SoundHint system for blind and partially sightless people

The SoundHint system that will enable blind and partially sightless people to independently use applications written for Windows 98 and NT environment is under development. The goal is to develop an application that will vocally describe the interface of any application, read text from the screen, tell which control or window has focus, read icons, menus, folders, file names, etc. This will make visually impaired people capable of using applications originally intended for GUI users. The main part of the system is our Slovenian text-to-speech synthesizer. It is based on the concatenation of basic speech units using a TD-PSOLA technique. Acoustic segments inventory consists of diphones and some frequently used polyphones. This synthesizer is also used in an employment agent EMA that provides employment information through the Internet.

[1]  Thierry Dutoit,et al.  MBR-PSOLA: Text-To-Speech synthesis based on an MBE re-synthesis of the segments database , 1993, Speech Commun..

[2]  Saso Dzeroski,et al.  Learning Multilingual Morphology with CLOG , 1998, ILP.

[3]  Ales Dobnikar.  Modeling segment intonation for Slovene TTS system , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[4]  Alan W. Black,et al.  Letter to sound rules for accented lexicon compression , 1998, ICSLP.

[5]  Matjaz Gams,et al.  Improvements in slovene text-to-speech synthesis , 1998, ICSLP.

[6]  Eric Moulines,et al.  Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones , 1989, Speech Commun..

[7]  Matjaz Gams,et al.  Text-to-speech synthesis in Slovenian language , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).