当前位置: X-MOL 学术IEEE Open J. Intell. Transp. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
VHF Speech Enhancement Based on Transformer
IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2022-01-31 , DOI: 10.1109/ojits.2022.3147816
Xue Han 1 , Mingyang Pan 1 , Zhengzhong Li 1 , Haipeng Ge 1 , Zongying Liu 1
Affiliation  

To solve the poor quality of Very high frequency (VHF) speech communication in the navigation field, a VHF speech enhancement model based on an improved transformer (VHFSE) is proposed in this paper. The long-term and short-term noise are the reasons for the poor quality of VHF voice communication. VHFSE can reduce these two aspects of noise. We select the Two-stage Transformer based Neural Network (TSTNN) as the baseline. The Transformer structure pays attention to global information and parallel computing, which can reduce the long-term noise. In order to strengthen the ability of the model to reduce short-term noise, we add CNN module to the transformer according to the ability of revolutionary neural networks (CNN) to extract local information. Meanwhile, to improve the real-time performance, this study employs the lightweight convolution module (Depthwise Separable Convolution) to efficiency of VHF speech communication. Experimental results show that the proposed model VHFSE obtains the highest PESQ and STOI values than other compared modules. Besides, we apply the self-built dataset in our proposed model. The spectrum diagram shows that our model has the best enhancement effect on navigation VHF speech.

中文翻译:

基于 Transformer 的 VHF 语音增强

针对导航领域甚高频(VHF)语音通信质量较差的问题,提出一种基于改进变压器(VHFSE)的甚高频语音增强模型。长期和短期的噪声是VHF语音通信质量差的原因。VHFSE 可以降低这两个方面的噪声。我们选择基于两阶段变压器的神经网络(TSTNN)作为基线。Transformer结构注重全局信息和并行计算,可以降低长期噪声。为了加强模型降低短期噪声的能力,我们根据革命性神经网络(CNN)提取局部信息的能力,在 Transformer 中加入了 CNN 模块。同时,为了提高实时性,本研究采用轻量级卷积模块(Depthwise Separable Convolution)来提高 VHF 语音通信的效率。实验结果表明,与其他比较模块相比,所提出的模型 VHFSE 获得了最高的 PESQ 和 STOI 值。此外,我们在我们提出的模型中应用了自建数据集。频谱图表明,我们的模型对导航 VHF 语音的增强效果最好。
更新日期:2022-01-31
down
wechat
bug