# Emotional speech synthesis and recognition

Area: [Speech and audio language models](https://mlsanity.com/speech/index.md). HTML: https://mlsanity.com/speech/emotional-speech-synthesis-and-recognition/

## Key facts

- Emotional speech synthesis and recognition: 259 papers on arXiv since 2021 (data through 19 Oct 2026).
- 30 of its 259 mapped papers (12%) cite “EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance” (2022, arXiv 2211.09496).
- 22 of its 259 mapped papers (8%) cite “MsEmoTTS: Multi-scale emotion transfer, prediction, and control for emotional speech synthesis” (2022, arXiv 2201.06460).
- 8 new papers 2 Oct–19 Oct.

## Most cited here

- [EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance](https://mlsanity.com/paper/2211.09496/) (2022), cited by 30 papers here
- [MsEmoTTS: Multi-scale emotion transfer, prediction, and control for emotional speech synthesis](https://mlsanity.com/paper/2201.06460/) (2022), cited by 22 papers here
- [Speech Synthesis with Mixed Emotions](https://mlsanity.com/paper/2208.05890/) (2022), cited by 19 papers here
- [EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting](https://mlsanity.com/paper/2504.12867/) (2025), cited by 18 papers here
- [Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2407.12229/) (2024), cited by 17 papers here
- [EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector](https://mlsanity.com/paper/2411.02625/) (2024), cited by 16 papers here
- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025), cited by 15 papers here
- [EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech](https://mlsanity.com/paper/2307.00024/) (2023), cited by 14 papers here
- [Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling](https://mlsanity.com/paper/2312.11947/) (2023), cited by 13 papers here
- [Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization](https://mlsanity.com/paper/2409.10157/) (2024), cited by 13 papers here

## New (2 Oct–19 Oct)

- [Speech LLMs That Breathe: Modeling Non-Verbal Vocalizations in Dialogue](https://mlsanity.com/paper/2610.25942/) (2026-10-19)
- [Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors](https://mlsanity.com/paper/2610.22832/) (2026-10-16)
- [E3-System: Expressive EmoData, Explicitly Controllable, Easy-to-Use TTS](https://mlsanity.com/paper/2610.12993/) (2026-10-09)
- [Steerspeech: Activation Steering For Emotion Control In Generated Speech](https://mlsanity.com/paper/2610.10415/) (2026-10-07)
- [Steering Follows Geometry, Not Labels: Emotion Directions in a Full-Duplex Speech Model](https://mlsanity.com/paper/2610.08887/) (2026-10-06)
- [Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters](https://mlsanity.com/paper/2610.05575/) (2026-10-04)
- [Tracing a Sparse Emotion-Control Circuit in LLM-Based Text-to-Speech](https://mlsanity.com/paper/2610.05080/) (2026-10-04)
- [EMODE: Dynamic Para-Semantic Experts for Emotion-Aware Speech Language Modeling](https://mlsanity.com/paper/2610.06956/) (2026-10-03)