CONF Kumar_SLT2026_2026/IDIAP When Synthetic Speech Is All You Have: Better Call GRPO Kumar, Shashi Labrak, Yanis Watawana, Hasindri Sankalpana Burdisso, Sergio Villatoro-Tello, Esaú Hacioğlu, Kadri Motlicek, Petr Stolcke, Andreas EXTERNAL http://publications.idiap.ch/attachments/papers/2026/Kumar_SLT2026_2026.pdf PUBLIC IEEE Spoken Language Technology 2026 2026 https://arxiv.org/abs/2607.08409 URL 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%→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.