{"slug": "when-synthetic-speech-is-all-you-have-better-call-grpo", "title": "When Synthetic Speech Is All You Have: Better Call GRPO", "summary": "Researchers at an undisclosed institution applied Group Relative Policy Optimization (GRPO) to adapt an LLM-based automatic speech recognition (ASR) system to synthetic speech, achieving a 40% relative word error rate (WER) reduction over supervised fine-tuning (SFT) and a 45% reduction with combined SFT and GRPO. The method improves stopping calibration and speech-to-text alignment without altering early-layer representations, offering a privacy-preserving alternative for regulated domains like banking.", "body_md": "arXiv:2607.08409v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/when-synthetic-speech-is-all-you-have-better-call-grpo", "canonical_source": "https://www.machinebrief.com/news/when-synthetic-speech-is-all-you-have-better-call-grpo-rdqw", "published_at": "2026-07-10 04:00:00+00:00", "updated_at": "2026-07-10 05:43:59.944661+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research"], "entities": ["GRPO", "Group Relative Policy Optimization", "LLM", "ASR", "SFT"], "alternates": {"html": "https://wpnews.pro/news/when-synthetic-speech-is-all-you-have-better-call-grpo", "markdown": "https://wpnews.pro/news/when-synthetic-speech-is-all-you-have-better-call-grpo.md", "text": "https://wpnews.pro/news/when-synthetic-speech-is-all-you-have-better-call-grpo.txt", "jsonld": "https://wpnews.pro/news/when-synthetic-speech-is-all-you-have-better-call-grpo.jsonld"}}