Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory
Authors:
- Alan W. BlackABAlan W. Black
- Keiichi TokudaKTKeiichi Tokuda
Top Cited Papers
- 15 October 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 15 (8) , 2222-2235
Abstract
In this paper, we describe a novel spectral conversion method for voice conversion (VC). A Gaussian mixture model (GMM) of the joint probability density of source and target features is employed for performing spectral conversion between speakers. The conventional method converts spectral parameters frame by frame based on the minimum mean square error. Although it is reasonably effective, the deterioration of speech quality is caused by some problems: 1) appropriate spectral movements are not always caused by the frame-based conversion process, and 2) the converted spectra are excessively smoothed by statistical modeling. In order to address those problems, we propose a conversion method based on the maximum-likelihood estimation of a spectral parameter trajectory. Not only static but also dynamic feature statistics are used for realizing the appropriate converted spectrum sequence. Moreover, the oversmoothing effect is alleviated by considering a global variance feature of the converted spectra. Experimental results indicate that the performance of VC can be dramatically improved by the proposed method in view of both speech quality and conversion accuracy for speaker individuality.Keywords
This publication has 31 references indexed in Scilit:
- A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech SynthesisIEICE Transactions on Information and Systems, 2007
- Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005IEICE Transactions on Information and Systems, 2007
- Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequencesComputer Speech & Language, 2007
- Modelling the uncertainty in recovering articulation from acousticsComputer Speech & Language, 2003
- Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in soundsSpeech Communication, 1999
- Continuous probabilistic transform for voice conversionIEEE Transactions on Speech and Audio Processing, 1998
- Speech spectrum conversion based on speaker interpolation and multi-functional representation with weighting by radial basis function networksSpeech Communication, 1995
- Transformation of formants for voice conversion using artificial neural networksSpeech Communication, 1995
- Unsupervised speaker adaptation from short utterances based on a minimized fuzzy objective function.Acoustical Science and Technology, 1993
- Voice conversion through vector quantization.Acoustical Science and Technology, 1990