Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2309.15649 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916105657778176 |
|---|---|
| author | Yang, Chao-Han Huck Gu, Yile Liu, Yi-Chieh Ghosh, Shalini Bulyko, Ivan Stolcke, Andreas |
| author_facet | Yang, Chao-Han Huck Gu, Yile Liu, Yi-Chieh Ghosh, Shalini Bulyko, Ivan Stolcke, Andreas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_15649 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting Yang, Chao-Han Huck Gu, Yile Liu, Yi-Chieh Ghosh, Shalini Bulyko, Ivan Stolcke, Andreas Computation and Language Artificial Intelligence Machine Learning Sound Audio and Speech Processing 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. |
| title | Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting |
| topic | Computation and Language Artificial Intelligence Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2309.15649 |