An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning

TL;DR

This paper provides a comprehensive overview of voice conversion techniques, from traditional statistical models to modern deep learning approaches, highlighting their performance, challenges, and available resources.

Contribution

It offers a detailed survey of current voice conversion methods, evaluates their performance, and discusses recent challenges and resources in the field.

Findings

Deep learning significantly improves voice quality and speaker similarity.

Voice Conversion Challenges (VCC) benchmarks current technology.

Resources for voice conversion research are summarized.

Abstract

Speaker identity is one of the important characteristics of human speech. In voice conversion, we change the speaker identity from one to another, while keeping the linguistic content unchanged. Voice conversion involves multiple speech processing techniques, such as speech analysis, spectral conversion, prosody conversion, speaker characterization, and vocoding. With the recent advances in theory and practice, we are now able to produce human-like voice quality with high speaker similarity. In this paper, we provide a comprehensive overview of the state-of-the-art of voice conversion techniques and their performance evaluation methods from the statistical approaches to deep learning, and discuss their promise and limitations. We will also report the recent Voice Conversion Challenges (VCC), the performance of the current state of technology, and provide a summary of the available resources for voice conversion research.