From: A unit selection text-to-speech-and-singing synthesis framework from neutral speech: proof of concept
∣αst∣
[0–4]
(4–7]
(7–12]
> 12
α<1
[0.8–1)
[0.67–0.8)
[0.5–0.67)
< 0.5
α>1
(1–1.26]
(1.26–1.50]
(1.50–2]
> 2