For the difficulty of separation between singing and accompaniment in the musical signals,an improved music separation method of based on discriminative training depth neural network(DNN) was proposed.Firstly,based on...For the difficulty of separation between singing and accompaniment in the musical signals,an improved music separation method of based on discriminative training depth neural network(DNN) was proposed.Firstly,based on the DNN model,considering the reconstruction errors and discrimination information between singing and accompaniment,an improved objective function was presented to discriminate the training;Then,an additional layer was added to DNN model,introducing the time-frequency masking to optimize the estimated accompaniment of the song,and the corresponding time-domain signal was obtained by inverse Fourier transform;Finally,the influence of different parameters on the separation performance was verified,and compared it with the existing music separation methods.The experimental results showed that the improved objective function and the introduction of time-frequency masking significantly improved the separation performance of the DNN,and the separation performance was improved about 4 dB compared with other existing music separation methods,thus verifying that the proposed method was an effective music separation algorithm.展开更多
以深度神经网络(deep neural network,DNN)为基础构建的自动驾驶软件已成为最常见的自动驾驶软件解决方案.与传统软件一样,DNN也会产生不正确输出或意想不到的行为,基于DNN的自动驾驶软件已经导致多起严重事故,严重威胁生命和财产安全....以深度神经网络(deep neural network,DNN)为基础构建的自动驾驶软件已成为最常见的自动驾驶软件解决方案.与传统软件一样,DNN也会产生不正确输出或意想不到的行为,基于DNN的自动驾驶软件已经导致多起严重事故,严重威胁生命和财产安全.如何有效测试基于DNN的自动驾驶软件已成为亟需解决的问题.由于DNN的行为难以预测和被人类理解,传统的软件测试方法难以适用.现有的自动驾驶软件测试方法通常对原始图片加入像素级的扰动或对图片整体进行修改来生成测试数据,所生成的测试数据通常与现实世界差异较大,所进行扰动的方式也难以被人类理解.为解决上述问题,提出测试数据生成方法IATG(interpretability-analysis-based test data generation),使用DNN的解释方法获取自动驾驶软件所做出决策的视觉解释,选择原始图像中对决策产生重要影响的物体,通过将其替换为语义相同的其他物体来生成测试数据,使生成的测试数据更加接近真实图像,其过程也更易于理解.转向角预测模型是自动驾驶软件决策模块重要组成部分,以此类模型为例进行实验,结果表明解释方法的引入有效增强IATG对转向角预测模型的误导能力.此外,在误导角度相同时IATG所生成测试数据比DeepTest更加接近真实图像;与semSensFuzz相比,IATG具有更高误导能力,且IATG中基于解释分析的重要物体选择技术可有效提高semSensFuzz的误导能力.展开更多
针对语音识别中DBN-DNN训练时间过长的问题,提出了一种DBN-DNN网络的快速训练方法。该方法从减少误差反向传播计算量的角度出发,在更新网络参数时,通过交替变换网络更新层数来实现加速;同时,也设计了逐渐减少网络全局更新频率和逐渐减...针对语音识别中DBN-DNN训练时间过长的问题,提出了一种DBN-DNN网络的快速训练方法。该方法从减少误差反向传播计算量的角度出发,在更新网络参数时,通过交替变换网络更新层数来实现加速;同时,也设计了逐渐减少网络全局更新频率和逐渐减少网络更新层数两种实施策略。这种训练方法可以与多种DNN加速训练算法相结合。实验结果表明,在不影响识别率的前提下,该方法独立使用或与随机数据筛选(stochastic data sweeping,SDS)算法、ASGD算法等DNN加速训练算法相结合,都可以取得较为理想的加速结果。展开更多
基金supported by the National Natural Science Foundation of China(61671095,61371164,61702065,61701067,61771085)the Project of Key Laboratory of Signal and Information Processing of Chongqing(CSTC2009CA2003)+1 种基金Chongqing Graduate Research and Innovation Project(CYS17219)the Research Project of Chongqing Educational Commission(KJ130524,KJ1600427,KJ1600429)
文摘For the difficulty of separation between singing and accompaniment in the musical signals,an improved music separation method of based on discriminative training depth neural network(DNN) was proposed.Firstly,based on the DNN model,considering the reconstruction errors and discrimination information between singing and accompaniment,an improved objective function was presented to discriminate the training;Then,an additional layer was added to DNN model,introducing the time-frequency masking to optimize the estimated accompaniment of the song,and the corresponding time-domain signal was obtained by inverse Fourier transform;Finally,the influence of different parameters on the separation performance was verified,and compared it with the existing music separation methods.The experimental results showed that the improved objective function and the introduction of time-frequency masking significantly improved the separation performance of the DNN,and the separation performance was improved about 4 dB compared with other existing music separation methods,thus verifying that the proposed method was an effective music separation algorithm.
文摘以深度神经网络(deep neural network,DNN)为基础构建的自动驾驶软件已成为最常见的自动驾驶软件解决方案.与传统软件一样,DNN也会产生不正确输出或意想不到的行为,基于DNN的自动驾驶软件已经导致多起严重事故,严重威胁生命和财产安全.如何有效测试基于DNN的自动驾驶软件已成为亟需解决的问题.由于DNN的行为难以预测和被人类理解,传统的软件测试方法难以适用.现有的自动驾驶软件测试方法通常对原始图片加入像素级的扰动或对图片整体进行修改来生成测试数据,所生成的测试数据通常与现实世界差异较大,所进行扰动的方式也难以被人类理解.为解决上述问题,提出测试数据生成方法IATG(interpretability-analysis-based test data generation),使用DNN的解释方法获取自动驾驶软件所做出决策的视觉解释,选择原始图像中对决策产生重要影响的物体,通过将其替换为语义相同的其他物体来生成测试数据,使生成的测试数据更加接近真实图像,其过程也更易于理解.转向角预测模型是自动驾驶软件决策模块重要组成部分,以此类模型为例进行实验,结果表明解释方法的引入有效增强IATG对转向角预测模型的误导能力.此外,在误导角度相同时IATG所生成测试数据比DeepTest更加接近真实图像;与semSensFuzz相比,IATG具有更高误导能力,且IATG中基于解释分析的重要物体选择技术可有效提高semSensFuzz的误导能力.
文摘针对语音识别中DBN-DNN训练时间过长的问题,提出了一种DBN-DNN网络的快速训练方法。该方法从减少误差反向传播计算量的角度出发,在更新网络参数时,通过交替变换网络更新层数来实现加速;同时,也设计了逐渐减少网络全局更新频率和逐渐减少网络更新层数两种实施策略。这种训练方法可以与多种DNN加速训练算法相结合。实验结果表明,在不影响识别率的前提下,该方法独立使用或与随机数据筛选(stochastic data sweeping,SDS)算法、ASGD算法等DNN加速训练算法相结合,都可以取得较为理想的加速结果。
