Designing assistive technologies for medication regimes in care settings

This paper presents some early design work of the Care in the Digital Community research project begun under the EPSRC IRC Network project Equator. Gaining a comprehensive understanding of user requirements in care settings poses interesting methodological challenges. This paper details some methodological options for working in the domestic domain and documents the translation of research into design recommendations. We report on the importance of medication issues in a hostel for former psychiatric patients and present an early prototype of a medication manager designed to be sensitive to the particular requirements of the setting.     

语音处理技术在语言学习中的应用

语音处理技术应用于语言的学习,可以改进、加强和丰富传统的语言学习方法,有利于提高学习效率;然而,如何有效地利用这些技术,建立各种计算机辅助语言学习 ＣＡＬＬ（Ｃｏｍｐｕｔｅｒ－Ａｉｄｅｄ Ｌａｎｇｕａｇｅ　Ｌｅａｒｎｉｎｇ）系统,是当前语音处理技术研究发展的一个重要方向。该文通过对传统的语言教学方法中所涉及到的主要因素的分析,研究了语音处理技术在语言学习系统中应用的主要层次和方法,以及使其更有效等方面的问题。     

蒙古语语音识别系统语言模型的设计

目前,蒙古语语音识别的研究尚处于空白阶段,因此蒙古语语音识别系统的研究与开发具有重要意义。而语言模型的确立是语音识别系统中最重要的环节之一。本文根据自己的实践,通过实验的方法最终确立了蒙古语、大量词汇语音识别系统中适宜的语言模型。     

基于单边自相关序列的语音特征及其在带噪语音识别中的应用

提出了一种抗噪声语音特征。首先计算语音信号单边自相关序列的差分序列,再计算该差分序列的线性预测系数,进一步求出例说系数。实验证明,传统的线性预测例谱系数和边自相关序列的一性预测倒谱数相比,采用单边自相关序列差分序列的线性预测倒谱系数作为语音信号的特征矢量,可以提高语音识别系统对带噪音语音的识别率。     

A commercial perspective on universal access and assistive technology: towards implementation

This paper presents one companys perspective on the implementation and provision of universal access (UA) and assistive technology in an industrial setting. The paper addresses the need to provide accessible work-places and also accessible customer services, from legal, commercial and ethical standpoints. The company in question, Royal Mail, is one of the UKs largest employers and service providers and so has been able to gather employee and customer data often unavailable to smaller organisations.     

Involving domain experts in assistive technology research

Teams engaging in assistive technology research should include expertise in the domain of disability itself, in addition to other areas of expertise that are more typical in human–computer interaction (HCI) research, such as computer science and psychology. However, unexpected problems can arise when HCI researchers do not adequately plan the involvement of domain experts in a research project. Although many research teams have included domain experts when designing assistive technologies, there has been little work published on how to best involve these experts in the research process. This paper is a first step towards filling that void. Based on the authors’ own experiences involving domain experts in research, as well as those documented in the literature, five types of domain experts and three broad roles that domain experts can play are identified, and five guidelines for their involvement are presented. This analysis will be useful to anyone in the assistive technology and universal accessibility communities, especially those who are in the early stages of conducting research in this area. It is intended to lay the foundation of best practices for involving domain experts in assistive technology research.     

视频处理与压缩技术

视频处理与压缩是多媒体计算与通信领域的核心主题之一,是连接视频采集传输和视觉分析理解的关键桥梁,也是诸多视频应用的基础。当前“5G+超高清+AI”正在引发多媒体计算与通信领域的新一轮重大技术革新,视频处理与压缩技术正在发生深刻变革,亟需建立视频大数据高效紧凑表示理论和方法。为此,学术研究机构和工业界对视频大数据的视觉表示机理、视觉信息紧凑表达、视频信号重建与恢复、高层与低层视觉融合处理方法及相应硬件技术等前沿领域进行了广泛深入研究。本文从数字信号处理基础理论出发,分析了当前视频处理与压缩领域的热点问题和研究内容,包括基于统计先验模型的视频数据表示模型及处理方法、融合深度网络模型的视频处理技术、视频压缩技术以及视频压缩标准进展等领域。详细描述了视频超分辨率、视频重建与恢复、视频压缩技术等领域面临的前沿动态、发展趋势、技术瓶颈和标准化进程等内容,对国际国内研究内容和发展现状进行了综合对比与分析,并展望了视频处理与压缩技术的发展与演进方向。更高质量视觉效果和高效率视觉表达之间将不再是单独研究的个体,融合类脑视觉系统及编码机理的视频处理与压缩技术将是未来研究的重要领域之一。     

