Time-Domain Pitch Synchronous Overlap and Add (TD-PSOLA) is a speech synthesis technique that uses a pitch-synchronous algorithm to modify the duration of speech segments to change the [[prosody]] ([[fundamental frequency]] and [[duration]]) of the synthesized speech.
TD-PSOLA can generate high-quality synthesized speech without much distortion or unwanted artifacts. It also operates efficiently with low computational demands, making it ideal for real-time use in devices with limited computing power.
![[td-psola.png]]
PSOLA analysis windowing, time-shift and synthesis windowing taken from [[Backstrom 2022]]
## References
Eric Moulines and Francis Charpentier. Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones. Speech communication, 9(5-6):453–467, 1990.
[[Backstrom 2022]] Chapter 3: [3.13 Pitch-Synchoronous Overlap-Add (PSOLA)](https://speechprocessingbook.aalto.fi/Representations/Pitch-Synchoronous_Overlap-Add_PSOLA.html?highlight=psola)