您现在的位置: 首页> 研究主题> 语音检测

语音检测

语音检测的相关文献在1996年到2023年内共计378篇,主要集中在无线电电子学、电信技术、自动化技术、计算机技术、语言学 等领域,其中期刊论文57篇、会议论文15篇、专利文献1161075篇;相关期刊46种,包括电声技术、电讯技术、电子产品世界等; 相关会议11种,包括第二十五届全国通信与信息技术发展学术研讨会、第九届全国人机语言通讯学术会议、第八届全国人机语音通讯学术会议(NCMMSC8)等;语音检测的相关文献由768位作者贡献,包括严迪群、陶建华、易江燕等。

语音检测—发文量

期刊论文>

论文:57 占比:0.00%

会议论文>

论文:15 占比:0.00%

专利文献>

论文:1161075 占比:99.99%

总计:1161147篇

语音检测—发文趋势图

语音检测

-研究学者

  • 严迪群
  • 陶建华
  • 易江燕
  • 王让定
  • 简志华
  • 郑榕
  • 傅睿博
  • 徐波
  • 李志雄
  • 李株亮
  • 期刊论文
  • 会议论文
  • 专利文献

搜索

排序:

年份

    • 吾买尔江·麦麦提; 阿布都热孜克·热孜克
    • 摘要: 本文通过介绍广播电台日常业务工作中的广播信号监测技术,结合当前广播信号监测技术手段以及其存在的缺点、发展方向,通过语音信号监测技术与广播信号监测工作相结合,提出了基于调制频谱的广播信号监测方法。
    • 李晨杰; 朱允斌
    • 摘要: The acceleration of life rhythm and rapid development of the Internet information technology lead to the increasing demand of news video storage and reutilization.It is a meaningful subject about how to segment a long news video into several small news items.A news video segmentation algorithm based on audio and video features is proposed.It only extracts anchor person feature and silence track feature which are the basic visual and audio features,respectively.Anchor person feature is detected via face recognition are combined Short-time energy and zero-crossing rate are used to detect silence feature and filter them with condition.Two features are combined to analyze the borders of different news item.The experiments are performed with news videos which are 3000 minutes in total,and the result is great:recall rate is 0.856 3,precision 0.932 6 and f1 measure 0.892 8.The accuracy of the border detected is frame.Analysis has been done about the influence of the length,restrictions and redundancy of silence track to the result.%随着人们生活节奏的加快和网络信息技术的迅猛发展,对新闻视频节目的存储和再利用需求日益剧增,如何将较长的新闻视频节目按其内容拆分成多个新闻条目成为了一个有意义的课题.提出了一种基于音视频特征的新闻拆条算法,仅提取了新闻视频在视觉、音频上的基本特征即主持人特征和音频静音段特征进行分析.通过人脸识别提取主持人特征,使用短时能量和过零率提取静音特征,并对其加以条件筛选,结合这两个特征完成拆条工作.针对总计时长3 000分钟的新闻联播节目进行实验,得到较好的实验结果:召回率0.856 3,准确率0.932 6和F1值0.892 8.且视频边界的准确度精确到帧.同时分析了静音段长度阈值、限制条件和毛刺现象对于新闻拆条结果的影响.
    • 呼德; 陈喆; 殷福亮
    • 摘要: Audio mixing is indispensable to achieve the sense of reality in video conference systems.In this paper,a digital audio mixing algorithm with equal-loudness is proposed.Voice activity detection (VAD) is first performed by the average power and short-term autocorrelation sequence of signal.Then,the noise caused by audio mixing directly is filtered by the time-varying filter,where the passband variation of the filter depends on the result of voice activity detection.Finally,to achieve the effect of equal-loudness,the weight of each channel signal in audio mixing is calculated with the average loudness of voice.Simulation results show that the proposed algorithm can make the average loudness of each channel signal close to the same,which can effectively decrease the distortion of small-signal.%在电视会议系统中,为获得接近真实的会议交流氛围,混音技术不可或缺.本文利用语音信号的响度特性,提出一种自动等响度数字混音算法.该算法首先利用信号平均功率和短时自相关函数进行语音活动检测(VAD),判断参与混音的每路信号中是否含有语音信号.然后,利用时变滤波器进行滤波处理,抑制混音过程中引入的噪声.最后,利用语音信号响度计算各路信号的权重,使各路语音的平均响度保持一致.仿真实验结果表明,本文的混音算法可使各路信号的平均响度基本相同,并具有良好的语音质量.
    • 赵欢; 祁威; 张希翔
