Physics

Accounting

Frame (networking)

Trajectory

Business

Pattern recognition (psychology)

Feature (linguistics)

Mathematics

Operating system

Algorithm

Statistics

Astronomy

Mean squared error

Gaussian

Philosophy

Spectral density

Artificial intelligence

Variance (accounting)

Computer science

Linguistics

Gaussian process

Quantum mechanics

Speech recognition

Process (computing)

Mixture model

Telecommunications

IEEE Transactions on Audio Speech and Language Processing

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.

Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory