arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.22692eess.AScs.AIcs.CLcs.LG
收藏

提升航空通信转录:使用LoRA微调Distil-Whisper

Enhancing Aviation Communication Transcription: Fine-Tuning Distil-Whisper with LoRA

California State Polytechnic University, Pomona(加州州立理工大学波莫纳分校);Edwards Air Force Base Test Center(爱德华兹空军基地测试中心);Skyryse

Shokoufeh Mirzaei, Jesse Arzate, Yukti Vijay

AI总结:

本文使用LoRA参数高效微调方法对distil-Whisper进行微调,利用空中交通管制语料库,将航空通信转录的词错误率降至3.86%,展示了其在驾驶舱应用中的潜力。

摘要:

航空通信的转录具有多种应用,从协助空中交通管制员识别复诵错误的准确性到搜索与救援行动。人工智能的最新进展为改进航空通信转录任务提供了前所未有的机遇。OpenAI的Whisper是领先的自动语音识别模型之一。然而,针对航空通信转录对Whisper进行微调在计算上并不高效。因此,本文旨在使用一种名为低秩适配(Low-Rank Adaptation)的参数高效微调方法,对Whisper的一个计算效率更高的版本——distil-Whisper进行微调。为了进行微调,我们使用了来自语言数据联盟的空中交通管制语料库数据集,该数据集包含美国三个主要机场附近约70小时的管制员和飞行员通话。目标是降低词错误率以提高航空通信转录的准确性。首先,从LoRA的初始超参数集(Alpha = 64,Rank = 32)开始,我们进行了网格搜索。我们应用了5折交叉验证来寻找distil-Whisper超参数的最佳组合。然后,我们对LoRA超参数进行了模型微调,在五折中实现了令人印象深刻的平均词错误率3.86%。这一结果凸显了该模型在驾驶舱中应用的潜力。

英文摘要:

Transcription of aviation communications has several applications, from assisting air traffic controllers in identifying the accuracy of read-back errors to search and rescue operations. Recent advances in artificial intelligence have provided unprecedented opportunities for improving aviation communication transcription tasks. OpenAI's Whisper is one of the leading automatic speech recognition models. However, fine-tuning Whisper for aviation communication transcription is not computationally efficient. Thus, this paper aims to use a Parameter-Efficient Fine-tuning method called Low-Rank Adaptation to fine-tune a more computationally efficient version of Whisper, distil-Whisper. To perform the fine-tuning, we used the Air Traffic Control Corpus dataset from the Linguistic Data Consortium, which contains approximately 70 hours of controller and pilot transmissions near three major airports in the US. The objective was to reduce the word error rate to enhance accuracy in the transcription of aviation communication. First, starting with an initial set of hyperparameters for LoRA (Alpha = 64 and Rank = 32), we performed a grid search. We applied a 5-fold cross-validation to find the best combination of distil-Whisper hyperparameters. Then, we fine-tuned the model for LoRA hyperparameters, achieving an impressive average word error rate of 3.86% across five folds. This result highlights the model's potential for use in the cockpit.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