# Expressive Text-to-Speech using Style Tag

arXiv: https://arxiv.org/abs/2104.00436 · HTML: https://mlsanity.com/paper/2104.00436/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2021.

## Built on by (most cited first, 20 of 20)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance](https://mlsanity.com/paper/2211.09496/) (2022)
- [Textless Speech Emotion Conversion using Discrete and Decomposed Representations](https://mlsanity.com/paper/2111.07402/) (2021)
- [VoiceLDM: Text-to-Speech with Environmental Context](https://mlsanity.com/paper/2309.13664/) (2023)
- [Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2412.06602/) (2024)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems](https://mlsanity.com/paper/2506.16381/) (2025)
- [Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus](https://mlsanity.com/paper/2203.15447/) (2022)
- [Self-supervised Context-aware Style Representation for Expressive Speech Synthesis](https://mlsanity.com/paper/2206.12559/) (2022)
- [Controlling Emotion in Text-to-Speech with Natural Language Prompts](https://mlsanity.com/paper/2406.06406/) (2024)
- [ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation](https://mlsanity.com/paper/2305.18028/) (2023)
- [Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS](https://mlsanity.com/paper/2207.06000/) (2022)
- [DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability](https://mlsanity.com/paper/2406.19135/) (2024)
- [ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2601.03632/) (2026)
- [Exploring speech style spaces with language models: Emotional TTS without emotion labels](https://mlsanity.com/paper/2405.11413/) (2024)
- [Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions](https://mlsanity.com/paper/2506.02742/) (2025)
- [Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech](https://mlsanity.com/paper/2606.01479/) (2026)
- [HiStyle: Hierarchical Style Embedding Predictor for Text-Prompt-Guided Controllable Speech Synthesis](https://mlsanity.com/paper/2509.25842/) (2025)
- [Expressive TTS Driven by Natural Language Prompts Using Few Human Annotations](https://mlsanity.com/paper/2311.01260/) (2023)
- [PRESENT: Zero-Shot Text-to-Prosody Control](https://mlsanity.com/paper/2408.06827/) (2024)

## Abstract (arXiv)

As recent text-to-speech (TTS) systems have been rapidly improved in speech quality and generation speed, many researchers now focus on a more challenging issue: expressive TTS. To control speaking styles, existing expressive TTS models use categorical style index or reference speech as style input. In this work, we propose StyleTagging-TTS (ST-TTS), a novel expressive TTS model that utilizes a style tag written in natural language. Using a style-tagged TTS dataset and a pre-trained language model, we modeled the relationship between linguistic embedding and speaking style domain, which enables our model to work even with style tags unseen during training. As style tag is written in natural language, it can control speaking style in a more intuitive, interpretable, and scalable way compared with style index or reference speech. In addition, in terms of model architecture, we propose an efficient non-autoregressive (NAR) TTS architecture with single-stage training. The experimental result shows that ST-TTS outperforms the existing expressive TTS model, Tacotron2-GST in speech quality and expressiveness.