{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generative-speech-recognition-error","title":"Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting","arxiv_id":"2309.15649","date":"2023-09-27","proceeding":null,"authors":["Chao-Han Huck Yang","Yile Gu","Yi-Chieh Liu","Shalini Ghosh","Ivan Bulyko","Andreas Stolcke"],"abstract":"We explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction. Our first focus is on instruction prompting to let LLMs perform these task without fine-tuning, for which we evaluate different prompting schemes, both zero- and few-shot in-context learning, and a novel task activation prompting method that combines causal instructions and demonstration to increase its context windows. Next, we show that rescoring only by in-context learning with frozen LLMs achieves results that are competitive with rescoring by domain-tuned LMs, using a pretrained first-pass recognition system and rescoring output on two out-of-domain tasks (ATIS and WSJ). By combining prompting techniques with fine-tuning we achieve error rates below the N-best oracle level, showcasing the generalization power of the LLMs.","url_abs":"https://arxiv.org/abs/2309.15649v2","url_pdf":"https://arxiv.org/pdf/2309.15649v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-wsj-eval92","task":"Speech Recognition","dataset":"WSJ eval92","model":"Task activating prompting generative correction","rank_in_archive_order":3,"of":17,"metrics":{"Word Error Rate (WER)":"2.11"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.15649","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}