English Emotional Voice Conversion Using StarGAN Model

The StarGANv2-VC model is a many-to-many non-parallel generative adversarial network (GAN) voice conversion (VC) that has proven effective in style tasks. This study aimed to investigate the scalability and diversity of for English emotional (EVC) across different speakers emotions. We carried out five experiments using an Emotional Speech Database (ESD), comprising single speaker-multi-emotion experiment, multi-speakers-multi-emotions experiment (gender-dependent), (gender-independent). also assessed effect training set size compared performance with CycleGAN model. Our found accurately converted pitch all four emotions (neutral, happy, sad, angry). However, model’s efficiency converting multi-emotions multi-speakers was not as high its multi-speakers. Further research needed this area. objectively quality speech Mel-frequency cepstral distortion (MCD) root-mean-square error (RMSE) spectrum prosody, respectively. Additionally, we conducted cross-emotion recognition convolutional recurrent neural (CRNN).