arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.03998eess.AScs.LGcs.SD
收藏

单通道时域增强网络提高抗噪自动语音识别性能

Improving noise robust automatic speech recognition with single-channel time-domain enhancement network

NTT Communication Science Laboratories, NTT Corporation(日本电信电话株式会社NTT通信科学实验室)

Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani

摘要:

随着深度学习的出现,抗噪自动语音识别(ASR)的研究进展迅速。然而,在单通道系统的噪声条件下的ASR性能仍然不能令人满意。事实上,大多数单通道语音增强(SE)方法(去噪)与在多条件训练数据上训练的最先进的ASR后端相比仅带来有限的性能增益。最近,已经有很多研究基于神经网络的SE方法在时域工作,表现出前所未有的性能水平。然而,它还没有确定是否可以将这种时域方法实现的高增强性能转化为ASR。在本文中,我们证明了单通道时域去噪方法可以显着提高ASR性能,在CHiME-4数据集的单通道跟踪的真实评估数据上,通过强大的ASR后端提供超过30%的相对字错误减少。这些积极的结果表明,单通道降噪仍然可以提高ASR性能,这应该为该方向的更多研究打开大门。

英文摘要:

With the advent of deep learning, research on noise-robust automatic speech recognition (ASR) has progressed rapidly. However, ASR performance in noisy conditions of single-channel systems remains unsatisfactory. Indeed, most single-channel speech enhancement (SE) methods (denoising) have brought only limited performance gains over state-of-the-art ASR back-end trained on multi-condition training data. Recently, there has been much research on neural network-based SE methods working in the time-domain showing levels of performance never attained before. However, it has not been established whether the high enhancement performance achieved by such time-domain approaches could be translated into ASR. In this paper, we show that a single-channel time-domain denoising approach can significantly improve ASR performance, providing more than 30 % relative word error reduction over a strong ASR back-end on the real evaluation data of the single-channel track of the CHiME-4 dataset. These positive results demonstrate that single-channel noise reduction can still improve ASR performance, which should open the door to more research in that direction.

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。

↑