An Evaluation of Many-to-One Voice Conversion Algorithms with Pre-Stored Speaker Data Sets
Daisuke Tani, Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano · Institutional Repositories DataBase (IRDB) · 2007
This paper describes an evaluation of many-to-one voice conversion (VC) algorithmsconverting an arbitraryspeaker’s voice into a particulartarget speaker’s voice. These algorithmseffectively generatea conversion model for a new source speaker using multiple parallel data sets of many pre-storedsource speakers and the single target speaker. We conducted experimental evaluations for demonstrating the conversion performance of each of the many-to-one VC algorithms,including not only the conventional algorithmsbased on a speaker independentGMM and on eigenvoice conversion (EVC), but also new algorithms based on speaker selection and on EVC with speaker adaptive training (SAT). As a result, it is shown that an adaptation process of the conversion model improves significantlyconversion performance,and the algorithmbased on speaker selection works well even when using a very limited amount of adaptation data. Index Terms: voice conversion, many-to-one VC, EVC, SAT, speaker selection 1.