MBR-PSOLA - TEXT-TO-SPEECH SYNTHESIS BASED ON AN MBE RE-SYNTHESIS OF THE SEGMENTS DATABASE

The use of the Time-Domain Pitch Synchronous OverLap-Add (TD-PSOLA) al gorithm in a Text-To-Speech synthesizer is reviewed. Its drawbacks are underlined and three conditions on the speech database are examined. In order to satisfy them, a previously described high quality resynthe sis process is developed and enhanced, which makes use of the well-kno wn Multi-Band Excited (MBE) model. An important by product of this ope ration is that optimal Pitch Marking turns out to be automatic. A temp oral interpolation block is finally added. The resulting Multi-Band Re synthesis Pitch Synchronous OverLap Add (MBR-PSOLA) synthesis algorith m supports spectral interpolation between voiced parts of segments, wi th virtually no increase in complexity. It provides the basis of a hig h-quality Text-To-Speech (TTS) synthesizer.