基于门控网络的军事装备控制指令语音识别研究

doi:10.19678/j.issn.1000-3428.0058590

计算机工程 ›› 2021, Vol. 47 ›› Issue (7): 301-306. doi: 10.19678/j.issn.1000-3428.0058590

基于门控网络的军事装备控制指令语音识别研究

柏财通^1,4, 高志强^2,4, 李爱^1,4, 崔翛龙^3,4

1. 中国人民武装警察部队工程大学研究生大队, 西安 710086;
2. 中国人民武装警察部队工程大学信息工程学院, 西安 710086;
3. 中国人民武装警察部队工程大学乌鲁木齐校区, 乌鲁木齐 830049;
4. 中国人民武装警察部队工程大学反恐指挥信息工程研究团队, 西安 710086

收稿日期:2020-06-09 修回日期:2020-07-13 发布日期:2021-07-15
作者简介:柏财通(1995-),男,硕士研究生,主研方向为智能语音识别;高志强,讲师、博士;李爱,硕士研究生;崔翛龙(通信作者),教授。
基金资助:
国家自然科学基金（U1603261）；网信融合基金（LXJH-10（A）-09）；武警部队军事理论研究项目（WJJY20JL0284）。

Research on Voice Recognition of Military Equipment Control Commands Based on Gated Network

BAI Caitong^1,4, GAO Zhiqiang^2,4, LI Ai^1,4, CUI Xiaolong^3,4

1. Graduated Group, Engineering University of PAP, Xi'an 710086, China;
2. College of Information Engineering, Engineering University of PAP, Xi'an 710086, China;
3. Urumqi Campus, Engineering University of PAP, Urumqi 830049, China;
4. Anti-terrorism Command Information Engineering Research Team, Engineering University of PAP, Xi'an 710086, China

Received:2020-06-09 Revised:2020-07-13 Published:2021-07-15

摘要/Abstract

摘要： 军事装备无感控制是军事装备智能化建设进程中的一个重要研究方向，其中语音控制技术作为无人装备无感控制手段的关键组成部分，受到了越来越多的重视。为完成军事装备语音控制任务，设计一种基于门控网络的中文语音识别网络，并构建军事装备控制指令数据集，实现基于控制指令语音识别技术的军事装备控制。在传统卷积神经网络的结构基础上引入深度残差门控卷积网络，提高识别网络的准确性，同时通过多途径构建军事装备控制指令数据集，设计一套针对军事装备无感控制的语音识别方案。实验结果表明，该语音识别网络军事语音控制指令识别率可达87%，外接语言模型后可达92%，语音识别准确率高、误差率低，可完成军事装备的语音控制任务。

关键词: 语音识别, 门控卷积神经网络, 装备无感控制, 长短时记忆网络, 残差网络

Abstract: The sensorless control of military equipment is an important research direction in intelligent military equipment development.As a key component of the sensorless control of unmanned equipment,speech control has attracted more and more attention.To realize military equipment control based on the voice recognition of control commands,this paper describes the design of a Chinese voice recognition network based on a gated network,and a data set of military equipment control commands.Based on the structure of the traditional convolutional neural networks,a deep residual gated convolutional network is introduced to improve the accuracy of the recognition network.At the same time,a data set of military equipment control commands is constructed by using multiple methods,and a voice recognition scheme for sensorless control of military equipment is designed.Experimental results show that the recognition rate of the proposed voice recognition network reaches 87%,and 92% when connected to a language model. This network improves the accuracy of voice recognition while reducing the errors,and can complete the voice control task of military equipment.

Key words: voice recognition, gated convolutional neural network, sensorless control of equipment, Long Short Term Memory (LSTM) network, residual network

中图分类号:

TP391

柏财通, 高志强, 李爱, 崔翛龙. 基于门控网络的军事装备控制指令语音识别研究[J]. 计算机工程, 2021, 47(7): 301-306.

