Editing Hidden Markov Models in Speech Synthesis (section)

==== Concatenative Synthesis ====
Concatenative synthesis addresses the difficulty in generating speech parameters from input text specifications. It employs a data-driven approach by connecting natural, prerecorded speech units, such as words, syllables, or diphones. Diphones are widely used and start in the middle of one phoneme and extend to the middle of the following one, capturing coarticulation. Building a diphone inventory involves recording all phonemes within possible contexts and labeling and segmenting diphones <ref>Tokuda, K., Nankaku, Y., Toda, T., Zen, H., Yamagishi, J., & Oura, K. (2013). Speech Synthesis Based on Hidden Markov Models. ''Proceedings of the IEEE'', ''101''(5), 1234–1252. <nowiki>https://doi.org/10.1109/JPROC.2013.2251852</nowiki></ref>. The pitch and duration of each diphone must be adjusted to match the prosody part of the specification. This approach balances memory requirements, complexity, and naturalness.