# EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech

arXiv: https://arxiv.org/abs/2307.00024 · HTML: https://mlsanity.com/paper/2307.00024/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 28 Jun 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [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)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality](https://mlsanity.com/paper/2205.04421/) (2022)
- [Emotional Voice Conversion: Theory, Databases and ESD](https://mlsanity.com/paper/2105.14762/) (2021)
- [PromptTTS: Controllable Text-to-Speech with Text Descriptions](https://mlsanity.com/paper/2211.12171/) (2022)
- [AdaSpeech: Adaptive Text to Speech for Custom Voice](https://mlsanity.com/paper/2103.00993/) (2021)
- [InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt](https://mlsanity.com/paper/2301.13662/) (2023)
- [AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarios](https://mlsanity.com/paper/2204.00436/) (2022)
- [EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance](https://mlsanity.com/paper/2211.09496/) (2022)
- [Deep Learning Based Assessment of Synthetic Speech Naturalness](https://mlsanity.com/paper/2104.11673/) (2021)
- [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)
- [Emotional speech synthesis with rich and granularized control](https://mlsanity.com/paper/1911.01635/) (2019)
- [VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network](https://mlsanity.com/paper/2007.15256/) (2020)
- [Emotion controllable speech synthesis using emotion-unlabeled dataset with the assistance of cross-domain speech emotion recognition](https://mlsanity.com/paper/2010.13350/) (2020)
- [GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis](https://mlsanity.com/paper/2106.15153/) (2021)

## Built on by (most cited first, 15 of 15)

- [EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting](https://mlsanity.com/paper/2504.12867/) (2025)
- [A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications](https://mlsanity.com/paper/2410.15595/) (2024)
- [Controlling Emotion in Text-to-Speech with Natural Language Prompts](https://mlsanity.com/paper/2406.06406/) (2024)
- [A Review of Human Emotion Synthesis Based on Generative Technology](https://mlsanity.com/paper/2412.07116/) (2024)
- [UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts](https://mlsanity.com/paper/2404.18398/) (2024)
- [Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions](https://mlsanity.com/paper/2506.02742/) (2025)
- [Marco-Voice Technical Report](https://mlsanity.com/paper/2508.02038/) (2025)
- [Beyond Global Emotion: Fine-Grained Emotional Speech Synthesis with Dynamic Word-Level Modulation](https://mlsanity.com/paper/2509.20378/) (2025)
- [Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis](https://mlsanity.com/paper/2512.18699/) (2025)
- [MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers](https://mlsanity.com/paper/2505.13082/) (2025)
- [Emotion-Aligned Generation in Diffusion Text to Speech Models via Preference-Guided Optimization](https://mlsanity.com/paper/2509.25416/) (2025)
- [RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis](https://mlsanity.com/paper/2510.14628/) (2025)
- [AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech](https://mlsanity.com/paper/2605.17583/) (2026)
- [Causal Prosody Mediation for Text-to-Speech:Counterfactual Training of Duration, Pitch, and Energy in FastSpeech2](https://mlsanity.com/paper/2603.11683/) (2026)
- [Iterative Self-Learning for Expressive Text-to-Speech Synthesis](https://mlsanity.com/paper/2608.15910/) (2026)

## Abstract (arXiv)

State-of-the-art speech synthesis models try to get as close as possible to the human voice. Hence, modelling emotions is an essential part of Text-To-Speech (TTS) research. In our work, we selected FastSpeech2 as the starting point and proposed a series of modifications for synthesizing emotional speech. According to automatic and human evaluation, our model, EmoSpeech, surpasses existing models regarding both MOS score and emotion recognition accuracy in generated speech. We provided a detailed ablation study for every extension to FastSpeech2 architecture that forms EmoSpeech. The uneven distribution of emotions in the text is crucial for better, synthesized speech and intonation perception. Our model includes a conditioning mechanism that effectively handles this issue by allowing emotions to contribute to each phone with varying intensity levels. The human assessment indicates that proposed modifications generate audio with higher MOS and emotional expressiveness.