Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses
cs.CL, cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Terminology
Sources
- ASR Error Correction using Large Language Models
- ProGRes: Prompted Generative Rescoring on ASR n-Best
- Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation
- LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context
- Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI
- Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition
- Chain of Correction for Full-text Speech Recognition with Large Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering