arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06237eess.AScs.LGcs.SD
收藏

鲁棒语音识别的端到端模型研究

An Investigation of End-to-End Models for Robust Speech Recognition

Indian Institute of Technology Bombay(印度理工学院孟买分校)

Archiki Prasad, Preethi Jyothi, Rajbabu Velmurugan

摘要:

用于鲁棒的自动语音识别(ASR)的端到端模型在先前的工作中还没有被充分地探索。对于端到端模型,可以选择使用语音增强技术来预处理输入语音,并使用增强的语音来训练模型。另一种选择是将噪声语音作为输入传递,并修改模型架构以适应噪声语音。以前还没有尝试过对这两种方法进行系统的端到端鲁棒ASR比较。我们解决了这一差距,并提出了一个详细的比较语音增强为基础的技术和三种不同的基于模型的适应技术,包括数据增强,多任务学习和对抗性学习的强大的ASR。虽然对抗性学习是对某些噪声类型性能最好的技术,但它的代价是降低了干净语音的WER。在其他相对平稳的噪声类型,一种新的语音增强技术优于所有基于模型的自适应技术。这表明,知识的基础噪声类型可以有意义地通知适应技术的选择。

英文摘要:

End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train the model using enhanced speech. Another alternative is to pass the noisy speech as input and modify the model architecture to adapt to noisy speech. A systematic comparison of these two approaches for end-to-end robust ASR has not been attempted before. We address this gap and present a detailed comparison of speech enhancement-based techniques and three different model-based adaptation techniques covering data augmentation, multi-task learning, and adversarial learning for robust ASR. While adversarial learning is the best-performing technique on certain noise types, it comes at the cost of degrading clean speech WER. On other relatively stationary noise types, a new speech enhancement technique outperformed all the model-based adaptation techniques. This suggests that knowledge of the underlying noise type can meaningfully inform the choice of adaptation technique.

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。

↑