University, The Imagination of Crowds

Posted by Sebastian

Oct 01, 2011 10:28 am GMT Viewed 880 times

Author: The Courier Source

Contact us if you are owner of this content and want to make changes.

Download Flag This

Live Chat

Categories

Topics

Events

University Researchers Harnessing Online Chat to Improve Artificial Speech Technologies

Comments

Crowdsourcing.org

Categories

Content

Crowdsourcing.org, an initiative by massolution®

Live Chat

Categories

Topics

Events

Related Content

University Researchers Harnessing Online Chat to Improve Artificial Speech Technologies

Comments

Crowdsourcing.org

Categories

Content

Crowdsourcing.org, an initiative by massolution®