Abstract： In view of the complex working environment,inconvenient operation and low efficiency of agricultural intelligent equipment,the application prospects of voice technology in agricultural intelligence were prospected. The overall architecture of the software and hardware of the voice system in agricultural equipment was proposed,and the voice technology was divided into four parts with voice prompt,voice alarm,voice control and visual voice.In the ROS development environment,the python compilation language was used to establish the control software system framework,and the complete set of control software was divided into crop information detection unit,operation information detection unit, voice signal receiving unit,operation command control unit and voice broadcast-alarm unit.Each modular programming of functional units was conducted to realize multi-functional synchronous and coordinated operation of the entire system.Taking the grape picking robot as example, the voice prompt function of the picking robot operation information,the voice control of the picking robot movement function,the field grape variety and maturity information recognition and storage and voice broadcast function were realized.It has a certain value for promoting the application of voice technology in agricultural intelligence.
SHAN A J.The application of SYN6288 Chinese speech synthesis chip in intelligent seeding monitor[J].Agricultural Science and Technology and Equipment,2012,12(6):43-44，47.（in Chinese）
GAO D F, YANG B, LIU H，et al. Multi-feature full convolutional network based ground-to-air voice enhancement method[J]. Journal of Sichuan University (Natural Science Edition), 2020, 57(2):289-296. （in Chinese）
ZHAO Z H, YANG X M. Blind source separation of speech based on FastICA[J]. Journal of Sichuan University (Natural Science Edition), 2015, 52(4):830-834. （in Chinese）
LIU X Y, YUAN B L, LI K.Design of intelligent irrigation system based on speech recognition[J].Journal of Shandong Agricultural University (Natural Science Edition),2020,51(3):479-481. （in Chinese）
［6］
KOFFI D, CURTIS O, MARGARET M. Relationship between relative maturity and grain yield of maize (Zea mays L.) hybrids in northwest New Mexico for the 2003-2019 period [J]. Agriculture,2020,10:1-12.
［7］
陈楚婷.卧室语音智能控制系统[J].科技创新与应用,2020,12(8):99-100.
CHEN C T.The bedroom voice intelligent control system[J]. Technology Innovation and Application,2020,12(8):99-100. （in Chinese）
MA K,HE R K,MA C M.Research on the experience design of home intelligent sweeping robot based on voice interaction[J].Packaging Engineering,2020, 41(18):118-124. （in Chinese）
［10］
TABINDA N S . 基于RealSense的自动换盘移栽秧苗检测研究[D].镇江：江苏大学,2019.
［11］
EHLERS F. Accessing and operating agricultural machinery: advancements in assistive technology for users with impaired mobility[J]. Assistive Technology,2019,31(5)：251-258.
［12］
GUERIN C, RAUFFET P, CHAUVIN C,et al. Toward production operator 4.0: modelling human-machine cooperation in industry 4.0 with cognitive work analysis[J]. IFAC Papers OnLine,2019,52(19)：73-78.
［13］
KIM Y G, LITTLE K, NORONHA B,et al. A voice activated biarticular exosuit for upper limb assistance du-ring lifting tasks[J]. Robotics and Computer-Integrated Manufacturing,2020,66:1-9.
YU L,LI T T.Design of intelligent voice control system based on ROS[J].Electronic Measurement Technology,2019,42(23):35-39. （in Chinese）
［15］
BANGJ U, CHOI M Y, KIM S H,et al. Automatic construction of a large-scale speech recognition database using multi-genre broadcast data with inaccurate subtitle timestamps[J]. IEICE Transactions on Information and Systems,2020,2:406-415.
［16］
TRAPPEY C V, TRAPPEY A J C, LIN S C C. Intelligent trademark similarity analysis of image, spelling, and phonetic features using machine learning methodologies[J]. Advanced Engineering Informatics,2020,45:1-12.
［17］
MAUDE D, LUCINDA H,ANNIE S,et al. The impact of respiratory function on voice in patients with presbyphonia[J]. Journal of Voice,doi：10.1016/j.jvoice.2020.05.027.
［18］
MAI X , ZHANG H, MENG Q H . Faster R-CNN with classifier fusion for small fruit detection[J]. IEEE Tran-sactions on Automation Science and Engineering，2020,17(3):1555-1569.
WANG Y F, HAN J G, FAN L H. Research brief of speech enhancement algorithm based on WGAN[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2019,31(1):136-142. （in Chinese）
TANG J, MOU H M, LENG J. Cross-modal dense depth based on speech and face parameterized representation[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2020,32(5):867-873. （in Chinese）
2021, Vol. 42 
