Pith. sign in

REVIEW 14 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.02407 v3 pith:PIPADSK6 submitted 2025-04-03 cs.SD eess.AS

classification cs.SDeess.AS
keywords flow-matchingrelativef5r-ttsgrouplearningoptimizationpolicyreinforcement
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling

    eess.AS 2026-06 unverdicted novelty 8.0 of 10

    WavTTS is the first raw-waveform diffusion TTS model using DiT flow matching and multi-scale mel supervision that approaches SOTA latent zero-shot performance while beating prior end-to-end models.

  2. Flow-GRPO: Training Flow Matching Models via Online RL

    cs.CV 2025-05 unverdicted novelty 8.0 of 10

    Flow-GRPO is the first online RL method for flow matching models, raising GenEval accuracy from 63% to 95% and text-rendering accuracy from 59% to 92% with little reward hacking.

  3. Reinforcement Learning for Flow-Matching Policies with Density Transport

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    RLDT fine-tunes pretrained flow-matching policies for continuous control by aligning them to a max-entropy RL transport field constructed via SVGD, using expected-target estimation for stable multi-step updates.

  4. FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech

    eess.AS 2026-06 conditional novelty 6.0 of 10

    FlowTTS-GRPO fine-tunes open-source flow-matching TTS models with multi-objective online RL via ODE-to-SDE conversion, improving speaker similarity and quality on CosyVoice 3.0 and F5-TTS.

  5. GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech

    cs.SD 2026-06 unverdicted novelty 6.0 of 10

    GLASS enables composable acoustic style control in zero-shot TTS by training independent GRPO-optimized LoRA adapters on style rewards that can be linearly combined.

  6. DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis

    eess.AS 2025-07 conditional novelty 6.0 of 10

    Reinforcement learning on duration prediction improves intelligibility and speaker similarity in a 4-step distilled text-to-speech model, and teacher-guided sampling recovers prosodic diversity.

  7. CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training

    cs.SD 2025-05 unverdicted novelty 6.0 of 10

    CosyVoice 3 achieves better content consistency, speaker similarity, and prosody naturalness in zero-shot multilingual speech synthesis by scaling data to one million hours, model size to 1.5 billion parameters, and i...

  8. Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm

    eess.AS 2026-07 conditional novelty 5.0 of 10

    Qwen-Audio-3.0-TTS claims state-of-the-art controllable multilingual text-to-speech across 16 languages and 20 Chinese dialects, using a 12.5 Hz tokenizer and multi-stage RL.

  9. FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech

    eess.AS 2026-06 unverdicted novelty 5.0 of 10

    FlowTTS-GRPO applies online RL with weighted multi-objective rewards to flow-matching TTS models via ODE-to-SDE conversion, reporting gains in speaker similarity and perceptual quality on CosyVoice 3.0 and F5-TTS.

  10. End-to-End Training for Discrete Token LLM based TTS System

    cs.SD 2026-06 unverdicted novelty 5.0 of 10

    An end-to-end optimization framework jointly trains the speech tokenizer, LLM, FM model, and reward model for discrete-token TTS, reporting new SOTA WER of 0.78% and 1.56% on Seed-TTS-Eval with 0.6B LLM and 0.5B FM.

  11. TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization

    cs.CV 2026-03 unverdicted novelty 5.0 of 10

    TIGFlow-GRPO uses a Trajectory-Interaction-Graph in conditional flow matching plus Flow-GRPO optimization to produce more accurate, socially compliant, and physically feasible trajectory forecasts on ETH/UCY and SDD datasets.

  12. Group Relative Policy Optimization for Speech Recognition

    eess.AS 2025-09 conditional novelty 5.0 of 10

    Applying GRPO with rule-based rewards to LLM-based ASR improves WER by up to 18.4% relative and reduces hallucination errors on unseen acoustic conditions.

  13. Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance

    cs.LG 2025-08 conditional novelty 4.0 of 10

    Blending a base diffusion model with its RL-finetuned version at sampling time lets users dial alignment strength, with the blend weight corresponding to the KL-regularization coefficient beta/w.

  14. From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning

    eess.AS 2026-07 unverdicted novelty 3.0 of 10

    A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.

Pith tools