BAI Caitong, GAO Zhiqiang, LI Ai, CUI Xiaolong. Research on Voice Recognition of Military Equipment Control Commands Based on Gated Network[J]. Computer Engineering, 2021, 47(7): 301-306.

https://www.ecice06.com/CN/Y2021/V47/I7/301

图/表 15

20210721093838

20210721093841

20210721093844

20210721093848

20210721093851

20210721093855

20210721093859

20210721093903

20210721093907

20210721093911

20210721093914

20210721093918

20210721093921

20210721093926

20210721093929

参考文献

[1] 朱鸿展.融合手势与语音的多通道标绘交互技术研究[D].长沙:国防科学技术大学,2014. ZHU H Z.Research on multi-channel plotting interactive technology combining gesture and speech[D].Changsha:National University of Defence Technology,2014.(in Chinese)
[2] 曹慧敏.基于海上侦察系统的声音识别技术研究[D].南京:南京理工大学,2010. CAO H M.Research on voice recognition technology based on maritime reconnaissance system[D].Nanjing:Nanjing University of Science and Technology,2010.
[3] 赵军辉,匡镜明,谢湘.应用于军事指挥中的鲁棒性语音识别系统[J].兵工学报,2004,25(4):509-512. ZHAO J H,KUANG J M,XIE X.Robust speech recognition system applied in military command[J].Journal of Ordnance Engineering,2004,25(4):509-512.(in Chinese)
[4] 路建伟,丁庆海,朱雪平,等.战场环境下的军事命令识别技术[J].南京理工大学学报(自然科学版),2002,26(4):438-441,445. LU J W,DING Q H,ZHU X P,et al.Military command recognition technology in battlefield environment[J].Journal of Nanjing University of Science and Technology(Natural Science Edition),2002,26(4):438-441,445.(in Chinese)
[5] 李鹏,杨元维,高贤君,等.基于双向循环神经网络的汉语语音识别[J].应用声学,2020,39(3):464-471. LI P,YANG Y W,GAO X J,et al.Chinese speech recognition based on bidirectional recurrent neural network[J].Applied Acoustics,2020,39(3):464-471.(in Chinese)
[6] 张瑞珍,韩跃平,张晓通.基于深度LSTM的端到端的语音识别[J].中北大学学报(自然科学版),2020,41(3):244-248. ZHANG R Z,HAN Y P,ZHANG X T.End-to-end speech recognition based on deep LSTM[J].Journal of North University of China (Natural Science Edition),2020,41(3):244-248.(in Chinese)
[7] 刘娟宏,胡彧,黄鹤宇.端到端的深度卷积神经网络语音识别[J].计算机应用与软件,2020,37(4):192-196. LIU J H,HU Y,HUANG H Y.End-to-end deep convolutional neural network speech recognition[J].Computer Applications and Software,2020,37(4):192-196.(in Chinese)
[8] 张威,翟明浩,黄子龙,等.SE-MCNN-CTC的中文语音识别声学模型[J].应用声学,2020,39(2):223-230. ZHANG W,ZHAI M H,HUANG Z L,et al.SE-MCNN-CTC Chinese speech recognition acoustic model[J].Applied Acoustics,2020,39(2):223-230.(in Chinese)
[9] HAN W,ZHANG Z D,ZHANG Y,et al.ContextNet:improving convolutional neural networks for automatic speech recognition with global context[EB/OL].[2020-05-05].https://arxiv.org/abs/2005.03191.
[10] COLLOBERT R,PUHRSCH C,SYNNAEVE G.Wav2Letter:an end-to-end ConvNet-based speech recognition system[EB/OL].[2020-05-05].https://arxiv.org/abs/1609.03193.
[11] DAUPHIN L,YANN N.Language modeling with gated convolutional networks[C]//Proceedings of the 34th International Conference on Machine Learning.Washington D.C.,USA:IEEE Press,2017:325-339.
[12] YING T,YANG J,LIU X M.Image super-resolution via deep recursive residual network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:235-244.
[13] MARTIN S,SCHLUTER R,NEY H.LSTM neural networks for language modeling[C]//Proceedings of the 20th ACM Conference of the International Speech Communication Association.New York,USA:ACM Press,2012:158-169.
[14] MARCELLO F.Language modelling for efficient beam-search[J].Computer Speech and Language 1995,9(4):353-380.
[15] MIAO Y J.An empirical exploration of CTC acoustic models[C]//Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing.Washington D.C.,USA:IEEE Press,2016:457-469.
[16] KINGMA A,DIEDERIK P,BA J.Adam:a method for stochastic optimization[EB/OL].[2020-05-05].https://arxiv.org/abs/.
[17] WANG Y S,DENG X J,PU S B,et al.Residual convolutional CTC networks for automatic speech recognition[EB/OL].[2020-05-05].https://arxiv.org/abs/1702.07793.
[18] WILLIAM C.Listen,attend and spell:a neural network for large vocabulary conversational speech recognition[C]//Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing.Washington D.C.,USA:IEEE Press,2016:59-72.
[19] ZHAO J F,XIA M,CHEN L J.Speech emotion recognition using deep 1D & 2D CNN LSTM networks[J].Biomedical Signal Processing and Control,2019,47(6):312-323.
[20] PRATAP V,HANNUN A,XU Q T,et al.wav2letter++:the fastest open-source speech recognition system[EB/OL].[2020-05-05].https://arxiv.org/abs/1812.07625.

