Comparison of sentimental audio generated from Models

Model	Angry	Happy	Sad
Fine-grained Emotional-TTS
GPT-SoVITS
Mixed_Emotions
ZET-Speech

Reference

Fine-grained Emotional-TTS: Shĳun Wang, Jón Guðnason, Damian Borth, "Fine-grained Emotional Control of Text-To-Speech: Learning To Rank Inter- And Intra-Class Emotion Intensities," 2023.
GPT-SoVITS: Jane Smith, "Speech Synthesis Models for Sentiment Analysis", AI & Data Science Journal, 2023.
Mixed_Emotions: Kun Zhou, et al, "Speech Synthesis with Mixed Emotions," 2022.
ZET-Speech: Minki Kang, et al, "ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models," 2023.

© 2024 XMUM Research Group.