电子器件2017，Vol.40Issue(5)：1229-1233,5.DOI:10.3969/j.issn.1005-9490.2017.05.034
基于改进的深度神经网络的说话人辨认研究
Research on Speaker Identification Based on Improved Deep Neural Network
摘要
Abstract
The technology of speaker identification will be used in many areas in the future. Firstly,a research is made on the use of two basic Deep Neural Network models which refer to Stacked Denoising-Autoencoders and Deep Belief Network on speaker identification. By pre-training layer-wisely without labels and back fine-tuning with labels,Deep Neural Network has overcome the shortcoming that is easy to fall into local minimum caused by back propagation. The experiments proves that Deep Network Model performs better than normal BP Network when the amount of neurons is bigger than certain number and its performance grows with the scale of Network enlarges. Considering the training time of large Deep Model is too long,this text proposes using Rectifier Linear Unit to replace traditional sigmoid function to improve deep model on speaker identification. The results of experiment show that the training time and error rate of improved deep model has decreased by 35% and 8.3% respectively.关键词
说话人辨认/堆叠降噪自编码/深度信念网络/整流线性单元Key words
speakeridentification/stacked denoising-autoencoders/deep belief network/rectifier neural network分类
信息技术与安全科学引用本文复制引用
赵艳,吕亮,赵力..基于改进的深度神经网络的说话人辨认研究[J].电子器件,2017,40(5):1229-1233,5.基金项目
国家自然科学基金项目( 61301219) （ 61301219）
南京工程学院校级项目( YKJ201107) （ YKJ201107）
2014年青蓝工程项目 （）
