An estimation method of voice timbre evaluation values using feature extraction with Gaussian mixture model based on reference singer

• Published in: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5265 - 5269
• Main Authors: Yamane, Soichi, Kobayashi, Kazuhiro, Toda, Tomoki, Nakano, Tomoyasu, Goto, Masataka, Nakamura, Satoshi
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.03.2016
• Subjects: Acoustics; Age; Covariance matrices; Data models; Estimation; estimation of evaluation values; Feature extraction; Gaussian; Gaussian mixture model; Mathematical models; reference singer; Regression; Singing; singing voice synthesis; Timbre; Voice; voice timbre

This paper presents an estimation method of voice timbre evaluation values for arbitrary singer's singing voices generated with a singing voice synthesis system towards the development of a singing voice retrieval system. The voice timbre evaluation values are numerical values corresponding to...