Dilek Hakkani-Tür

LLMs can guide phoneme editing to create synthetic accented speech from just a handful of examples, substantially improving ASR accuracy where training data is scarce.

Current depression patient simulators are more like Pollyannas than patients, resolving negative emotions too quickly and following a predictable trajectory from negative to positive.

Forget prompt engineering and fine-tuning: this "Reasoning Inception" method injects targeted reasoning into LLM agents at test time to fix conversational errors on the fly.