ABSTRACT
We designed this book to show the range of speech technologies in computer-assisted language learning (CALL) in the United States and Europe. While that range can be described on many dimensions, our original idea was to present work in three basic pillars of speech technology relevant to CALL: recognition, synthesis, and visualization. Research in these pillars leads to computer applications that, potentially, listen to learners speak (speech recognition), talk flexibly to them (speech synthesis), and display pictures of their speaking difficulties (visualization of the speech signal).
