A Study of Bilinear Models in Voice Conversion

Abstract

This paper presents a voice conversion technique based on bilinear models and introduces the concept of contextual modeling. The bilinear approach reformulates the spectral envelope representation from line spectral frequencies feature to a two-factor parameterization corresponding to speaker identity and phonetic information, the so-called style and content factors. This decomposition offers a flexible representation suitable for voice conversion and facilitates the use of efficient training algorithms based on singular value decomposition. In a contextual approach (bilinear) models are trained on subsets of the training data selected on the fly at conversion time depending on the characteristics of the feature vector to be converted. The performance of bilinear models and context modeling is evaluated in objective and perceptual tests by comparison with the popular GMM-based voice conversion method for several sizes and different types of training data

Voice Conversion

“…line spectral frequencies to a two-factor parameterization corresponding to speaker identity and phonetic information. The spectral vector y sc , uttered by speaker s and corresponding to the phonetic content class c, is represented as a product of a speaker-dependent matrix A s and a phonetic content vector b c using the asymmetric bilinear model (Popa et al, 2011):…”

A Unified Factors Analysis Framework for Discriminative Feature Extraction and Object Recognition

“…Content and style factors can be seen as two independent elements which influence the object and determine the observation [15], as mentioned before. The information contributed to recognition is defined as content factor and the negative information is style factor during pattern recognition.…”

“…Solutions are given through the optimization of both intuitive and pragmatic objectives, with the aim of extracting low-dimensional, simplified, and robust features from the high-dimensional, redundant, disturbed, and distorted original data. Content and style factors can be seen as the two components of an object [15]. During pattern recognition field, the information explored as base of recognition is defined as content factor and the information disturbed recognition is defined as style factor.…”