The key paper about the STRAIGHT vocoder, which was originally intended for manipulating recorded natural speech.
Hideki Kawahara, Ikuyo Masuda-Katsuse and Alain de Cheveigné “Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds” in Speech Communication, Volume 27, Issues 3–4, April 1999, Pages 187–207. DOI: 10.1016/S0167-6393(98)00085-5
Also see the STRAIGHT website.