StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion

Citations Over TimeTop 10% of 2019 papers

Abstract

Non-parallel multi-domain voice conversion (VC) is a technique for learning mappings among multiple domains without relying on parallel data.This is important but challenging owing to the requirement of learning multiple mappings and the nonavailability of explicit supervision.Recently, StarGAN-VC has garnered attention owing to its ability to solve this problem only using a single generator.However, there is still a gap between real and converted speech.To bridge this gap, we rethink conditional methods of StarGAN-VC, which are key components for achieving non-parallel multi-domain VC in a single model, and propose an improved variant called StarGAN-VC2.Particularly, we rethink conditional methods in two aspects: training objectives and network architectures.For the former, we propose a source-and-target conditional adversarial loss that allows all source domain data to be convertible to the target domain data.For the latter, we introduce a modulation-based conditional method that can transform the modulation of the acoustic feature in a domain-specific manner.We evaluated our methods on non-parallel multi-speaker VC.An objective evaluation demonstrates that our proposed methods improve speech quality in terms of both global and local structure measures.Furthermore, a subjective evaluation shows that StarGAN-VC2 outperforms StarGAN-VC in terms of naturalness and speaker similarity.

Related Papers

• → Automatic Labeling of Semantic Roles with a Dependency Parser in Hungarian Economic Texts(2015)1 cited
• → A Framework for Language Resource Construction and Syntactic Analysis: Case of Arabic(2018)1 cited
• → Morphological and Syntactic Processing for Text Retrieval(2004)8 cited
• Syntactic Parsing based on Phrase Structure in Natural Language Processing(2009)
• Exploiting the Translation Context for Multilingual WSD(2008)