共查询到19条相似文献,搜索用时 156 毫秒
1.
介绍了一种基于LabVIEW环境开发的说话人识别虚似仪器.在实验室录音的情况下,该仪器具有较高的识别率,友好的用户界面,良好的存储能力,实现了实时的与文本无关的说话人识别. 相似文献
2.
3.
4.
在正交频分多址(OFDMA)系统中,合理的资源分配对于提升系统的性能具有重要的意义。针对多用户OFDMA系统,对最大化系统容量为目标的资源分配算法进行研究,提出了一种基于智能水滴算法的无向全连通图资源分配模型,以无向全连通图的顶点集和边集来描述用户与子载波之间的匹配关系。在此基础上,进一步对智能水滴算法进行改进。仿真结果表明,在满足用户比例公平性的条件下,与蚁群算法相比,基于改进智能水滴算法的全连通图分配方案能够提高2.17%~4.91%的系统速率,同时具有更快的收敛速度,提高了系统性能。 相似文献
5.
针对传统天车的控制系统的缺点,提出了一种基于FLEX遥控器的天车控制系统改造方案,在原有天车控制系统的基础上增加遥控系统,对原系统主电路控制电路、保护电路进行改进实现了天车的遥控控制,试验证明该系统运行稳定可靠. 相似文献
6.
7.
8.
9.
低轨(LEO)卫星到地面之间的无线保真(Wi-Fi)通信系统当前已经获得了广泛关注。针对LEO卫星信道的高误码、长时延等特点,采用导频插入、选择重传、帧聚合等方法对IEEE802.11g进行改进,并在开放式无线接入研究平台(WARP)v3上完成了改进方案的设计。对改进后方案的多普勒频偏性能、远距离传输速率以及高速移动条件下的传输速率等系统性能进行测试的结果表明,改进后方案在复杂信道环境下可以获得比商业Wi-Fi更好的系统性能。通过模拟验证改进方案的系统性能,证明了基于LEO卫星的Wi-Fi卫星通信系统的可实现性。 相似文献
10.
RFID系统及其设备自身所具有的许多特殊性和局限性会带来各种各样的安全性问题,特别是当系统中包含大量的标签和多个读写器时,一些传统的解决方法就无能为力了.本文提出了一种基于多读写器的Hash锁改进方法,并且对这个方法进行了分析. 相似文献
11.
支撑向量机(Support Vector Macbinc,SVM)是一种新的统计学习方法,作为一种说话人识别的手段具有独特的优势.通过产生的支持向量来概括数据集合中的信息,其分类核函数仅依赖于一小部分训练样本,即支持向量,从而降低信息的采集量和识别时间.本文介绍了说话人识别的基本原理,特征提取、模型训练等方面,通过实验证明支撑向量机(SVM)在说话人识别系统应用中表现出的良好性能. 相似文献
12.
Several theoretical approaches have been put forth to predict and explain the effects of teleconferencing technologies. One approach is to examine the functions of nonverbal signals and to make predictions based on the fact that different teleconferencing technologies allow nonverbal communication to different extents. One of the functions of nonverbal signals is to allow the listener to provide feedback to the speaker in a communication. Prior research has shown that such feedback enhances listener comprehension. In this study, it was hypothesized that different teleconferencing technologies would allow different levels of feedback based on their ability to accommodate nonverbal signals, and this in turn would affect comprehension. An experimental study was conducted to compare comprehension, feedback, and satisfaction in telephone and computer conferencing. The study confirmed that comprehension and speaker satisfaction are related to feedback, but failed to show a relationship between listener satisfaction and feedback. No difference in comprehension, listener, or speaker satisfaction was observed across teleconferencing technologies. Role-related differences were observed between the speaker and the listener. It is suggested that the effects of teleconferencing technologies can be mapped systematically by examining each of the functions of nonverbal signals, one at a time. 相似文献
13.
针对合成孔径雷达(Synthetic Aperture Radar,SAR)成像中真假目标难以区分的问题,提出了一种极化合成孔径雷达(Polarmetric SAR,PolSAR)成像固定极化转发式干扰诱饵目标鉴别方法。该方法首先通过极化熵对目标进行分类,提取低极化熵的目标并对目标进行Wigner-Ville分布(Wigner-Ville Distribution,WVD)变换,再利用Hough变换计算WVD图像中的曲线斜率,将计算出的多普勒调频率与理论调频率进行对比,进而完成真实目标与假目标的鉴别,最终通过极化对消对鉴别出的目标进行抑制。实验结果验证了该方法的有效性。 相似文献
14.
15.
16.
车辆自动识别系统 (AVI)移动站具有机动、快速和自动识别车辆的特点 ,适合于在城市监管中广泛应用。它采用射频识别 (RFID)技术 ,通过车卡 (TAG)采集车辆数据信息 ,对车辆进行自动识别和处理 ,识别率超过 99%;采用视频识别 (VFID)技术 ,通过摄像机采集车辆图像信息 ,在光照较强的情况下 ,识别率可以达到 80 %以上。 相似文献
17.
风险识别是风险管理的基础。研究海外收购专利IP风险(因素)识别方法,为良好的IP风险管理所必须,对成功的专利收购具有重要意义。本文基于管理实践总结海外收购专利IP风险(因素)识别原理,提出一套"商业目标、系统方法、识别工具和循证实践"的系统识别方法,以防止对目标企业专利IP风险(因素)识别出现重大遗漏,确保海外投资的安全。 相似文献
18.
Kim Nguyen Thuy Hang Dao 《Journal of Promotion Management》2018,24(3):398-419
ABSTRACTBuilding on social-identity theory, the research develops a model for understanding of the impact of consumer identification with a nation on consumers' brand evaluations. It posits that developing-country consumers' identification with a foreign (developed) nation influences three factors—consumer-based brand equity, consumer-based country image, and consumer-based brand credibility. The research was informed by data from 400 Vietnamese consumers in relation to two Japanese brands Sony and Honda and analyzed using structural equation modeling (SEM). The findings show that Vietnamese (developing-country) consumers prefer Japanese (developed-country) brands over domestic brands, when these consumers identify with the developed nation. 相似文献
19.
《International Journal of Research in Marketing》2022,39(1):77-95
In two studies we investigate how voice shopping may provide access to meaningful data on customer mood and how retailers may use such data. In Study 1 we explores the use of a machine learning approach to predict customer mood based on customer commands in the voice shopping process. We compare it to a heuristic approach to customer mood prediction based on situational correlates of mood that that a smart speaker can access (weather, music choice, day of week, and daylight). In Study 2 we explore how a voice retailer could use the potential capability to predict customer mood. Our results provide evidence that a customer’s good mood is associated with purchases of higher-priced premium brands. In addition, retailers can use mood prediction to adapt the presentation of product information to fit customer mood, thus helping customers optimize their decisions. In a sensitivity analysis, we examine what accuracy of mood prediction could enable retailers to use the explored effects. 相似文献