Text-to-speech algorithms based on FFT synthesis
- 6 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 667-670
- https://doi.org/10.1109/icassp.1988.196674
Abstract
The authors present FFT synthesis algorithms for a French text-to-speech system based on diphone concatenation. FFT synthesis techniques are capable of producing high quality prosodic modifications of natural speech. Several approaches are presented to reduce the distortions due to diphone concatenation. They are based on appropriate manipulations of the phase spectrum, either by phase equalization across all the diphones, or by phase smoothing between successive diphones. The resulting speech is significantly better quality than with conventional LPC synthesis. An experiment to reduce the computational cost by performing all the FFTs off-line is described. The resulting speech is slightly degraded with respect to 'full' FFT synthesized speech, but it remains more natural in comparison with the LPC speech.Keywords
This publication has 9 references indexed in Scilit:
- Speech synthesis by linear interpolation of spectral parameters between dyad boundariesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- On synthesizing natural-sounding speech by linear predictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The speech synthesis system for an unlimited Japanese vocabularyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Diphone synthesis using an overlap-add technique for speech waveforms concatenationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Mixed-phase deconvolution of speech based on a sine-wave modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Speech coder using phase equalization and vector quantizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- High quality time-scale modification for speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The waveform segment vocoder: A new approach for very-low-rate speech codingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Signal estimation from modified short-time Fourier transformIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984