Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions
This work addresses the need for more natural and diverse emotional speech synthesis in human-computer interactions, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackles the problem of generating expressive speech for unseen and mixed emotions, which existing TTS systems cannot handle due to their reliance on predefined categorical emotions. The proposed PUE approach successfully enables zero-shot synthesis of such emotional speech by using emotion-guided prompt learning and LLM contextual knowledge.
Existing expressive text-to-speech (TTS) systems primarily model a limited set of categorical emotions, whereas human conversations extend far beyond these predefined emotions, making it essential to explore more diverse emotional speech generation for more natural interactions. To bridge this gap, this paper proposes a novel prompt-unseen-emotion (PUE) approach to generate unseen emotional speech via emotion-guided prompt learning. PUE is trained utilizing an LLM-TTS architecture to ensure emotional consistency between categorical emotion-relevant prompts and emotional speech, allowing the model to quantitatively capture different emotion weightings per utterance. During inference, mixed emotional speech can be generated by flexibly adjusting emotion proportions and leveraging LLM contextual knowledge, enabling the model to quantify different emotional styles. Our proposed PUE successfully facilitates expressive speech synthesis of unseen emotions in a zero-shot setting.