聋人手语动漫教学系统的设计

聋人手语动漫教学系统的设计从研究和快速发展聋人手语并使其成为一种语言的角度出发,汲取聋人语言教学中的理论研究成果,运用分词和三维动画技术实现集翻译、教学和训练评价于一体的手语教学系统。     

自然手语翻译器系统设计和实现

为了更好的服务好聋人群体,社会做了很多努力。但手语普及和学习的困难,影响了服务的实际效果。为了解决这个问题,文章提出了一套聋人自然手语资源建设、服务平台开发和手机终端APP实现的综合方案。该方案在电子化自然手语资源的基础上,综合运用了自然语言处理、知识管理、3D动画建模、移动互联技术、Android开发等技术,开发了聋人自然手语翻译器。整个系统由自然手语生成子系统、自然手语资源管理子系统和手语展示客户端组成。自然手语生成子系统包括自然语言处理、自然手语动画自动生成等模块;自然手语资源管理子系统完成对自然手语相关资源的管理,包括自然语言语义知识、自然手语转换语义知识、手语资源等。该系统经济实用,应用广泛,使用便捷,前景广阔,可用于手语学习、手语虚拟主持人,有助于手语的学习和推广,促进和谐社会的建设与发展。     

TelecomI+D04: Speech into Sign Language Statistical Translation System for Deaf People

This paper presents a set of experiments used to develop a statistical system from translating speech to sign language for deaf people. This system is composed of an Automatic Speech Recognition (ASR) system, followed by a statistical translation module and an animated agent that represents the different signs. Two different approaches have been used to perform the translations: a phrase-based system and a finite state transducer. For the evaluation, the followings figures have been considered: WER (Word Error Rate), BLEU and NIST. The paper presents translation results of reference sentences and sentences from the Automatic Speech Recognizer. Also three different configurations have been evaluated for the Speech Recognizer. The best results were obtained with the finite state transducer, with a word error rate of 28.21% for the reference text, and 29.27% using the ASR output.     

INDAX: An Operational Interactive Cabletext System

INDAX is a local area home information system developed by Cox Cable Communications, Inc. for the delivery of videotex services to residential Customers. The large bandwidth provided by this medium allows integration of one-way (teletext) with two-way (videotext) transmissions into a cohesive delivery vehicle. As a data delivery mechanism, INDAX is well suited to many different types of servies. Among the earliest service offerings are generalized information retrieval and transaction services such as home banking and shopping. Implementation and traffic characteristics of these services are described in the following sections. In addition, INDAX supports interactive entertainment options such as opinion polling in conjunction with the standard entertainment programming. Status monitoring and control services such as security monitoring and energy management can also be delivered via INDAX. While the traffic model described is oriented towards a residential service, the modular system architecture readily supports differing traffic statistics by the addition of communications and processing modules.     

Sign Language by Cellphone

In the past, engineers working on technology to aid the deaf had focused primarily on hearing devices, such as hearing aids and cochlear implants, but recently they?ve been getting into what?s known as deaf technology: applications designed to make the day-to-day lives of the deaf and hearing-impaired easier.     

一种面向交通标志识别系统的图像识别算法

目前各类面向交通标志识别系统的机器算法大多存在计算复杂度高、实时性差等问题,文中基于ELM模型,加入改进的PCA方法,提出了一种面向交通标志识别系统的PCA-ELM图像识别算法。该算法依次通过HOG特征的提取、改进的PCA方法降维、ELM模型的特征训练,实现交通标志图像的识别。经过实验测试,发现该算法能够较好地兼顾识别率和计算复杂度,符合交通标志识别系统图像识别的准确性与实时性要求,具有一定的实用价值。     

手语文本自动分词的设计与实现

手语是我国听障人重要交流之一,手语文本自动分词系统对听障人的政治、文化、生活的发展有着重要意义。研发了手语文本自动分词系统,这是在汉语切分的基础上针对手语特点进行手语切分,而且是利用计算机对文本里面的内容进行自动分词。该系统包括基本的自动分词方法、歧义的处理等基本模块,每一环节互相协助,互相依赖,共同决定该系统的价值、质量和应用水平。     

基于手语表达内容与表达特征的手语识别技术综述

手语识别(SLR)技术是打破听障人群与健听人群间交流壁垒的重要技术手段。该文综述了近几年的手语数据集、评价指标以及手语识别方法。首先,系统梳理了手语数据集并分析了手语识别方法的数据集发展方向。其次,详细介绍了手语识别方法的评价指标。然后,根据手语表达内容、手语识别方法所采用的特征分类总结分析了孤立词手语识别方法与连续语句识别方法、仅依靠手部特征的手语识别方法与多特征融合的手语识别方法。最后探讨了手语识别技术面临的挑战及其发展方向。     

残疾人手语交流辅助系统手语识别和翻译

为了使聋哑人与更多不懂手语的人自然地交流,本作品将手语翻译成文字和语音,利用Microsoft Kinect记录手语手势的三维坐标,通过机器学习和优化算法,在Intel Atom平台上实现了手语翻译.     

