Alleviating the one-to-many mapping problem in voice conversion with context-dependent modeling
نویسندگان
چکیده
This paper addresses the "one-to-many" mapping problem in Voice Conversion (VC) by exploring source-to-target mappings in GMM-based spectral transformation. Specifically, we examine differences using source-only versus joint source/target information in the classification stage of transformation, effectively illustrating a "one-to-many effect" in the traditional acoustically-based GMM. We propose combating this effect by using phonetic information in the GMM learning and classification. We then show the success of our proposed context-dependent modeling with transformation results using an objective error criterion. Finally, we discuss implications of our work in adapting current approaches to VC.
منابع مشابه
Using Context-based Statistical Models to Promote the Quality of Voice Conversion Systems
This article aims to examine methods of optimizing GMM-based voice conversion systems performance in which GMM method is introduced as the basic method for improvement of voice conversion systems performance. In the current methods, due to using a single conversion function to convert all speech units and subsequent spectral smoothing arising from statistical averaging, we will observe quality ...
متن کاملCross - Lingual Voice Conversion
CROSS-LINGUAL VOICE CONVERSION Cross-lingual voice conversion refers to the automatic transformation of a source speaker’s voice to a target speaker’s voice in a language that the target speaker can not speak. It involves a set of statistical analysis, pattern recognition, machine learning, and signal processing techniques. This study focuses on the problems related to cross-lingual voice conve...
متن کاملطراحی یک روش آموزش ناموازی جدید برای تبدیل گفتار با عملکردی بهتر از آموزش موازی
Introduction: The art of voice mimicking by computers, has with the computer have been one of the most challenging topics of speech processing in recent years. The system of voice conversion has two sides. In one side, the speaker is the source that his or her voice has been changed for mimicking the target speaker’s voice (which is on the other side). Two methods of p...
متن کاملModeling of Partial Digest Problem as a Network flows problem
Restriction Site Mapping is one of the interesting tasks in Computational Biology. A DNA strand can be thought of as a string on the letters A, T, C, and G. When a particular restriction enzyme is added to a DNA solution, the DNA is cut at particular restriction sites. The goal of the restriction site mapping is to determine the location of every site for a given enzyme. In partial digest metho...
متن کاملA Time Dependent Pollution Routing Problem in Multi-graph
This paper considers a time dependent(the travel time is not constant throughout the day) pollution routing problem (TDPRP), which aids the decision makers in minimizing travel time, toll cost and emitted pollution cost. In complexity of urban areas most of the time one point is accessible from another with more than one edge. In contrast to previous TDPRP models, which are designed with only ...
متن کامل