5th International Conference on Spoken Language Processing
This paper describes a method of concatenative speech synthesis that makes use of 3-dimensional labelling of speech, and shows how this can be applied to the synthesis of both mono-lingual and foreign-language speech. The dimensions encode phonetic, prosodic, and voice-quality information in order to fully describe the acoustic characteristics of each speech segment.
Sound Example #1 Sound Example #2
Sound Example #3 Sound Example #4 Sound Example #5 Sound Example #6
Bibliographic reference. Campbell, Nick (1998): "Multi-lingual concatenative speech synthesis", In ICSLP-1998, paper 0024.