ID 原文 译文
39186 本文提出一种基于最大化该区域最小降噪量的优化设计方法，将水平面划分为不同子区域，每个子区域分别使用对应的优化初级声场传递函数进行噪声控制。 Accordingly, the horizontal plane is divided into several sub-regions, the optimized primary acoustic transfer function is used for noise control in each sub-region.
39187 该方法减小了区域内初级声场传递函数的变化范围，有效提高了区域内的最小降噪量。 The proposed method can reduce the variation of the primary acoustic transfer function in a certain region, and thus can increase the minimum noise reduction in this region effectively.
39188 实验结果验证了该噪声控制方法的有效性。 Experimental results show the validity of the proposed method for head-mounted active noise control system.
39189 语音增强的目的是从带有噪声的语音中分离出纯净语音，实现语音的质量和可懂度的提高。 The purpose of speech enhancement is to separate clean speech signal from speech mixed with additional noise, improve speech quality and speech intelligibility.
39190 近年来，采用有监督学习的深度神经网络已经成为了语音增强的主流方法。 In recent years, supervised deep learning neural networks have been a popular method of speech enhancement.
39191 卷积循环网络是一种新型的神经网络结构，包含编码层、中间层、解码层三个主要模块，其已经在语音增强任务中取得了较好的效果。 Convolutional recurrent neural network is a novel network structure including encoder, middle layer and decoder.
39192 时频注意力机制是一个由数个相连的卷积层通过跳跃连接构成的简单网络模块，在训练过程中可以计算语音幅度谱特征图的非邻域相关性，从而更加有利于网络关注到语音的谐波特性。 Time-frequency attention mechanism is a simple network module composed of several convolutional layers with skip connections. In training process, it can compute the non-local correlations of speech magnitude.
39193 本文将时频注意力机制引入卷积循环网络的编码层和解码层中，实验结果表明，在不同信噪比条件下，该方法相比基线卷积循环网络能够进一步提高语音质量和可懂度，且增强后的语音信号可以保留更多的语谱谐波信息，实现更低程度的语音失真。 In this paper, we applied T-F attention module into a convolutional neural network. The experimental results show in different signal-to-noise ratio conditions, the proposed method can further improve speech quality and intelligibility, and maintain more speech harmonic information, and achieve lower speech distortion.
39194 针对立体声音频采集设备逐渐普及的趋势，本文提出了一种保留立体声相位信息的声音场景分类算法。 With increasing devices supporting the recording of binaural audios, binaural audio processing methods become a field of possible exploration in acoustic scene classification(ASC).
39195 在预处理阶段，根据左右通道的相位信息对音频样本进行源环境提取，生成一种全新的四通道特征。 Therefore, we would like to investigate the primary ambient extraction(PAE), a binaural audio processing method which decomposes a binaural audio sample into four channels using the phase information.