Research

text version of diagram

The Research group focuses on three areas of research: Speech Processing, Text-based Language Processing, and Human Factors in Speech and Language Interfaces.

Speech Processing Research includes two main target areas: Multilingual Speech Recognition and Multilingal Text-to-Speech technology. These main areas are supported by activities in various other domains, such as pronunciation modelling, intonation modelling, language-, dialect- and speaker- identification and adaptation.

Areas of interest in Text-based Language Processing include morphological analysis and the bootstrapping of language resources. These research areas support the speech-related activities, and also contribute to the research area of automated statistical machine translation.

Human Factors Research investigates ways in which users interact with speech and language systems, with an emphasis on usability for low literacy and technologically unsophisticated users. The various main research streams all support and are strengthened by one another.