融合注意力机制和连接时序分类的多模态手语识别

连续手语识别的难点之一是手语数据中存在时空维度的冗余信息,以及手语数据与给定标签序列的对齐问题。因此,本文提出一种融合注意力机制和连接时序分类的连续手语识别模型,可以提取手语数据中彩色和深度视频片段的短期时空特征以及手部运动轨迹特征,将三种模态的特征融合后使用空间注意力加权并按照时间顺序输入到双向长短期记忆网络中进行时序建模,以获取长期时空特征,最后利用融合注意力机制和连接时序分类模型的解码网络以端到端的方式实现连续手语的准确识别。本模型在自行采集的中国手语数据集上进行测试,得到了高达0.935的准确率。      

一种经济实用的远程交互式有线电视会议系统

该方案借助于原有有线电视传输网络、设备，建立了一种经济实用的远程交互式有线电视系统，为社会各界提供了较为满意的电视会议服务，以少量的投资盘活了有线电视网大量闲置资源，比目前基于H.320/H.323等标准的传统电视会议系统节约投资70％以上。     

基于时空注意力网络的中国手语识别

手语识别广泛应用于聋哑人与正常人之间的交流中。针对手语识别任务中时空特征提取不充分而导致识别率低的问题,提出了一种新颖的基于时空注意力的手语识别模型。首先提出了基于残差3D卷积网络(Residual 3D Convolutional Neural Network,Res3DCNN)的空间注意力模块,用来自动关注空间中的显著区域；随后提出了基于卷积长短时记忆网络(Convolutional Long Short-Term Memory,ConvLSTM)的时间注意力模块,用来衡量视频帧的重要性。所提算法的关键在于在空间中关注显著区域,并且在时间上自动选择关键帧。最后,在CSL手语数据集上验证了算法的有效性。     

基于多特征SVMs分类器的手语识别

在手语识别的研究中,手语图像全局特征与局部特征相融合的方法可以准确地表征手语手势特征.本文在不进行图像分割的情况下提取手语图像的7Hu不变矩特征量、SIFT等多种特征,在进行了多特征融合后,分别采用基于线性核函数的SVMs和基于径向基核函数的SVMs作为分类器进行手语识别,单个手语字母最好识别率可达到99.4872%,平均识别率95.556%.     

基于深度学习的手语识别综述

手语识别涉及计算机视觉、模式识别、人机交互等领域,具有重要的研究意义与应用价值。深度学习技术的蓬勃发展为更加精准、实时的手语识别带来了新的机遇。该文综述了近年来基于深度学习的手语识别技术,从孤立词与连续语句两个分支展开详细的算法阐述与分析。孤立词识别技术划分为基于卷积神经网络(CNN)、3维卷积神经网络(3D-CNN)和循环神经网络(RNN) 3种架构的方法;连续语句识别所用模型复杂度更高,通常需要辅助某种长时时序建模算法,按其主体结构分为双向长短时记忆网络模型、3维卷积网络模型和混合模型。归纳总结了目前国内外常用手语数据集,探讨了手语识别技术的研究挑战与发展趋势,高精度前提下的鲁棒性和实用化仍有待于推进。

     

A Sign-Component-Based Framework for Chinese Sign Language Recognition Using Accelerometer and sEMG Data

Identification of constituent components of each sign gesture can be beneficial to the improved performance of sign language recognition (SLR), especially for large-vocabulary SLR systems. Aiming at developing such a system using portable accelerometer (ACC) and surface electromyographic (sEMG) sensors, we propose a framework for automatic Chinese SLR at the component level. In the proposed framework, data segmentation, as an important preprocessing operation, is performed to divide a continuous sign language sentence into subword segments. Based on the features extracted from ACC and sEMG data, three basic components of sign subwords, namely the hand shape, orientation, and movement, are further modeled and the corresponding component classifiers are learned. At the decision level, a sequence of subwords can be recognized by fusing the likelihoods at the component level. The overall classification accuracy of 96.5% for a vocabulary of 120 signs and 86.7% for 200 sentences demonstrate the feasibility of interpreting sign components from ACC and sEMG data and clearly show the superior recognition performance of the proposed method when compared with the previous SLR method at the subword level. The proposed method seems promising for implementing large-vocabulary portable SLR systems.     

虚拟演播室互动控制系统

本文介绍了上海文广新闻传媒集团（SMG）虚拟演播室互动控制系统的结构、模块组成、工作流程以及动画控制效果,举例说明了虚拟互动控制系统在实际节目中的多种应用及节目效果,并介绍了虚拟互动控制系统将来的发展。     

数据挖掘在智能教学系统中的应用

智能教学系统以其绝对的优势已经为大多数人所接受,但在使用他的过程中也存在着一些不足。如何更好地满足用户的个性化、主动性及知识库数据的重组,提出数据挖掘技术来解决这一系列问题,以期智能教学系统为使用者提供更佳的服务。     

Ultra-Robust and Sensitive Flexible Strain Sensor for Real-Time and Wearable Sign Language Translation

Flexible strain sensors with high sensitivity and high mechanical robustness are highly desirable for their accurate and long-term reliable service in wearable human-machine interfaces. However, the current application of flexible strain sensors has to face a trade-off between high sensitivity and high mechanical robustness. The most representative examples are micro/nano crack-based sensors and serpentine meander-based sensors. The former one typically shows high sensitivity but limited robustness, while the latter is on the contrary. Herein, ultra-robust and sensitive flexible strain sensors are developed by crack-like pathway customization and ingenious modulation of low/high-resistance regions on a serpentine meander structure. The sensors show high cyclic stability (10 000 cycles), strong tolerance to harsh environments, high gauge factor (>1000) comparable with that of the crack-based sensor, and fast response time (<58 ms). Finally, the sensors are integrated into a wearable sign language translation system, which is wireless, low-cost, and lightweight. Recognition rates of over 98% are demonstrated for the translation of 21 sign languages with the assistance of machine learning. This system facilitates achieving barrier-free communication between signers and nonsigners and offers broad application prospects in gesture interaction.