# Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

arXiv: https://arxiv.org/abs/2509.24629 · HTML: https://mlsanity.com/paper/2509.24629/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2025.

## Built on by (most cited first, 7 of 7)

- [VoXtream2: Full-stream TTS with dynamic speaking rate control](https://mlsanity.com/paper/2603.13518/) (2026)
- [Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input](https://mlsanity.com/paper/2603.06444/) (2026)
- [The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation](https://mlsanity.com/paper/2604.26347/) (2026)
- [HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech](https://mlsanity.com/paper/2606.28249/) (2026)
- [WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS](https://mlsanity.com/paper/2607.06461/) (2026)
- [GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech](https://mlsanity.com/paper/2607.02633/) (2026)
- [SEmoEdit: Probing and Harnessing the Editability of Pre-trained Speech Flows](https://mlsanity.com/paper/2609.34648/) (2026)

## Abstract (arXiv)

While emotional text-to-speech (TTS) has made significant progress, most existing research remains limited to utterance-level emotional expression and fails to support word-level control. Achieving word-level expressive control poses fundamental challenges, primarily due to the complexity of modeling multi-emotion transitions and the scarcity of annotated datasets that capture intra-sentence emotional and prosodic variation. In this paper, we propose WeSCon, the first self-training framework that enables word-level control of both emotion and speaking rate in a pretrained zero-shot TTS model, without relying on datasets containing intra-sentence emotion or speed transitions. Our method introduces a transition-smoothing strategy and a dynamic speed control mechanism to guide the pretrained TTS model in performing word-level expressive synthesis through a multi-round inference process. To further simplify the inference, we incorporate a dynamic emotional attention bias mechanism and fine-tune the model via self-training, thereby activating its ability for word-level expressive control in an end-to-end manner. Experimental results show that WeSCon effectively overcomes data scarcity, achieving state-of-the-art performance in word-level emotional expression control while preserving the strong zero-shot synthesis capabilities of the original TTS model.