选择文件类型/文献管理软件名称

选择包含的内容

基于门控网络的军事装备控制指令语音识别研究

Research on Voice Recognition of Military Equipment Control Commands Based on Gated Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈虹, 王瀚文, 金海波. 融合改进自编码器和残差网络的入侵检测模型[J]. 计算机工程, 2024, 50(2): 188-195.
[2]	丰芳宇, 罗晓曙, 蒙志明, 王广宇. 基于抗混叠残差注意力网络的人脸表情识别[J]. 计算机工程, 2023, 49(8): 190-198.
[3]	王名茂, 陈向阳, 叶子, 肖利芳, 郑戎. 全局区分性增强与边界监督的篡改检测网络[J]. 计算机工程, 2023, 49(6): 154-161.
[4]	王同官, 赖惠成, 蔡玉玺, 高古学, 汪烈军. 基于注意力残差网络的人脸超分辨率重建[J]. 计算机工程, 2023, 49(6): 234-241.
[5]	谌雨章, 黄逸姿, 张钧涵. 基于多速率空洞卷积的多尺度水下小目标检测[J]. 计算机工程, 2023, 49(6): 257-264.
[6]	陈明, 刘蓉, 张晔. 基于多重注意力机制的中文医疗实体识别[J]. 计算机工程, 2023, 49(6): 314-320.
[7]	李宜亭, 屈丹, 杨绪魁, 张昊, 沈小龙. 基于分解门控注意力单元的高效Conformer模型[J]. 计算机工程, 2023, 49(5): 73-80.
[8]	丁子轩, 俞雷, 张娟, 李想, 王新宇. 基于深度残差自适应注意力网络的图像超分辨率重建[J]. 计算机工程, 2023, 49(5): 231-238.
[9]	石磊, 张吉涛, 高宇飞, 卫琳, 陶永才. 基于Transformer与BiLSTM的网络流量入侵检测[J]. 计算机工程, 2023, 49(3): 29-36,57.
[10]	冉瑞生, 翁稳稳, 王宁, 彭顺顺. 基于人脸关键特征提取的表情识别[J]. 计算机工程, 2023, 49(2): 254-262.
[11]	刘群坡, 盛月琴, 高如新, 卜旭辉. 基于关键帧和注意力残差网络的手语识别[J]. 计算机工程, 2023, 49(12): 224-230, 242.
[12]	赵德春, 舒洋, 李玲, 陈欢, 张子豪. 丢弃冗余块的语音识别Transformer解码加速方法[J]. 计算机工程, 2023, 49(10): 105-111, 119.
[13]	赫晓慧, 宋定君, 李盼乐, 田智慧, 周广胜. 融合多尺度特征的遥感影像道路提取方法[J]. 计算机工程, 2022, 48(8): 196-205.
[14]	郝阿香, 贾郭军. 结合注意力与批特征擦除的行人重识别模型[J]. 计算机工程, 2022, 48(7): 270-276,306.
[15]	曹瑞阳, 郭佑民, 牛满宇. 基于最大最小距离的多中心数据综合增强方法[J]. 计算机工程, 2022, 48(6): 174-181.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于门控网络的军事装备控制指令语音识别研究

Research on Voice Recognition of Military Equipment Control Commands Based on Gated Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献

相关文章 15

编辑推荐

Metrics

本文评价