Speech Technology

This is an important paper actually, let me leave it for the future

https://arxiv.org/abs/2407.16370

Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction

Rithik Sachdev, Zhong-Qiu Wang, Chao-Han Huck Yang

Building upon the strength of modern large language models (LLMs), generative error correction (GEC) has emerged as a promising paradigm that can elevate the performance of modern automatic speech recognition (ASR) systems. One representative approach is to leverage in-context learning to prompt LLMs so that a better hypothesis can be generated by the LLMs based on a carefully-designed prompt and an N-best list of hypotheses produced by ASR systems. However, it is yet unknown whether the existing prompts are the most effective ones for the task of post-ASR error correction. In this context, this paper first explores alternative prompts to identify an initial set of effective prompts, and then proposes to employ an evolutionary prompt optimization algorithm to refine the initial prompts. Evaluations results on the CHiME-4 subset of the Task 1 of the SLT 2024 GenSEC challenge show the effectiveness and potential of the proposed algorithms.

arXiv.org

Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction

Building upon the strength of modern large language models (LLMs), generative error correction (GEC) has emerged as a promising paradigm that can elevate the performance of modern automatic speech...

www.tg-me.com/us/Speech Technology/com.speechtech/1962

1.7K viewsAug 22, 2024 at 15:06

This is an important paper actually, let me leave it for the future

https://arxiv.org/abs/2407.16370

Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction

Rithik Sachdev, Zhong-Qiu Wang, Chao-Han Huck Yang

Building upon the strength of modern large language models (LLMs), generative error correction (GEC) has emerged as a promising paradigm that can elevate the performance of modern automatic speech recognition (ASR) systems. One representative approach is to leverage in-context learning to prompt LLMs so that a better hypothesis can be generated by the LLMs based on a carefully-designed prompt and an N-best list of hypotheses produced by ASR systems. However, it is yet unknown whether the existing prompts are the most effective ones for the task of post-ASR error correction. In this context, this paper first explores alternative prompts to identify an initial set of effective prompts, and then proposes to employ an evolutionary prompt optimization algorithm to refine the initial prompts. Evaluations results on the CHiME-4 subset of the Task 1 of the SLT 2024 GenSEC challenge show the effectiveness and potential of the proposed algorithms.

BY Speech Technology