摘要
随着现代科学和计算机技术的发展,人们需要一种更方便、更自然的方式与机器交互。人们从外界获取信息的时候,最为重要、最为详细的信息来源只有两个,即形象和语言,而语言是人类最有效、最方便的交流形式。当前,随着人工智能的发展,语音识别系统的使用范围正在逐步扩大。基于此,从语音识别领域的专利数据入手,探讨语音识别技术,并在此基础上,对语音识别技术的未来研究和发展进行展望。
With the development of modern science and computer technology,people need a more convenient and natural way to interact with machines.When people obtain information from the outside world,there are only two most important and detailed sources of information,that is,image and language,and language is the most effective and convenient form of communication for human beings.Currently,with the development of artificial intelligence,the scope of use of speech recognition systems is gradually expanding.This article starts with the patent data in the field of speech recognition,discusses the speech recognition technology,and on this basis,looks forward to the future research and development of speech recognition.
作者
谢赛赛
XIE Saisai(Beijing Center for Patent Examination Cooperation of Patent Office of the State Intellectual Property Office,Beijing 100160,China)
出处
《电声技术》
2021年第10期27-29,49,共4页
Audio Engineering
关键词
语音识别
专利分析
预处理
speech recognition
patent analysis
pretreatment