基于人工智能技术和语音识别的机器同步翻译系统  

Machine synchronous translation system based on artificial intelligence technology and speech recognition

作　　者：郭慧骏 GUO Huijun(Jinzhong University,Jinzhong 030619,China)

机构地区：[1]晋中学院,山西晋中030619

出　　处：《现代电子技术》2022年第9期152-156,共5页Modern Electronics Technique

摘　　要：传统机器同步翻译系统受到复杂语句参数的影响,翻译精准度较低,为了剔除多余参数,提升翻译准确性,设计了人工智能技术和语音识别的机器同步翻译系统。利用单片机SPCE061A对复杂的数字信号进行处理。同步翻译服务器中训练数据支持大量用户的翻译服务,翻译结果通过用户终端会话界面显示。利用PMDL模型检测关键字信号,并记录PCM音频数据,对采集到的脉冲码调制信号进行数据切片,从而唤醒人工智能语音服务。建立语音识别流程,精确地输出语音相关语义。以输入文本为搜索条件,设计人工交互同步翻译程序,对集合进行修剪,从而获得最佳的翻译效果。通过实验可以看出,该系统的语句翻译准确率为0.9~1.0,较好地解决了传统系统翻译准确率低的问题。The translation accuracy of the traditional machine synchronization translation systems is low because of its complex statement parameters.In view of this,a machine synchronization translation system with artificial intelligence technology and speech recognition is designed to eliminate the redundant parameters and improve the translation accuracy.The SCM SPCE061A is used to process complex digital signals.In the synchronous translation server,the trained data are obtained to support translation services for a large number of users,and the translation results are displayed by the user terminal conversation interface.The PMDL model is used to detect keyword signals,record PCM audio data,and slice the collected pulse code modulation signals,so as to wake up artificial intelligence voice services.A speech recognition process is established to accurately output speech⁃related semantics.By taking the input text as the search condition,a manual interactive synchronous translation program is designed to trim the collection,so as to obtain the best translation effect.It can be seen by the experiments that the accuracy rate of statement translation of this system is 0.9~1.0,so it can improve the translation accuracy of the traditional systems.

关 键 词：机器同步翻译 人工智能技术 语音识别 信号处理 界面显示 数据切片 语义输出 

分 类 号：TN912.3-34[电子电信—通信与信息系统] TP311.52[电子电信—信息与通信工程]