4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Dynamical Modelling of Vowel Sounds as a Synthesis Tool

M. Banbrook, S. McLaughlin

Department of Electrical Engineering, University of Edinburgh, Edinburgh, UK

Speech synthesis can be produced using many varied techniques from formant/parametric synthesis to concatenation approaches. This paper presents a novel technique, based on the nonlinear dynamics of speech rather than than the time or frequency domain representations. It is demonstrated that the technique can be implemented effectively and used to produce high quality synthesised speech.

Full Paper
Sound Examples: #1   #2   #3   #4   #5   #6  

Bibliographic reference.  Banbrook, M. / McLaughlin, S. (1996): "Dynamical modelling of vowel sounds as a synthesis tool", In ICSLP-1996, 1981-1984.