On synthetic banking speech alone, GRPO cuts ASR WER 40% relative to SFT (36.71%→22.09%) by improving stopping calibration and attention anchoring to audio.
The state of TTS: A case study with human fooling rates,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Synthetic Speech Is All You Have: Better Call GRPO
On synthetic banking speech alone, GRPO cuts ASR WER 40% relative to SFT (36.71%→22.09%) by improving stopping calibration and attention anchoring to audio.