CTMedia bridges with German Research Center for Artificial Intelligence

CTMedia has recently established a new international relationship with the the Speech Group in the Language Technology lab of the German Research Center for Artificial Intelligence (DFKI). This new international link will be first implemented with a 6 month  internship of the Phd student Angel Calzada, hosted at DFKI.   The work of Angel Calzada will be focussed on the expressive speech synthesis research line and will be closely linked to the ongoing work in the projects PAVOQUE and SSPNet. We hope that this will be the first step towards a fruitful collaboration! About DFKI Founded in 1988, the German Research Center for Artificial Intelligence (DFKI) is one of the largest nonprofit contract research institutes in the field of innovative software technology based on artificial intelligence methods. R&D is carried out in several research labs from world-class basic research to product commercialisation including Language Technology, Intelligent User Interfaces, and Robotics with close ties with major German universities. DFKI Language Technology Lab The Language Technology Lab conducts research in modelling and processing human languages. They develop and improve core language technologies for information extraction, mono- and cross-lingual information access, morphological processing, deep linguistic analysis, text summarization, document categorization, grammar checking, speech synthesis, and other advanced software functionalities. They design and implement processing components such as taggers, parsers, generators and tools for the maintenance of terminologies and dictionaries. They integrate their techniques and components with other technologies such as speech processing, data bases, or graphics. They implement software prototypes for a variety of applications. They create resources for R&D such as lexicons, grammars, test suites, and discourse models. They develop methods and tools for technology and system evaluation together with partners in research and industry. They provide consulting on the potentials and ramifications of language technology and on the selection of methods, products and services for specific tasks. DFKI-LT Speech Group The speech group in the DFKI Language Technology lab carries out research on expressive, multilingual, and adaptive Text-To-Speech Synthesis (TTS) as well as emotion-oriented interactive technologies. The open source modular TTS platform MARY (http://mary.dfki.de/), developed by the DFKI speech group, provides state-of-the art speech synthesis using the two most recent synthesis algorithms: high quality unit selection as well as compact Hidden Markov Model (HMM) based synthesis. The group’s core competences include a range of methods for generating expressivity in synthetic speech, voice customization, and tools for the quick creation of new voices. In the international speech synthesis evaluation event “Blizzard Challenge”, MARY TTS regularly reaches high scores, showing that it can compete with the best state-of-the-art systems world-wide.