Crimsonwing has been awarded the tender to develop the Maltese Text to Speech Synthesiser by the Foundation for Information Technology Accessibility (FITA) in August 2010.
Crimsonwing has been working on the solution for this unique Synthesiser for several months now and is just bringing it to perfection until its release date in 2012, when it will be freely available for download.
The project is co-financed (85%) by the EU’s ERDF (European Regional Development Fund), and national Maltese funds (15%). It is part of the Operational Programme I – Cohesion Policy 2007-2013 Investing in Competitiveness for a Better Quality of Life - which is exactly what Crimsonwing is aiming for.
The Speech Synthesiser will have three different voices - a male, female and a child voice. The quality of the synthesised speech is highly dependent on the corpus of recorded speech used to create the diphone database. This is why it is recorded in a professional studio to ensure best quality of sound (44 KHz 16bit sound quality). A large database of recordings is required for sufficiently natural-sounding speech, spanning several to tens of hours.
The Synthesiser will be Windows SAPI compliant (Speech Application Programming Interface) and inter-operable with any application that is SAPI compliant (e.g. Window-Eyes Screen Reader, etc).
“Crimsonwing is very proud to be associated with the FITA for the development of a Maltese Speech Engine. Whilst the technology exists for a number of languages, this is a first for Maltese! The application of this tool is widespread and will facilitate use of ICT products or services to illiterate persons and people with vision, dyslexia or cognitive difficulties. The project is particularly technically challenging. However, the team has made good progress and is well on track with the release of the 2nd prototype“ said Carmel Gafa, Crimsonwing’s Head of Technology.
The Crimsonwing R&D team has presented this at GhILM's third International Conference on Maltese Linguistics on the 9th April 2011, presenting the findings and developments to date for Crimsonwing's Speech Synthesiser.