Outside Echo

This page outlines Outside Echo's two main projects, turning the initial idea into a concrete vision and then making it reality through an innovative approach to both project management and research & development.

LLSTI - incubating SLT centres in the developing world

Map of LLSTI PartnersAs the new millenium arrived, Speech and Language Technology (SLT) was starting to provide an alternative interface to information systems, offering great promise for those in the developing world unable to access mainstream IT. But SLT companies were only slowly expanding their repetoire of languages, each new language requiring resources and expertise that was hard to obtain and uneconomic to maintain. Surely the long term solution was for the language technology expertise and resources to be in the country where the language was spoken and available for everyone's benefit.

The object of the Local Language Speech Technology Initiative (LLSTI) was therefore to incubate centres of SLT expertise around the world, focusing on developing and applying the technology to address information access issues in those countries. Outside Echo initiated and managed the Local Language Speech Technology Initiative (LLSTI) from 2003-2007. This unique global, developing-world, project based on Open Source software, produced text-to-speech (TTS) technology, and voice applications using that technology, in regional languages. LLSTI partners have produced phone-based information systems in Kiswahili and all eleven South African languages.

Managing LLSTI initially involved communicating the vision; securing funding; requests for participation; managing sub-contracts with partner organisations; organising training & workshops around the world; reporting to sponsors etc. In the second phase it involved working with other organisations to identify and then prototype services which make use of the technology, with the aim of impacting lives of people otherwise unreached by IT.

You can find out more about LLSTI at the project archive.

Audio Notetaker - multi-media note-taking

Taking comprehensive notes from lectures, interviews and meetings is never easy, but for people with dyslexia, dyspraxia and other difficulties such as RSI, it can be almost impossible. To solve this, we invented the concept of audio note-taking, which is a technique which uses image, text, colour and audio together to provide a set of multi-media notes. The technique is embodied in a novel PC, Mac - and now mobile - application called Audio Notetaker.

Audio Notetaker screenshot

Audio Notetaker is neither an audio editor or a transcription tool - yet can be used effectively for both. It allows the audio to be treated in exactly the same way as text, so the student has the straight choice whether to keep information in audio or textual form. To achieve this, Audio Notetaker has a novel user interface for the audio, as well as complex signal processing to accurately identify the speaker's phrases in even the most poorly-recorded lecture.

Outside Echo developed the ideas for Audio Notetaker from the initial concept, through UI simulation, focus groups, initial prototypes all the way to full commercial deployment, at which point it span out Sonocent Ltd to promote and develop the product.

You can find out more about Audio Notetaker, view a demonstration and download a trial version on Sonocent's website.