Speech recognition and natural language process technology can receive and sort audio content . this is the first step toward retrieval entire video and sort video content . in this paper , we deal with the problem of segmenting news video data into semantically coherent scene using audio and video data , besides , classifying of news video content 利用语音识别技术和自然语言处理技术对音频流中的语音段进行处理，就可以解决音频内容的提取和分类问题，这样就更有利于检索的进行，进而可以对所对应的视频段进行内容分类，这些都为我们的研究创造了条件。
This dissertation discusses important issues pertinent to the ums ( unified messaging system ) based on the experience gained in the project of zhx - ums ( zhonghongxun unified messaging system ) . the work presented in this dissertation reflects the author ' s involvement in the development of the zhx - ums prototype system , and can be classified into two groups : system top - design and software development . an emphasis has been given to the software development , which directly related two techniques : tts ( text - to - speech ) and asr ( auto speech recognition ) 本文以作者参与“中鸿讯统一消息服务系统( zhx - ums ) ”设计与开发工作为背景，在讨论有关ums的体系结构、关键技术和实现方法等方面问题的基础上，重点讨论了文本-语音转换技术( tts )和自动语音识别技术( asr )的现状及其在ums系统中的应用与开发。
This paper describes a method of realizing voice application system of atc ( air traffic control ) training simulator . through study on speech recognition and text - to - speech , this system introduces ibm ' s newly techniques - viavoice speech recognition and text - to - speech system , makes an organic combination between voice application system and atc training system , realizes automatic voice control of atc training simulator , which can be programmable and self - educated 本文通过对语音识别技术和语音合成技术的研究，在引进ibmviavoice语音识别与语音合成系统的基础上，根据空管模拟训练机的功能需求分析，将语音识别技术与管制训练控制系统有机结合，实现了计算机系统自动对非特定管制学员、连续管制指令语言的识别和仿真模拟雷达显示控制。
The thesis makes researches on technologies of call centers , voice disposing technologies and the synthetic application of these technologies . with setting up a call center which is called epcc ( electric power call center ) in a electric power company , the thesis describes pivotal technologies in call centers , such as voice disposing technologies > , crm ( customer relationship management ) and web technologies , the thesis represents standard schemes and standard frames of call centers , and the thesis describes pivotal technologies in voice disposing procedures , such as speech synthesize and speech recognize , and the thesis describes voice disposing technology " s applications in call centers that are called ivr ( interactive voice response ) systems , then the thesis discusses the acd ( auto call distribution ) program in epcc 本论文通过建立呼叫中心的一个实例(电力呼叫中心) ，对呼叫中心、语音技术及其综合应用进行了较为深入的研究。通过呼叫中心的电力应用，较详细地论述了呼叫中心的关键技术：语音技术、客户关系管理crm和web技术等；较深入地阐述了呼叫中心的典型方案和典型结构；较详细地论述了语音信号处理技术的关键技术：语音合成技术及语音识别技术：深入讨论了语音技术在呼叫中心的具体应用- - - ivr系统及其关键技术；较详细地讨论了电力呼叫中心中所采用的acd算法，并基于acd算法完善了呼叫中心的表现形式。
This paper reviews the research of progress of current large vocabulary continuous speech recognition and describes main problems on the moden design of the mandarin large vocabulary speech recognition system ( lvsrs ) . the key issues affecting lvsrs and principles are discussed in detail 本文综述了近年来大词汇量连续语音识别技术进步和发展，描述了大词汇量连续汉语语音识别系统的设计方法.对语音识别系统中的一些关键技术和原理进行了详细地分析和讨论，并对语音识别技术进一步发展中存在的问题和近年语音识别研究发展动向进行了讨论
Speech recognition technology is concerned with many research fields of varied subjects . it has close relationship with acoustics 、 phonetics 、 linguistics 、 artificial 、 intelligence 、 digital signal processing 、 pattern recognition as well as optimization theory etc . all this research fields have contributed a lot to the development of speech recognition 语音识别技术作为一门交叉学科,它与声学、语音学、语言学、人工智能、模式识别、数字信号处理、计算机学科等众多学科都有紧密的联系。
Speech recognition is a cross - disciplinary , is gradually becoming it , the key to human interface technology , voice recognition and voice synthesis technologies combining technology integral voice response systems , voice synthetic systems , interactive toys , enable people to voice ordering through operation , the control mode flexibility , a broad market prospect 语音识别是一门交叉学科，正逐步成为信息技术中人机接口的关键技术，语音识别技术与语音合成技术相结合组成语音应答系统、语音合成系统、互动式玩具等，使人们能够通过语音命令进行操作，控制方式灵活方便，具有广阔的市场前景。
Presents the talking and mobile robot developed by harbin institute of technology for china science and technology museum , which is driven by two dc motors with enevgy provided by storage batteries and moves around to greet visitors through simple path planning and talks with people in the big hall on the first floor through voice mixture and identification technology for a duration of 4 hours per charge because of light weight and low energy consumption 研制的机器人以蓄电池为能源，通过两个直流力矩电机分别驱动机器人前进或转弯，可无缆行走具有较强的避障和一定的路径规划能力;同时利用语音合成和语音识别技术，可与人进行简单的对话，对场馆的展品进行自动解说，智能化程度较高.机器人的造型和材料上有所突破，质量较轻，能耗低，一次充电可行走4h
