# UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts

arXiv: https://arxiv.org/abs/2404.18398 · HTML: https://mlsanity.com/paper/2404.18398/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network](https://mlsanity.com/paper/1808.03314/) (2018)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset](https://mlsanity.com/paper/2010.14794/) (2020)
- [PromptTTS: Controllable Text-to-Speech with Text Descriptions](https://mlsanity.com/paper/2211.12171/) (2022)
- [InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt](https://mlsanity.com/paper/2301.13662/) (2023)
- [EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance](https://mlsanity.com/paper/2211.09496/) (2022)
- [Controllable Emotion Transfer For End-to-End Speech Synthesis](https://mlsanity.com/paper/2011.08679/) (2020)
- [iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform](https://mlsanity.com/paper/2203.02395/) (2022)
- [Emotional End-to-End Neural Speech Synthesizer](https://mlsanity.com/paper/1711.05447/) (2017)
- [EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model](https://mlsanity.com/paper/2106.09317/) (2021)
- [EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture](https://mlsanity.com/paper/2012.03500/) (2020)
- [iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre](https://mlsanity.com/paper/2206.14866/) (2022)
- [EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech](https://mlsanity.com/paper/2307.00024/) (2023)
- [MM-TTS: Multi-modal Prompt based Style Transfer for Expressive Text-to-Speech Synthesis](https://mlsanity.com/paper/2312.10687/) (2023)
- [Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech](https://mlsanity.com/paper/2110.04153/) (2021)
- [METTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer](https://mlsanity.com/paper/2307.15951/) (2023)

## Built on by (most cited first, 5 of 5)

- [Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning](https://mlsanity.com/paper/2406.11161/) (2024)
- [Beyond Global Emotion: Fine-Grained Emotional Speech Synthesis with Dynamic Word-Level Modulation](https://mlsanity.com/paper/2509.20378/) (2025)
- [UDDETTS: Unifying Discrete and Dimensional Emotions for Controllable Emotional Text-to-Speech](https://mlsanity.com/paper/2505.10599/) (2025)
- [When One Modality Sabotages the Others: A Diagnostic Lens on Multimodal Reasoning](https://mlsanity.com/paper/2511.02794/) (2025)
- [AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech](https://mlsanity.com/paper/2605.17583/) (2026)

## Abstract (arXiv)

Emotional Text-to-Speech (E-TTS) synthesis has garnered significant attention in recent years due to its potential to revolutionize human-computer interaction. However, current E-TTS approaches often struggle to capture the intricacies of human emotions, primarily relying on oversimplified emotional labels or single-modality input. In this paper, we introduce the Unified Multimodal Prompt-Induced Emotional Text-to-Speech System (UMETTS), a novel framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech. The core of UMETTS consists of two key components: the Emotion Prompt Alignment Module (EP-Align) and the Emotion Embedding-Induced TTS Module (EMI-TTS). (1) EP-Align employs contrastive learning to align emotional features across text, audio, and visual modalities, ensuring a coherent fusion of multimodal information. (2) Subsequently, EMI-TTS integrates the aligned emotional embeddings with state-of-the-art TTS models to synthesize speech that accurately reflects the intended emotions. Extensive evaluations show that UMETTS achieves significant improvements in emotion accuracy and speech naturalness, outperforming traditional E-TTS methods on both objective and subjective metrics.