Title :
Voice conversion using Viterbi algorithm based on Gaussian mixture model
Author :
Zhi-Hua, Jian ; Zhen, Yang
Author_Institution :
Nanjing Univ. of Post & Telecom, Nanjing
fDate :
Nov. 28 2007-Dec. 1 2007
Abstract :
A novel method for voice conversion based on Viterbi algorithm is proposed in this paper, which uses the matrix of transition probabilities of the target speaker to represent the relationship between the subsequent frames, and then determines the most appropriate component of the GMM by utilizing the Viterbi algorithm for each frame of the source speaker. It avoids the spectral discontinuities between adjacent frames and the spectral averaging. Both objective and subjective evaluations have demonstrated that the proposed method improves the performance of the conventional voice conversion system based on GMM.
Keywords :
matrix algebra; probability; speech processing; Gaussian mixture model; Viterbi algorithm; spectral averaging; spectral discontinuities; transition probability matrix; voice conversion; Data mining; Degradation; Loudspeakers; Signal processing algorithms; Speech enhancement; Speech processing; Speech synthesis; Telecommunications; Vectors; Viterbi algorithm; Gaussian mixture model; Speech Processing; Viterbi algorithm; Voice conversion;
Conference_Titel :
Intelligent Signal Processing and Communication Systems, 2007. ISPACS 2007. International Symposium on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-1447-5
Electronic_ISBN :
978-1-4244-1447-5
DOI :
10.1109/ISPACS.2007.4445816
