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 1906.08415cs.SDcs.LGcs.MMeess.AS
收藏

一种鲁棒小足迹关键词识别的单声道语音增强方法

A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting

Inner Mongolia University(内蒙古大学);Harbin Institute of Technology(哈尔滨工业大学)

Yue Gu, Zhihao Du, Hui Zhang, Xueliang Zhang

摘要:

对噪声的鲁棒性对于现实环境中的关键字定位(KWS)至关重要。为了提高鲁棒性,涉及语音增强前端。在这项研究中,一个预先训练好的语音增强前端和一个基于卷积神经网络(CNN)的KWS系统连接起来,而不是把语音增强作为一个单独的预处理之前的KWS系统,其中一个特征变换块被用来将增强前端的输出转换成KWS系统的输入。整个模型是联合训练的,因此来自KWS系统的语言和其他有用的信息可以反向传播到增强前端,以提高其性能。为了适应小尺寸器件,提出了一种新的卷积递归网络,它需要较少的参数和计算量,并且不会降低性能。此外,通过将输入特征从功率谱图转换为Mel谱图,计算量更小,性能更好。我们的实验结果表明,所提出的方法显着提高KWS系统的噪声鲁棒性。

英文摘要:

Robustness against noise is critical for keyword spotting (KWS) in real-world environments. To improve the robustness, a speech enhancement front-end is involved. Instead of treating the speech enhancement as a separated preprocessing before the KWS system, in this study, a pre-trained speech enhancement front-end and a convolutional neural networks (CNNs) based KWS system are concatenated, where a feature transformation block is used to transform the output from the enhancement front-end into the KWS system's input. The whole model is trained jointly, thus the linguistic and other useful information from the KWS system can be back-propagated to the enhancement front-end to improve its performance. To fit the small-footprint device, a novel convolution recurrent network is proposed, which needs fewer parameters and computation and does not degrade performance. Furthermore, by changing the input features from the power spectrogram to Mel-spectrogram, less computation and better performance are obtained. our experimental results demonstrate that the proposed method significantly improves the KWS system with respect to noise robustness.

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。

↑