Improvements to a Sample-Concatenation Based Singing Voice Synthesizer

TitleImprovements to a Sample-Concatenation Based Singing Voice Synthesizer
Publication TypeConference Paper
Year of Publication2006
AuthorsBonada, J., Blaauw M., & Loscos A.
AbstractThis 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.
preprint/postprint documentfiles/publications/9d0455-AES121-jbonada-mblaauw-aloscos.pdf