ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

An enhanced ABS/OLA sinusoidal model for waveform synthesis in TTS

Michael W. Macon, Mark A. Clements

This paper describes a method for text-to-speech waveform synthesis based on the Analysis-by-Synthesis/Overlap-Add (ABS/OLA) sinusoidal model. This model has been shown in previous work to be a useful framework for pitch and time-scale modification of both speech and music signals. This paper explores some extensions of the original ABS/OLA formulation that attempt to overcome specific artifacts, including a phase dithering approach for unvoiced speech synthesis and an improved pitch modification method that compensates for undesirable energy modulation effects. The implementation of the model within a text-to-speech synthesis (TTS) system is described, and the results of a listener evaluation of the method are discussed.


doi: 10.21437/Eurospeech.1999-508

Cite as: Macon, M.W., Clements, M.A. (1999) An enhanced ABS/OLA sinusoidal model for waveform synthesis in TTS. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2327-2330, doi: 10.21437/Eurospeech.1999-508

@inproceedings{macon99_eurospeech,
  author={Michael W. Macon and Mark A. Clements},
  title={{An enhanced ABS/OLA sinusoidal model for waveform synthesis in TTS}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={2327--2330},
  doi={10.21437/Eurospeech.1999-508}
}