Diphone

A unit of speech used in text-to-speech synthesis, consisting of the transition from the middle of one phoneme to the middle of the next. Diphone-based synthesis works by recording a set of all possible phoneme-to-phoneme transitions in a language and concatenating the appropriate diphones to produce complete utterances. This approach produces reasonably natural speech while requiring a relatively small database — typically a few thousand recorded segments per language — making it practical for resource-constrained environments such as developing assistive technology for less widely supported languages. Diphone synthesis was an important step between early formant synthesis and modern unit selection or neural speech synthesis.