/en/ - General

Take it easy!

Posting mode: Reply

Visit J-List - Your Favorite Online Shop and Friend in Japan

Get the Newest Figures from J-List - Your Favorite Online Shop and Friend in Japan

[]

Name
E-mail
Options
Subject
Comment	Max comment length: 4096 Emotes Styling
Files	Drag files to upload or click here to select them Choose File Supported file types: GIF, JPG, PNG, WebM, OGG, SWF
Password	(Password used for deletion)

01/20/25	A total rewrite for the site is in progress. Read more.
05/21/24	Happy birthday hikari3! (News post)
12/21/23	Recent news post: Check here. Also, new board added: /i/ - Oekaki.
11/25/23	Accepting banner submissions; check this thread for more details.
11/17/23	New blotter! Use this to keep an eye for small updates.
	[Show All]

Read-Only. Visit the all-new hikari3.ch

VOCALOID1 MFPA implementation QueueSevenM!Tnq5UWtkfs 03/02/2026 (Mon) 21:20:44 No. 12155

So I've been working on a project to re-implement the VOCALOID1 engine. I'm basing it on the description in Jordi Bonada's PhD thesis "Voice Processing and Synthesis by Performance Sampling and Spectral Models" and not the original papers as the former is more detailed, easier to follow, and also describes the VOCALOID2 engine. After a lot of trouble with getting TWM f0 estimation to work, I've finally gotten to implementing MFPA. And amazingly, it seems to have worked first try. Compare my results: https://i.ibb.co/dsvgv0fd/Screen-Shot-2026-03-02-at-3-54-48-PM.png To the results in the study: https://i.ibb.co/C3fjdWVd/Screen-Shot-2026-03-02-at-3-55-09-PM.png

Your fortune: Bad Luck

Index Catalog Archive Top Reply

Posters: 1

Delete Post: [ File only ]

Reason: Global

no cookies?

Quick Reply