A birdseye view of Open Brain AI main developments.
Open Brain AI is an advanced computational platform and a sophisticated ensemble of tools that have been meticulously developed and refined as early as 2007.
The first code was developed for Charalambos Themistocleous PhD research in 2007. He developed text to IPA converter and early text-to-sound alignment facilitate his research.
Speech-to-Text transcription interfaces for Greek, English, and Swedish. The release of Tensorflow by Google allowed us to quicly develop and test various types of Neural Nets, including Recurrent (LSTM), Convolutional, and Feedforward Deep Neural Networks. We build the a machine learning application for the identification of patients with Mild Cognitive Impairment from Healthy Controls.
Developing a pipeline for analyzing audio recordings of patients, transcribing them automatically, and conducting measures of grammar and speech. Subsequently the measures are feeded to Deep Neural Networks to provide diagnosis. We applied the system to subtype patients with Primary Progressive Aphasia.
In the shadow of the global pandemic in 2020, Open Brain AI evolved into a unified interface for these diverse tools, breathing new life into them.
The Django site was developed and the Domain Name Open Brain AI was acquired in a cafe under the Acropolis in Athens, Greece. Open Brain AI was underwent further refinements in the summer that followed. A spelling algorithm, the subject of a previously published paper co-authored with Brenda Rapp, constitutes another vital component. The source code of the spelling up is available on Github.
Access the online tools now from the link below.