ID 原文 译文
39166 论文侧重于方法原理、机理和架构方面的探讨，具体的算法实现细节感兴趣的读者可以参考相应的文献。 We discuss the basic principles underlying those beamformers and their pros and cons. Due to space limit, however, we will not present much detail on the derivation of every individual algorithm. The interested reader is therefore encouraged to follow the respective references listed in the paper.
39167 脑机接口作为患有交流或肢体障碍的病人与机器设备交流沟通的一种技术，近年来在生物医学工程、康复工程等领域受到广泛关注。 As a system to communicate between patients with communication disorders or physically disabilities and machines, brain-computer interface technologies have received widespread attentions in recent years.
39168 基于发音想象的脑机接口作为一种新型的脑机接口方式，由于其具有为患有言语障碍的病人提供有效、舒适的言语交流的潜力，其相关研究正在迅速发展。 Meanwhile, as a new type of brain-computer interface, brain-computer interface for speech imagery develops rapidly because of its potential to offer an effective and comfortable communication tool to patients suffering communication disorders.
39169 本文首先介绍常见的基于发音想象的脑机接口所用到的信号采集技术，然后详述现有文献中的相关研究内容和信号处理算法， This review paper first introduces common signal acquisition technologies used in existing brain-computer interfaces for speech imagery, and presents in details the signal processing algorithms in speech-imagery-targeted brain-computer interface studies.
39170 最后讨论基于发音想象的脑机接口存在的问题以及对未来工作进行展望。 Finally, some practical considerations and discussions are provided on the existing research problems and future developments of brain-computer interface technologies for speech imagery.
39171 基于非负矩阵分解(Nonnegative matrix factorization， NMF)的语音增强算法需要和背景噪声类型匹配的噪声基矩阵(Basis matrix)，而在实际中，这是很难被保证的。 In nonnegative matrix factorization(NMF)-based speech enhancement, the matched noise basis matrix needs to be trained, which is difficult to be guaranteed in practice.
39172 本文提出了一种基于噪声基矩阵在线更新的非负矩阵分解语音增强方法， In this paper, an NMF-based speech enhancement method is proposed in which the noise basis matrix is updated online.
39173 该方法首先利用一个无语音帧判决模块识别出带噪语音的无语音区域，然后利用一个固定长度的滑动窗口(Sliding window)来包含若干帧最近过去的带噪语音的无语音帧，并用这些无语音帧的幅度谱在线更新噪声基矩阵，最后利用更新得到的噪声基矩阵和预先训练的语音基矩阵实现语音增强。 First, the non-speech regions of noisy signal are determined by utilizing a decision module of non-speech frame. Then, a fixed-length sliding window is used to cover several recent past frames of noisy speech determined as non-speech, and the magnitude spectrums of these non-speech frames are used to update the noise basis matrix online.
39174 该方法能够在线更新出匹配的噪声基矩阵，有效地解决了噪声基矩阵不匹配的问题。 After that, the updated noise basis matrix and the pre-trained speech basis matrix are used to achieve speech enhancement.
39175 实验证明，本文所提的方法在线学习到的噪声基矩阵在大多数条件下比匹配训练集下训练得到的噪声基矩阵的性能还要优越。 This method can obtain the matched noise basis matrix online and effectively solve the problem of the mismatch of the noise basis matrix. The test results demonstrate that the noise basis matrix trained online by the proposed method performs better than that trained from the matched dataset in most conditions.