Speech synthesis systems

Speech synthesis systems are classified by two kinds of mapping:

1. Information-to-phonology:
   1. concatenated text;
   2. concatenated diphones with PSOLA pitch/duration synthesis;
   3. parametric / formant synthesis.
2. Phonology-to-speech:
   1. Text-to-Speech (TTS);
   2. Concept-to-Speech (CTS) or Meaning-to-Speech (MTS).

 
• MBROLA