Title :
Spectral Conversion Based on Maximum Likelihood Estimation Considering Global Variance of Converted Parameter
Author :
Toda, Tomoki ; Black, Alan W. ; Tokuda, Keiichi
Author_Institution :
Language Technol. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
fDate :
March 18-23, 2005
Keywords :
Gaussian processes; maximum likelihood estimation; probability; smoothing methods; spectral analysis; speech processing; statistical analysis; Gaussian mixture model; dynamic features; global variance; maximum likelihood estimation; over-smoothing; parameter estimation; postfiltering; probability density; spectral conversion; spectral enhancement; voice transformation; Covariance matrix; Data mining; Degradation; Heuristic algorithms; Maximum likelihood estimation; Parameter estimation; Smoothing methods; Speech synthesis; Training data; Vectors;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415037
