Title :
VTLN-based voice conversion
Author :
Sundermann, D. ; Ney, Hermann
Author_Institution :
Dept. of Comput. Sci., RWTH Aachen Univ. of Technol., Germany
Abstract :
In speech recognition, vocal tract length normalization (VTLN) is a well-studied technique for speaker normalization. As voice conversion aims at the transformation of a source speaker´s voice into that of a target speaker, we want to investigate whether VTLN is an appropriate method to adapt the voice characteristics. After applying several conventional VTLN warping functions, we extend the piecewise linear function to several segments, allowing a more detailed warping of the source spectrum. Experiments on voice conversion are performed on three corpora of two languages and both speaker genders.
Keywords :
speech recognition; piecewise linear function; speaker normalization; speech recognition; vocal tract length normalization; voice conversion; Computer science; Frequency; Parameter estimation; Piecewise linear techniques; Smoothing methods; Speech recognition; Target tracking; Training data;
Conference_Titel :
Signal Processing and Information Technology, 2003. ISSPIT 2003. Proceedings of the 3rd IEEE International Symposium on
Print_ISBN :
0-7803-8292-7
DOI :
10.1109/ISSPIT.2003.1341181
