ID 原文 译文
57468 为了优化组合特征在异常声音识别中的效率，提出一种用集合经验模态分解( EEMD) 对异常声音帧信号进行有效性检测和提取多层特征的算法. In order to optimize the efficiency of combined features in abnormal sound recognition，an algo- rithm for detecting the effectiveness of abnormal sound frame signals and extracting multi-layer features using ensemble empirical mode decomposition ( EEMD) is proposed.
57469 首先对异常声音帧信号进行集合经验模态分解，得到固有模态函数;然后根据给定的固有模态函数层数阈值，对该帧信号进行有效性检测; Firstly，an ensemble empirical mode decomposition is performed on the abnormal sound frame signal to obtain the intrinsic model function，and then the validity of the frame signal is tested according to the given layer threshold of the intrinsic modal function.
57470 再对有效帧信号的每一层固有模态函数提取梅尔频率倒谱系数、翻转梅尔频率倒谱系数、线性预测倒谱系数、短时能量和能量比，并将它们归一化后拼接成多层特征. Finally，the Mel frequency cepstral coefficients，the inverted Mel frequency cepstral coefficients， the linear prediction cepstral coefficients，the short-time energy and energy ratio are extracted for each lay- er of the intrinsic modal function of the effective frame signal，and then all of them are normalized and spliced into multi-layer feature.
57471 根据提取的特征，用深度卷积神经网络实现异常声音识别分类. According to the extracted features，the deep convolutional neural network is used to realize the classification and recognition of abnormal sound.
57472 仿真结果表明，提出的新方法在 4 类异常声音识别中的识别率可以达到 98.65% . Simulations show that the proposed new method can achieve a recognition rate of 98. 65% in four types of abnormal sound recognition.
57473 为了利用商品文本标题实现商品自动分类，提出一种基于高层特征融合的商品分类模型. In order to realize automatic classification of commodities by leveraging text titles of commodi- ties，a commodity classification model high-level feature fusion ( HFF) based on high-level feature fusion is proposed.
57474 首先，提出基于字嵌入和词嵌入的文本底层特征表示法，进而获得更强的商品标题结构特征表达; Firstly，a char embedding and word embedding based low-level feature representation meth- od for the text title is proposed. Then a stronger feature expression of the commodity title structure can be obtained.
57475 其次，提出了联合自注意力、卷积神经网络和通道注意力的机制，对文本标题的底层特征进行增强并获得高层增强特征; Secondly，a joint self-attention mechanism，convolutional neural network，and channel atten- tion are proposed to enhance the low-level features and obtain high-level enhancement features of the text title.
57476 最后，通过将文本的字嵌入和词嵌入的高层增强特征进行融合，最终获得商品文本标题的综合特征，并实现商品自动分类. Finally，by fusing the high-level enhancement features of the word embedding and the char embed- ding of the text，a comprehensive feature of the text title of the commodity is finally obtained and used for the commodity classification.
57477 以商品标题语料作为数据集进行了实验，实验结果表明，该模型对三级商品类别的分类精度能够达到 84. Experiments are conduct on the dataset of the commodity titles. The experi- ments show that the classification accuracy of HFF for the third-level commodity can reach 84.