Rule synthesis of speech from dyadic units
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 568-570
- https://doi.org/10.1109/icassp.1977.1170350
Abstract
Peterson, Wang, and Sivertsen[1] suggested the use of the units called "dyads" as the basic unit for speech synthesis. This paper describes an approach to speech synthesis by rule which uses a unit that is similar but smaller than the dyad as defined by Peterson et al. This new unit specifies only the transition between the two phones of the dyad, while the "steady state" portions are obtained by connecting with straight lines the end points of adjacent transitions. Further simplifications of the dyadic concept include a reduced collection of dyadic transitions, and the storage of only the end points of the dyadic transitions: the transitions themselves are then obtained by interpolation between these end points. This paper describes a complete rule synthesis scheme which uses these simplified dyads in combination with a word pronouncing dictionary and suitable prosodic rules.Keywords
This publication has 4 references indexed in Scilit:
- Rule synthesis of speech from dyadic unitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Speech resynthesis from phoneme-related parametersThe Journal of the Acoustical Society of America, 1976
- Speech Analysis and Synthesis by Linear Prediction of the Speech WaveThe Journal of the Acoustical Society of America, 1971
- Segmentation Techniques in Speech SynthesisThe Journal of the Acoustical Society of America, 1958