Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
This addresses the need for more natural and expressive speech synthesis in applications like virtual assistants, though it is incremental as it builds on existing methods.
The paper tackles the problem of jointly converting speaker identity and speaker-dependent emotional style in voice conversion, proposing a StarGAN-based framework that achieves effective results in objective and subjective evaluations.
Traditional voice conversion(VC) has been focused on speaker identity conversion for speech with a neutral expression. We note that emotional expression plays an essential role in daily communication, and the emotional style of speech can be speaker-dependent. In this paper, we study the technique to jointly convert the speaker identity and speaker-dependent emotional style, that is called expressive voice conversion. We propose a StarGAN-based framework to learn a many-to-many mapping across different speakers, that takes into account speaker-dependent emotional style without the need for parallel data. To achieve this, we condition the generator on emotional style encoding derived from a pre-trained speech emotion recognition(SER) model. The experiments validate the effectiveness of our proposed framework in both objective and subjective evaluations. To our best knowledge, this is the first study on expressive voice conversion.