基于卷积神经网络的声纹检测签到系统
Voiceprint Detection Sign in System Based on Convolutional Neural Network
DOI: 10.12677/CSA.2021.119239, PDF,    国家自然科学基金支持
作者: 梁景泉, 周子程, 刘秀燕*：青岛理工大学信息与控制工程学院，山东 青岛
关键词: 卷积神经网络；声纹识别；签到系统；Convolutional Neural Network； Voiceprint Recognition； Sign-In System
摘要: 针对高校传统考勤方式，如人工点名、手写签到等方式存在他人代替、耗时且效率低下等问题，基于深度学习强大的建模能力，本项目提出基于改进神经网络模型的智能化课堂语音签到系统，采用卷积神经网络(Convolutional Neural Network, CNN)进行语音模型的训练，自动提取语音深层次的声纹特征并识别，实验结果表明该系统能有效提高点名效率并能够制止代签等行为，具有有效提高教师的课堂教学效率的重要意义。
Abstract: Aiming at the problems of substitution, time-consuming and low efficiency of traditional attendance methods in colleges and universities, such as manual roll call and handwritten check-in, based on the powerful modeling ability of deep learning, this project proposes an intelligent classroom voice check-in system based on improved neural network model, which uses convolutional neural network (CNN) to train the voice model. The experimental results show that the system can effectively improve the roll call efficiency and stop the signing behavior, which is of great significance to improve the efficiency of teachers’ classroom management.
文章引用：梁景泉, 周子程, 刘秀燕. 基于卷积神经网络的声纹检测签到系统[J]. 计算机科学与应用, 2021, 11(9): 2342-2349. https://doi.org/10.12677/CSA.2021.119239

参考文献

[1] 胡晶晶, 周斌. 高校行政办公自动化系统建设与发展的研究[J]. 数码世界, 2020(12): 235-236.
[2] 王润泽, 王亮, 刘涛, 栗斌. 考虑实时路况反馈的动态路径规划算法研究[J]. 测绘科学, 2020, 45(7): 163-169.
[3] 林志伟, 王庆九, 马超虹, 谢礼礼, 吴森洋. 基于itchat的微信群签到系统开发[J]. 实验室研究与探索, 2020, 39(1): 108-115.
[4] 王健杰, 汪鹏程, 范祥林, 郁书好. 基于Android的企业GPS签到APP的设计与实现[J]. 计算机科学与应用, 2019, 9(7): 1352-1357. [Google Scholar] [CrossRef] 
[5] 张丹. 深度学习神经网络在语音识别中的应用探讨[J]. 电子世界, 2021(6): 67-68.
[6] 施巍巍. 经验模态分解方法及其在语音识别算法中的研究[D]: [硕士学位论文]. 杭州: 浙江理工大学, 2014.
[7] Zhang, X., Wang, Z. and Wang, D. (2017) A Speech Enhancement Algorithm by Iterating Single- and Multi-Microphone Processing and Its Application to Robust ASR. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, 5-9 March 2017, 276-280. [Google Scholar] [CrossRef] 
[8] 赵从健, 雷菊阳, 李明明. 基于无监督学习的语音签到系统[J]. 软件, 2019, 40(12): 183-187.
[9] 朱泰, 管震臻, 李新战, 等. 基于语音识别的课堂签到器[J]. 科技资讯, 2018, 16(10): 32-33.
[10] 范长青. 小词汇量非特定人连续语音识别系统的研究[D]: [硕士学位论文]. 沈阳: 沈阳理工大学, 2008.
[11] Rabiner, L.R. (1978) On Creating Reference Templates for Speaker Independent Recognition of Isolated Words. IEEE Transactions on Acoustics Speech and Signal Processing, 26, 34-42. [Google Scholar] [CrossRef] 
[12] Prasanna Kumar, M.K. and Kumaraswamy, R. (2017) Sin-gle-Channel Speech Separation Using Empirical Mode Decomposition and Multi Pitch Information with Estimation of Number of Speakers. International Journal of Speech Technology, 20, 109-125. [Google Scholar] [CrossRef] 
[13] Issa, D., Demirci, M.F. and Yazici, A. (2020) Speech Emotion Recognition with Deep Convolutional Neural Networks. Biomedical Signal Processing and Control, 59, Article ID: 101894. [Google Scholar] [CrossRef] 
[14] Nguyen, Q.H. and Cao, T.D. (2020) A Novel Method for Recognizing Vietnamese Voice Commands on Smartphones with Support Vector Machine and Convolutional Neural Networks. Wireless Communications and Mobile Computing, 2020, Article ID: 2312908. [Google Scholar] [CrossRef] 
[15] Tang, J., Deng, C. and Huang, G.B. (2015) Extreme Learning Machine for Multilayer Perceptron. IEEE Transactions on Neural Networks and Learning Systems, 27, 809-821. [Google Scholar] [CrossRef] 
[16] Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) Imagenet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Sys-tems, 25, 1097-1105.
[17] LeCun, Y., Bottou, L., Bengio, Y., et al. (1998) Gradient-Based Learning Applied to Docu-ment Recognition. Proceedings of the IEEE, 86, 2278-2324. [Google Scholar] [CrossRef] 
[18] 刘晓晨, 潘孝勤, 曹金璇, 芦天亮. 声纹识别和语音识别技术在公安领域的应用[J]. 网络安全技术与应用, 2021(4): 153-155.
[19] 李育贤, 李玓. 声纹识别技术在车载语音交互中的应用前景[J]. 汽车工业研究, 2021(1): 30-32.
[20] 张金鑫. 面向家居场景的声纹识别关键技术研究[D]: [硕士学位论文]. 南京: 南京邮电大学, 2020.
[21] 白莹, 赵振东, 戚银城, 王斌, 郭建勇. 基于小波神经网络的与文本无关说活人识别方法研究[J]. 电子与信息学报, 2006, 28(6): 1036-1039.