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 2409.14494cs.CLcs.LGcs.SDeess.AS
收藏

CPT增强的Wav2vec2.0:面向教室环境的抗噪语音识别

CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments

University of Maryland(马里兰大学);Stanford University(斯坦福大学)

Ahmed Adel Attia, Dorottya Demszky, Tolulope Ogunremi, Jing Liu, Carol Espy-Wilson

AI总结:

本文研究持续预训练(CPT)在将Wav2vec2.0适配到教室语音识别中的效果,证明CPT可将词错误率降低超过10%,并显著提升模型对不同噪声、麦克风和教室条件的鲁棒性。

摘要:

构建对教室环境具有鲁棒性和适应能力的自动语音识别(ASR)系统,对于开发辅助教师和学生的人工智能工具至关重要。本文研究了持续预训练(CPT)在将Wav2vec2.0适配到教室领域中的有效性。我们证明CPT在这一方面是一种强有力的工具,能够将基于Wav2vec2.0的模型的词错误率(WER)降低超过10%。更具体地说,CPT提高了模型对不同噪声、麦克风和教室条件的鲁棒性。

英文摘要:

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining (CPT) in adapting Wav2vec2.0 to the classroom domain. We show that CPT is a powerful tool in that regard and reduces the Word Error Rate (WER) of Wav2vec2.0-based models by upwards of 10%. More specifically, CPT improves the model's robustness to different noises, microphones and classroom conditions.

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。

↑