基于C++ Builder的田野语音采集系统的设计与实现

本文结合我国少数民族语言濒危现象,以C++ Builder 6.0为开发工具,设计开发了田野语音采集系统,用于保护语言文化遗产。该系统主要功能包括:数据管理、音频设置与分析、快速采集、普通采集、系统管理、数据库的备份与恢复等。相对其他方言采集工具,该系统能有效提高语音采集的质量和效率,便于对语音数据库进行科学管理,具有一定的应用价值。     

Mixture reality-based assistive system for visually impaired people

Individuals with visual impairments often face challenges in their daily lives, particularly in terms of independent mobility. To address this issue, we present a mixed reality-based assistive system for visually impaired individuals, which comprises a Microsoft Hololens2 device and a website and utilizes a simultaneous localization and mapping (SLAM) algorithm to capture various large indoor scenes in real-time. This system incorporates remote multi-person assistance technology and navigation technology to aid visually impaired individuals. To evaluate the effectiveness of our system, we conducted an experiment in which several participants completed a large indoor scene maintenance task. Our experimental results demonstrate that the system is robust and can be utilized in a wide range of indoor environments. Additionally, the system enhances environmental perception and enables visually impaired individuals to navigate independently, thus facilitating successful task completion.     

一种精确检测语音端点的方法

端点检测是语音识别中的一项关键技术,端点检测的准确性对语音识别的性能有很大影响,特别是对端点检测比较敏感的语音识别算法。本文引用窗长动态变化的端点检测技术,并将传统的双门限端点检测算法和窗长动态改变的端点检测技术结合起来用于语音端点检测。大量实验表明这种技术可以比较精确的检测语音端点,特别是地检测语音的起始端点中有很大的优势。使用改进后的语音端点检测技术,可以有效地提高语音识别率。     

Generating American Sign Language animation: overcoming misconceptions and technical challenges

Misconceptions about the English literacy rates of deaf Americans, the linguistic structure of American Sign Language (ASL), and the suitability of traditional machine translation (MT) technology to ASL have slowed the development of English-to-ASL MT systems for use in accessibility applications. This article traces the progress of a new English-to-ASL MT project targeted to translating texts important for literacy and user-interface applications. These texts include ASL phenomena called “classifier predicates.” Challenges in producing classifier predicates, novel solutions to these challenges, and applications of this technology to the design of user-interfaces accessible to deaf users will be discussed.     

Mechanisms for actuated assistive hip orthoses

Mobility is often a central problem for people having muscle weaknesses. The need for new devices to assist walking and walk related activities is therefore growing. Lower limb actuated orthoses have already proven their positive impact with paraplegic patients and are potentially promising for assisting people with weak muscles. However, the transfer from the existing systems of mobilization towards assistance implies several technical challenges as the seamless integration and the reduction of power consumption. In this paper two assistive orthoses which use different types of actuation mechanisms are presented and discussed. The first one is based on a ball screw and an excavator-like mechanism while the second one is based on a double differential actuation. Their technical capabilities are compared and contextualized for diverse activities. Objective characteristics such as the range of motion of the devices, the transparency, the maximal torque that they can provide or the RMS torque during cyclic trajectories are compared to point out which device is better adapted for specific situations.     

