Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Xiaoxue, Zhang, Huayun, Chen, Nancy F.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909634969731072
author Gao, Xiaoxue
Zhang, Huayun
Chen, Nancy F.
author_facet Gao, Xiaoxue
Zhang, Huayun
Chen, Nancy F.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02742
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions
Gao, Xiaoxue
Zhang, Huayun
Chen, Nancy F.
Audio and Speech Processing
Artificial Intelligence
Sound
Signal Processing
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.
title Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions
topic Audio and Speech Processing
Artificial Intelligence
Sound
Signal Processing
url https://arxiv.org/abs/2506.02742