This paper discusses some important issues in current speech synthesis research. Modelling of speaker characteristics and emotions are used as a examples of new trends in the area. The relation to speech recognition research is also emphasized. New methods such as automatic learning and the use of new analysis techniques are also referred to.
Bibliographic reference. Carlson, Rolf (1991): "Synthesis: modelling variability and constraints", In EUROSPEECH-1991, 1043-1048.