Vision, Speech and Natural Languages
Research in vision, speech and natural language are three core areas of artificial intelligence in which Carnegie Mellon Computer Science has had a continuing strong presence.
Computer vision involves acquiring and interpreting the rich visual world around us. There are seven CSD faculty members, and more than 20 across all of SCS, whose research spans various aspects of computer vision, including core vision capabilities, cartography and photo interpretation, biology-motivated vision, people image analysis, and the convergence of computer vision and graphics. Our speech recognition efforts are more tightly coupled with natural language processing and machine translation. Such projects challenge not only the language technologies aspects, but also severe system design, integration, networking, user-interfaces and form factor analysis. CMU's early natural language processing efforts were focused on building robust NLP interfaces to databases and interactive applications, which required parsing imperfectly typed input. Today, our efforts focus on open-domain machine translation, which requires statistical machine learning models and training from large-scale parallel (pre-translated) text. Other work focuses on the role of NLP in intelligent tutoring systems together with the Science of Learning Center and in interactive dialog systems.