This paper describes recent improvements to our singing voice synthesizer based on concatenation and transformation of audio samples using spectral models. Improvements include firstly robust automation of previous singer database creation process, a lengthy and tedious task which involved recording scripts generation, studio sessions, audio editing, spectral analysis, and phonetic based segmentation; and secondly synthesis technique enhancement, improving the quality of sample transformations and concatenations, and discriminating between phonetic intonation and musical articulation.

Authors: Blaauw, Merlijn; Bonada, Jordi; Loscos, Alex
Affiliation: Universitat Pompeu Fabra - MTG
AES Convention: 121 (October 2006) Paper Number: 6900
Publication Date: October 1, 2006 Import into BibTeX
Subject: Analysis and Synthesis
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=13734

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD 121Papers)   /121/6900.pdf

Start a discussion about this paper!