汉语文语转换及语音编解码的基于DSP的综合实时处理

提出了汉语文语转换和语音编解码的基于DSP的实时综合处理的思想。介绍了实时综合处理的基于DSP的硬件与软件实现。文章介绍的基于DSP的实时综合处理具有以下几个方面的特点：(1)在单片DSF和不超过IMB的DSP最小系统上实现了一个任意文本的汉语文语转换系统;(2)为提高语音合成的自然度,提供了灵活的语音定制功能;(3)根据通信信道容最大小,实现可灵活选择的采甩语音合成方式的语音通信和语音编码方式的语音通信;(4)基于DSP的实时综合处理的在线重构;(5)基于RS232的通用异步串口的包括命令解释引擎、合成引擎、编码引擎等的模块化DSP软件结构。     

Personal storytelling: Using Natural Language Generation for children with complex communication needs,in the wild…

This paper describes a Natural Language Generation system (NLG), How was School Today? that automatically creates a personal narrative from sensor data and other media (photos and audio). It can be used by children with complex communication needs in schools to support interactive narrative about personal experiences. The robustness of story generation to missing data was identified as a key area for improvement in a feasibility study of the system at a first special needs school. This paper therefore suggests three possible methods for generating stories from unstructured data: clustering by voice recording, by location, or by time. Clustering based on voice recordings resulted in stories that were perceived as most easy to read, and to make most sense, by parents in a quantitative evaluation. This method was implemented in the live system, which was developed and evaluated iteratively at a second special needs school with children with different usage profiles. Open challenges and possibilities for NLG in augmented and alternative communication are also discussed.     

电话语音识别系统

讨论了一个典型的电话语音识别系统的设计与实现。首先提出了系统的整体模型,之后给出了系统的整体结构和系统的主要模块。较详细地介绍了声学层识别的速度优化和电话信道补偿问题,以及语言模型的容错算法和基于语义依存关系的容错理解模型,并对系统各层次模块性能进行了实验测试。     

一个基于SGML的面向语音合成的标记语言的分析

讨论了语音合成系统,在输入文档中加入注释标记的重要性和必要性;以及说明迷了实现合成器之间的兼容,便于它们与其它系统集成,而制定一个统一的文本民注释方案的重要性。     

一款可编程语音处理器的设计与应用

为了提高通信系统的保密性,降低制造成本,需要进行专用处理器的设计.该文基于SELP(Sinusoidal Excitation Linear Prediction)算法模型原理,设计了一款高质量多速率语音专用处理器芯片.芯片使用可重构体系结构和超长指令字系统设计方法,将复杂度高的子程序进行优化,能够显著提高指令并行度.仿真结果表明:在该芯片上实现语音压缩编码算法,执行效率高于相同工艺水平的通用数字信号处理器,并保持原有编码质量.该处理器能够实现多种类型的语音压缩算法,使语音算法可以达到高保密性、低复杂度和易开发性.     

一种数字语音处理研究平台的设计

设计了一种支持多视图和多种数据接口的研究平台。该平台采用了模块组合式的体系结构，使得新的语音处理算法能够便捷地加入到平台中。所有模块被分为内部模块和外部模块。内部模块集成语音的数据接口和可视化功能，外部模块则实现语音的分析功能。该平台采用了纵版的显示方式，不同算法得到的结果被垂直排列显示在一个窗口内，有利于对比分析，还内建了支持基于XML的语音标注格式，能够被直接应用到语料库建设和语音分析等领域。     

信息技术与语文教学整合的研究

信息技术与语文教学的整合是真正意义上的语文教学革命,它改变了教学信息的传递,使教学信息的线性传递方式转变为非线性传递方式。用多种媒体形式的信息组织语文教学,使得教学效果更加直观生动,从而与以往的语文教学有很大的不同。信息技术与语文教学的整合强调寓教于乐,它具有媒体的多样性、交互性、集成性能更好地培养学生自主探索的能力,学生的语文素养提高了,听、说、读、写等语文教学内容在信息技术的支持下获得了新的发展。