Computer Technology to Aid Therapy of Speech Disorders

Under the auspices of the OLP project, a complete computer-based system was developed that may significantly contribute to the therapy of specific speech disorders at the articulation level. The system effectively combines automatic speech recognition and distance learning. Based on real-time audio-visual feedback of the subject's speech, therapy can be specially designed and customised to each individual's specific needs. With the aid of statistical data models developed during training phase or therapy session, speech production is evaluated. The distance learning capabilities allow remote collaboration and exchange of data for further analysis of different cases.

Part of the integrated system incorporates an articulation practice software tool that uses real-time phonetic mapping technology. The so-called STAPTk offers visual feedback of speech articulation using a kinematics map. User's speech activates a moving sprite around a window area that has been set up according to particular sounds. The closer the acoustics are to a target sound, the nearer the sprite comes to the specific target.

The developed prototype has been based on a neural networks technology trained to map acoustics to a 2D position. The key application of the innovative technology is in speech therapy when training individuals to improve articulation. Other applications include practicing speech in second language learning.

For further information, please visit:
http://www.xanthi.ilsp.gr/olp/

Copyright ©European Communities, 2008
Neither the Office for Official Publications of the European Communities, nor any person acting on its behalf, is responsible for the use, which might be made of the attached information. The attached information is drawn from the Community R&D Information Service (CORDIS). The CORDIS services are carried on the CORDIS Host in Luxembourg - http://cordis.europa.eu. Access to CORDIS is currently available free-of-charge.

Most Popular Now

Making Cancer Vaccines More Personal

In a new study, University of Arizona researchers created a model for cutaneous squamous cell carcinoma, a type of skin cancer, and identified two mutated tumor proteins, or neoantigens, that...

AI Tool Beats Humans at Detecting Parasi…

Scientists at ARUP Laboratories have developed an artificial intelligence (AI) tool that detects intestinal parasites in stool samples more quickly and accurately than traditional methods, potentially transforming how labs diagnose...