# Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS

arXiv: https://arxiv.org/abs/2409.18512 · HTML: https://mlsanity.com/paper/2409.18512/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 27 Sep 2024.

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023)
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset](https://mlsanity.com/paper/2010.14794/) (2020)
- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://mlsanity.com/paper/2302.12822/) (2023)
- [Universal Information Extraction as Unified Semantic Matching](https://mlsanity.com/paper/2301.03282/) (2023)
- [ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations](https://mlsanity.com/paper/2312.14398/) (2023)
- [Learning Speech Representation From Contrastive Token-Acoustic Pretraining](https://mlsanity.com/paper/2309.00424/) (2023)
- [Controlling Emotion in Text-to-Speech with Natural Language Prompts](https://mlsanity.com/paper/2406.06406/) (2024)
- [Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis](https://mlsanity.com/paper/2303.07711/) (2023)

## Built on by (most cited first, 1 of 1)

- [AutoStyle-TTS: Retrieval-Augmented Generation based Automatic Style Matching Text-to-Speech Synthesis](https://mlsanity.com/paper/2504.10309/) (2025)

## Abstract (arXiv)

Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models heavily rely on prompt design to guide the generation process. However, existing prompt selection methods often fail to ensure that prompts contain sufficiently stable speaker identity cues and appropriate emotional intensity indicators, which are crucial for expressive speech synthesis. To address this challenge, we propose a two-stage prompt selection strategy specifically designed for expressive speech synthesis. In the static stage (before synthesis), we first evaluate prompt candidates using pitch-based prosodic features, perceptual audio quality, and text-emotion coherence scores evaluated by an LLM. We further assess the candidates under a specific TTS model by measuring character error rate, speaker similarity, and emotional similarity between the synthesized and prompt speech. In the dynamic stage (during synthesis), we use a textual similarity model to select the prompt that is most aligned with the current input text. Experimental results demonstrate that our strategy effectively selects prompt to synthesize speech with both high-intensity emotional expression and robust speaker identity, leading to more expressive and stable zero-shot TTS performance. Audio samples and codes will be available at https://whyrrrrun.github.io/ExpPro.github.io/.