ID 原文 译文
39286 同时，利用对抗机制，使生成模型和判别模型分别训练目标语音和干扰语音的特征，提高了语音分离的有效性。 At the same time, the generative model and discriminative model are used to train the features of the target speech and the interference speech respectively, which improves the effectiveness of speech separation.
39287 实验中，采用Aishell数据集进行对比测试。 In the experiment, a comparative test is performed on the Aishell data set.
39288 结果表明，本文所提方法在三种信噪比条件下都有良好的分离效果，能更好地恢复出目标语音中的高频频段信息。 The results show that the proposed method has a good separation effect under three SNR conditions, and can better recover the high frequency band information of the target speech.
39289 通过对复杂环境下声音识别技术进行研究，本文提出了美尔谱系数(MFSC)与卷积神经网络(CNN)相组合的环境声音识别方法。 Through research on sound recognition technology in complex environments, this paper proposes an environmental sound recognition method that combines the Merrill Spectrum Coefficient(MFSC) and Convolutional Neural Network(CNN).
39290 对声音事件提取其MFSC特征，将特征参数作为输入送入设计好的CNN模型中对声音事件进行分类。 The MFSC features of sound events are extracted, and the feature parameters are used as input to the designed CNN model to classify the sound events.
39291 实验数据集采用ESC-10，将构建的卷积神经网络模型与随机森林、支持向量机(SVM)、深度神经网络(DNN)及DCASE比赛中常用的三种识别模型进行对比实验。 The experimental data set uses ESC-10 to compare the constructed convolutional neural network model with three recognition models commonly used in random forest, support vector machine(SVM), deep neural network(DNN) and DCASE competitions.
39292 实验结果表明，在相同数据集下，本文所设计的美尔谱系数与卷积神经网络相组合的环境声音识别方法相较传统的声音识别方法在识别率上分别有13.1%，18.3%，15.7%的提升， The experimental results show that, under the same data set, the environmental sound recognition method combining the Meir spectral coefficients and the convolutional neural network designed in this paper has a recognition rate of 13.1%, 18.3%, and 15.7%, respectively, compared with the traditional sound recognition method.
39293 相较于DCASE比赛中的三种常用识别模型，本文所设计识别模型识别率及识别效率均有明显的优势。 Compared with the three commonly used recognition models in the DCASE competition, the recognition rate and recognition efficiency of the recognition model designed in this paper have obvious advantages.
39294 稳态视觉诱发电位(steady-state visual evoked potentials，SSVEP)的共振频率为诱发最大SSVEP响应对应的刺激频率，对其研究在临床神经科学和脑机接口技术领域均具有很好的应用前景。 The resonance frequency of steady-state visual evoked potential was the stimulation frequency corresponding to the maximum visual steady-state response, and the research of SSVEP had a good application prospect in clinical neuroscience and brain computer interface technology.
39295 刺激光源面积是影响SSVEP共振频率的一个要素，但目前对共振频率随光源面积变化规律知之甚少。 The area of stimulus light source was a factor affecting SSVEP resonance frequency, but little was known about the variation of resonance frequency with the area of light source.