The Speech Transcription Platform Project
The speech transcription platform project, supported by the Department of Arts and Culture, entailed the development of a Web-based platform that would enable users with varying degrees of sophistication to easily and quickly transform speech in the South African languages to text, with the assistance of the latest in speech recognition technology.
The Babel Project
The Babel project was an international collaborative project aimed at solving the spoken term detection task in previously unstudied languages. MuST was part of the BabelOn consortium consisting of BBN (USA), BUT (Czech Republic), LIMSI (France), MIT (USA) and Johns Hopkins University (USA).
Google Text To Speech Project
MuST collaborated with Google to create new voices for four South African languages. Different female speakers with similar voice profiles were selected as voice contributors. This allowed for voices to be mixed in such a way that the resulting voice would not sound like any specific individual. The datasets were released for further use.
The SADE Project
The SADE project, supported by the Department of Arts and Culture, the Technology Innovation Agency and commercial partners, developed a fully South African directory inquiries system, specifically built to deal with South African accents and names.
The V-BAT Project
The V-BAT project was carried out in collaboration with the Web Foundation and One World South Asia and funded by the Rockefeller Foundation. It investigated the applicability of speech technology in helplines designed to assist small farmers in India with relevant, reliable and up-to-date information.
The VOICES Project
The EU-funded VOICES project developed speech technology, use cases and business models involving voice technology in two application domains (health and agriculture) in West Africa. MuST researchers were particularly involved in developing and assessing speech recognition and speech synthesis in two of Mali’s languages, namely Bambara and Bomu.
The Lwazi Project
The Lwazi project, funded by the South African government, was a large-scale project to develop speech technologies, and their applications, for South Africa’s eleven official languages. This project was carried out under the leadership of the CSIR Meraka Institute, and produced a wide range of open-source tools, public-domain resources and generally accessible applications. MuST and the CSIR Meraka Institute also collaborated on resource development for the National Centre for Human Language Technologies (NCHLT) in developing extensive, high-quality speech resources for public use. Many of these resources are now available for public download from the Resource Management Agency (RMA).
The CAIR Project
MuST is a node of the Centre for Artificial Intelligence Research (CAIR), a South African research network that conducts foundational, directed and applied research into various aspects of Artifical Intelligence.