基于多种机器学习算法的车载语音文本分类研究  

Research on Vehicle Speech and Text Classification Based on Multiple Machine Learning Algorithms

作　　者：刘威 张森 宋冠谕 丁晓雯 LIU Wei;ZHANG Sen;SONG Guanyu;DING Xiaowen(Guangxi Automobile New Four Chemicals Key Laboratory,SAIC-GM-Wuling Automobile Co.,Ltd.,Liuzhou Guangxi 545007,China)

机构地区：[1]上汽通用五菱汽车股份有限公司广西汽车新四化重点实验室,广西柳州545007

出　　处：《信息与电脑》2021年第23期68-70,共3页Information & Computer

摘　　要：车载语音交互是指用语音直接控制车控模块,如空调、天窗、座椅等,同时也可以通过语音指令实现在线音乐播放、导航、打电话及天气查询等功能,大大提高了驾驶过程中的安全性,用户也拥有了更好的驾驶体验。本文主要对自然语言理解(Natural Language Understanding,NLU)技术进行研究,运用多种机器学习算法对车载语音文本进行分类,确定最优算法,以应用到车载语音场景中,并对车载语音文本类别进行校验,提高识别率。On board voice interaction refers to using voice to directly control vehicle control modules, such as air conditioner,skylight, seat, etc. at the same time, it can also realize online music playback, navigation, telephone call, weather query and other functions through voice commands, which greatly improves the safety in the driving process and gives users a better driving experience. This paper mainly studies the natural language understanding(NLU) technology, classifies the vehicle voice text by using a variety of machine learning algorithms, determines the optimal algorithm, applies it to the vehicle voice scene, verifies the vehicle voice text category, and improves the recognition rate.

关 键 词：车载语音交互 机器学习 文本分类 

分 类 号：P456.7[天文地球—大气科学及气象学]