Some languages allow the clustering of the same consonant in vowel contexts and this phenomenon is known as "consonant gemination". Gemination plays a particular role in the phonology of such languages because several words change meaning as a function of singleton versus geminate consonants (minimal pairs). The GEMMA project, started in 1993, investigates the role of gemination in the Italian language.
Creating an automatic speech recognizer that imitates the process through which a listener deciphers the words intended by a speaker requires understanding how lexical items are stored in memory. The LaMIT project, carried out in cooperation with the Speech Communication Group at the Massachusetts Institute of Technology, is investigating the lexical access model proposed by Kenneth N. Stevens for American English and extending it to Italian. The goal is to understand whether Stevens's approach has universal application across languages, with relevant implications for how the human brain recognizes speech. This investigation will form the foundation for the development of a complete speech recognition system for Italian.
The xkl project is a joint initiative between the Speech groups of the Massachusetts Institute of Technology and Sapienza University of Rome. The goal is to make a legacy software called xkl actual and modern and to make it available to the speech research community. The xkl code was originally created by the late Dennis Klatt (see the documentation page on the MIT website and Chapter 8 of the book on speech software tools Dennis Klatt was working on when he passed away).
The xkl software is covered by an MIT licensing agreement that grants free access to the software for non-commercial use, and defines terms for commercial use.