    • 摘要: Child-directed Speech(CDS) has large influence on early child growth,so it is significant to recognize CDS from a speech and make full use of it.In order to improve the detection accurary,this paper constructs a Chinese CDS detection model based on Adaboost algorithm.It uses a decision tree as a weak classifier for extracting features of Chinese CDS to learn,and forms weak classifier tuple,while the classification results of this group of weak classifiers are weighted voting,to distinguish the voice category.Experimental results show that the vowel duration of CDS is longer than nonCDS;increasing the number of weak classifiers will improve the accuracy of Chinese CDS;the longer the length of test speech is,the higher the detection accuracy of Chinese CDS;compared with v-SVM algorithm,Adaboost algorithm has higher accuracy and precision in Chinese CDS detection,and it improves the robustness of the detection system.%儿向语音对早期儿童成长有较大影响,正确检测并充分利用儿向语音具有现实意义.为此,构建一种基于Adaboost算法的汉语儿向语音检测模型,以提高检测准确率.使用决策树作为弱分类器对提取的汉语儿向语音特征进行学习,并组成弱分类器元组,同时对该弱分类器组的分类结果进行加权,区分待测语音的类别.实验结果表明,汉语儿向语音的元音持续时长超过非儿向语音的元音持续时长;提升弱分类器的数量可提高汉语儿向语音检测正确率;分段语音时间越长,汉语儿向语音检测正确率越高;采用改进的Adaboost算法比采用v-SVM算法具有更高的准确率和精度,同时可增强系统的鲁棒性.
    • 谷晓彬; 冯国英; 刘建
    • 摘要: The adaptive filtering algorithm based on recursive least square algorithm was applied to a laser Doppler vibrometer and the corresponding weak vibration measuring devices were built up . Compared with Chebyshev low-pass filtering algorithm , simulation and experimental results show that this adaptive filtering algorithm can suppress the random Gaussian white noise and restore the original signal; the RLS algorithm can effectively filter out noise from the vibration signal , and restore the low-frequency 20 Hz signal drowned out in the noise; the RLS algorithm also can filter out noise from voice leading voice to being pure and enhance speech signal . The above verifies the feasibility of this algorithm in the heterodyne vibration measurement . The algorithm is simple and easy to use , fast and has strong convergence . In the aspect of filtering random noise , the RLS algorithm is more effective than low-pass filter .%将递归最小二乘自适应滤波算法应用于激光多普勒测振技术中,搭建了相应的微弱振动测量装置.模拟仿真与实验中,通过与设计的切比雪夫低通滤波算法对比,结果表明:该递归最小二乘自适应滤波算法能够有效抑制随机高斯白噪声,还原出原始信号;能够对简谐振动信号实现有效滤波,并且可以还原出淹没在噪声中的低频20 Hz信号;文中算法可以去除语音噪声,使声音更加纯净,增强语音信号,以此验证了该算法在外差振动测量中的可行性.该算法简单易用、收敛性强、速度快,尤其对于随机噪声的去除比普通的低通滤波器更加有效.
    • 徐东杰; 臧冠华; 盘丹梅; 吕旭; 王涛
    • 摘要: with the advent of the era of“Internet +”, in the life more and more items to realize intelligent control. Look now, college students com-monly use an alarm clock, mobile phone to timing, however, in addition to both often occur when the timing is not allowed, and out of adaptability, everyone will be out of the idea of want to sleep involuntarily close them, lead to miss many important things. This study on the spot to Zigbee wireless transmission protocol as the beginning of the project design, through the feedback CC2530 chip with the voice module, in order to achieve the effect of“never pillow bell”, allowing students to a more regular routine.%随着“互联网+”时代的到来,生活中越来越多的物品得以实现智能化控制。放眼现在,大学生普遍使用闹钟、手机进行定时,然而,二者除经常会出现时定时不准的情况外,而且出于适应性,大家会出于想再睡一会的想法不由自主的关闭它们,导致错过许多很重要的事情。本研究针对这一痛点,以Zigbee无线传输协议作为项目设计的切入点,通过CC2530芯片与语音模块的反馈,以达到“头不离枕头铃不停”的效果,使得大学生可以更有规律的作息。
    • 周鹤; 何培宇; 张勇; 殷晴青; 罗胡琴
    • 摘要: 虚拟阵列DOA(Direction Of Arrival)估计算法由于计算量低和资源利用率高得到了快速发展,然而虚拟阵列语音信号DOA估计算法还少有报道.本文为了提高语音信号DOA估计的准确度,对虚拟阵列语音信号DOA估计算法进行了改进.算法首先对接收信号进行能量及熵结合的语音分帧检测;其次基于功率谱方差最小和谱熵最大两个原则分别对检测后的信号进行选帧,并对选出的帧做DOA估计;最后将两者的DOA估计结果进行加权平均.本文对方差选帧的DOA估计结果、谱熵选帧的DOA估计结果和两者加权平均后的DOA估计结果进行了比较.实验结果和分析表明结合方差选帧及谱熵选帧的DOA估计算法在用于虚拟阵列语音信号DOA估计时有更高的准确率.
    • 李磊
    • 摘要: 介绍了语音问题的种类,阐述了语音检测方法及其在网络中的应用,探讨了通信网络中网元级以及网元内部的语音问题定位的方法.%This paper introduces the types of phonetic problems, expounds the voice detection method and its application in the network, and probes into the methods for the positioning of positioning of phonetic problems of network element and internal network elements in communication network.
  • 查看更多

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号