KLATTSTAT: knowledge-based parametric speech synthesis.
Gopala K. Anumanchipalli, Ying-Chang Cheng, Joseph Fernandez et al. · SSW · 2010
This paper is an initial investigation into using knowledge-based parameters in the field of statistical parametric speech synthesis (SPSS). Utilizing the types of speech parameters used in the Klatt Formant Synthesizer we present automatic techniques for deriving such parameters from a speech database and building a statistical parametric speech synthesizer from these derived parameters. Although the work is exploratory, it shows promise in using more speech production inspired parameterizations for statistical speech synthesis.
Cited by 9 works.
Authors
References
- Software for a cascade/parallel formant synthesizer
- Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds
- From text to speech: the MITalk system
- Unit selection in a concatenative speech synthesis system using a large speech database
- Statistical parametric speech synthesis
- CLUSTERGEN: a statistical parametric synthesizer using trajectory modeling
- Acoustics of American English Speech: A Dynamic Approach
- An Excitation Model for HMM-Based Speech Synthesis Based on Residual Modeling
- A deterministic plus stochastic model of the residual signal for improved parametric speech synthesis
- Minimum generation error training by using original spectrum as reference for log spectral distortion measure