mlsanityData to 7 Oct 2026

F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization

arXiv 2504.02407 ↗First posted 3 Apr 2025cs.SD eess.AScited by 24

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

We present F5R-TTS, a novel text-to-speech (TTS) system that integrates Group Relative Policy Optimization (GRPO) into a flow-matching based architecture. By reformulating the deterministic outputs of flow-matching TTS into probabilistic Gaussian distributions, our approach enables seamless integration of reinforcement learning algorithms. During pretraining, we train a probabilistically reformulated flow-matching based model which is derived from F5-TTS with an open-source dataset. In the subsequent reinforcement learning (RL) phase, we employ a GRPO-driven enhancement stage that leverages dual reward metrics: word error rate (WER) computed via automatic speech recognition and speaker similarity (SIM) assessed by verification models. Experimental results on zero-shot voice cloning demonstrate that F5R-TTS achieves significant improvements in both speech intelligibility (a 29.5% relative reduction in WER) and speaker similarity (a 4.6% relative increase in SIM score) compared to conventional flow-matching based TTS systems. Audio samples are available at https://frontierlabs.github.io/F5R.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 23 of its 27 references that are in the map. First posted on arXiv 3 Apr 2025.

Builds on

23 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching9 Oct

Other references · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  6. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  7. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  8. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  9. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 293
  10. 2023Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modelingcited by 166
  11. 2024E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTScited by 149
  12. 2024Nemotron-4 340B Technical Reportcited by 143
10 more
  1. 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 119
  2. 2024FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMscited by 118
  3. 2022Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkitcited by 92
  4. 2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 92
  5. 2024BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of datacited by 74
  6. 2021Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verificationcited by 71
  7. 2024WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmarkcited by 39
  8. 2024Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimizationcited by 31
  9. 2025Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidancecited by 26
  10. 2024Preference Alignment Improves Language Model-Based TTScited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 13.

24 papers.

Sort:

By area:

  1. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
  2. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 142
  3. 2025DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesiscited by 7
  4. 2025Multi-Metric Preference Alignment for Generative Speech Restorationcited by 7
  5. 2025Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidancecited by 7
  6. 2025Step-Audio-EditX Technical Reportcited by 6
  7. 2025YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidancecited by 5
  8. 2026FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learningcited by 5
  9. 2025No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTScited by 3
  10. 2026LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Spacecited by 3
  11. 2026FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speechcited by 3
  12. 2025Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesiscited by 2
12 more
  1. 2025YingMusic-SVC: Real-World Robust Zero-Shot Singing Voice Conversion with Flow-GRPO and Singing-Specific Inductive Biasescited by 2
  2. 2025Vox-Evaluator: Enhancing Stability and Fidelity for Zero-shot TTS with A Multi-Level Evaluatorcited by 1
  3. 2026WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modelingcited by 1
  4. 2026GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speechcited by 1
  5. 2026GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech modelcited by 1
  6. 2026Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generationcited by 0
  7. 2026TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimizationcited by 0
  8. 2026Reinforcement Learning for Flow-Matching Policies with Density Transportcited by 0
  9. 2026End-to-End Training for Discrete Token LLM based TTS Systemcited by 0
  10. 2026Imitation Learning for Elder-Facing Speech Synthesiscited by 0
  11. 2026Sequential Trajectories and Simultaneous Blending: Multi-Emotion Modeling for Instruction-Following TTScited by 0
  12. 2026Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speechcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Explore the Reinforcement Learning for the LLM based ASR and TTS system
  2. 2025Multi-Reward GRPO for Stable and Prosodic Single-Codebook TTS LLMs at Scale
  3. 2025Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization
  4. 2026VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation
  5. 2025GLM-TTS Technical Report
  6. 2026Resonate: Reinforcing Text-to-Audio Generation via Online Feedback from Large Audio Language Models ↗
  7. 2025Towards Flow-Matching-based TTS without Classifier-Free Guidance
  8. 2026When Synthetic Speech Is All You Have: Better Call GRPO