{"ID":6267184,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-13T01:02:08.706470581Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08409","arxiv_id":"2607.08409","title":"When Synthetic Speech Is All You Have: Better Call GRPO","abstract":"LLM-based ASR adapted to regulated domains such as banking is bottlenecked by privacy: real speech is costly and legally constrained to collect, making synthetic text-to-speech (TTS) an attractive substitute. Yet synthetic speech stays acoustically mismatched with real recordings, and work on this gap has stayed within supervised fine-tuning (SFT). We instead turn to reinforcement learning, and show that Group Relative Policy Optimization (GRPO) extracts far more from the same synthetic speech than SFT. Synthetic-only adaptation of the model with GRPO, a critic-free method rewarding low-WER hypotheses, reduces WER by 40\\% relative to SFT (36.71\\%$\\to$22.09\\%), and an SFT-then-GRPO combination pushes this further to 45\\%. We trace the gain to behavior rather than representation: GRPO reduces insertion errors by improving stopping calibration and speech-to-text alignment by better anchoring attention to audio, leaving early-layer representations intact. When synthetic speech is the main resource, reinforcement learning should be preferred over supervised fine-tuning.","short_abstract":"LLM-based ASR adapted to regulated domains such as banking is bottlenecked by privacy: real speech is costly and legally constrained to collect, making synthetic text-to-speech (TTS) an attractive substitute. Yet synthetic speech stays acoustically mismatched with real recordings, and work on this gap has stayed within...","url_abs":"https://arxiv.org/abs/2607.08409","url_pdf":"https://arxiv.org/pdf/2607.08409v1","authors":"[\"Shashi Kumar\",\"Yanis Labrak\",\"Hasindri Watawana\",\"Sergio Burdisso\",\"Esaú Villatoro-Tello\",\"Kadri Hacioğlu\",\"Petr Motlicek\",\"Andreas Stolcke\"]","published":"2026-07-09T12:34:56Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}