Title :
Regression approaches to perceptual age control in singing voice conversion
Author :
Kobayashi, Kaoru ; Toda, Takechi ; Nakano, T. ; Goto, Misako ; Neubig, Graham ; Sakti, Sakriani ; Nakamura, Shigenari
Author_Institution :
Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Ikoma, Japan
Abstract :
The perceptual age of a singing voice is the age of the singer as perceived by the listener, and is one of the notable characteristics that determines perceptions of a song. In this paper, we describe a novel voice timbre control technique based on the perceptual age for singing voice conversion (SVC). Singers can sing expressively by controlling prosody and voice timbre, but the varieties of voices that singers can produce are limited by physical constraints. Previous work has attempted to overcome the limitation through the use of statistical voice conversion. This technique makes it possible to convert singing voice timbre of an arbitrary source singer into that of an arbitrary target singer. However, it is still difficult to intuitively control singing voice characteristics by manipulating parameters corresponding to specific physical traits, such as gender and age. In this paper, we develop a technique for controlling the voice timbre based on perceptual age that maintains the singer´s individuality. The experimental results show that the proposed voice timbre control method makes it possible to change the singer´s perceptual age while not having an adverse effect on the perceived individuality.
Keywords :
regression analysis; speech synthesis; SVC; age control; arbitrary source singer; arbitrary target singer; perceptual age control; regression approaches; singing voice characteristics; singing voice conversion; singing voice timbre; statistical voice conversion; voice timbre control technique; Joints; Speech; Static VAr compensators; Timbre; Training; Vectors; perceptual age; regression approaches; singer´s individuality; singing voice conversion; voice timbre control;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
Conference_Location :
Florence
DOI :
10.1109/ICASSP.2014.6855139