Speaker diarization is the problem of determining “who spoke when” in an audio recording when the number and identities of the speakers are unknown. Motivated by applications in automatic speech recognition and audio indexing, speaker diarization has been studied extensively over the past decade, and there are currently a wide variety of approaches – including both top-down and bottom-up unsupervised clustering methods. The contributions of this thesis are to provide a unified analysis of the current state-of-the-art, to understand where and why mistakes occur, and to identify directions for improvements.In the first part of the thesis, we analyze the behavior of six state-of-the-art diarization systems, all evaluated on the National Institute of Standards and Technology (NIST) Rich Transcription 2009 evaluation dataset. While performance is typically assessed in terms of a single number – the diarization error rate (DER) – we further characterize the errors based on speech segment durations and their proximity to speaker change points.

关键词：语音识别和音频索引；扬声器系统；改善

查看摘要 索取原文[104页]

支付开辟互联网企业向金融发展方的通道。“支付”是指消费者通过银行或支付平台连接付款给商家的行为，完成交易。互联网金融模式下的支付方式以网络、移动支付为基础来转移货币价值以清偿债权债务关系。支付在促成电商实现交易的同时，其沉淀资金功能也自然推动其向金融业务发展，货币基金的销售只是序幕拉开，一旦客户通过移动网络购买金融产品习惯形成，零售金融生态将整体改变。

关键词：支付；互联网；第三方支付；移动支付

查看摘要 索取原文[105页]

The drive towards richer, more interactive content places increasingly stringent latency requirements on datacenters. A critical component of meeting these is ensuring that the network responds agilely to congestion, bounding network latency and improving high-percentile flow completion times. We propose a new approach to rapidly detecting and responding to congestion. We introduce FastLane, a congestion signaling mechanism that allows senders to respond more quickly. By delivering signals to senders with high probability and low latency, FastLane allows them to retransmit packets sooner, avoiding resource-wasting timeouts. It also enables senders to make more informed decisions by differentiating between out-of-order delivery and packet loss. We demonstrate through simulation and implementation that FastLane reduces high-percentile flow completion times by over 80% by effectively managing congestion hot-spots. These benefits come at minimal cost—FastLane consumes no more than 2% of bandwidth and 5% of buffers.

关键词：拥塞信号机制；拥塞管理；响应敏捷；

查看摘要 索取原文[15页]

Ray tracing allows for physically-accurate renderings of various phenomena, producing a highquality image. Because of its computational complexity, ray tracing is typically reserved for offline rendering, where each image is allowed virtually unlimited time to render. Much work has been done to accelerate ray tracing to enter the interactive domain, requiring each image to be produced in less than a few seconds. Current ray tracers can interactively produce images with only a limited subset of their possible offline effects. My work with Professor Ravi Ramamoorthi and Soham Mehta focuses on physical phenomena that are too computationally expensive to render interactively. We focus on two effects: soft shadows cast by area lights and di?use indirect lighting, but the principles behind our work can be applied to various other phenomena.

关键词：物理渲染；筛选；射线追踪

查看摘要 索取原文[25页]

Physical Therapy is a branch of rehabilitative health that uses specially designed exercises and equipment to help patients regain or improve their physical abilities. Researchers have explored the use of software based rehabilitation tools based on video game consoles like Nintendo Wii Fit and Microsoft Kinect to provide remote rehabilitation facilities to patients. We propose a Kinect based Physical Therapy Application that guides patients to perform exercises and assists therapists to monitor as well as teach the specially designed exercises to patients. The application includes an Automated Exercise Generator for therapists to de ne exercises, an Automated Gesture Recognition and Tracking System to track and guide the patients while they perform the exercises and a Visual Feedback System for patients to correct the position and movement of their Joints. In this paper, we investigate how to enable continuous tracking of patients for pre-authored physiotherapy exercises. We introduce a state-machine-based approach that tracks a patient's progress and provides continuous feedback indicating whether the patient is doing an exercise correctly or not.

关键词：物理治疗；康复工具；自动手势识别；跟踪系统

查看摘要 索取原文[29页]

This thesis introduces and explores the idea of \user-guided inverse 3D modeling" — an interactive approach to shape construction and redesign that extracts well-structured, parameterized, procedural descriptions from unstructured, hierarchically  at input data, such as point clouds, boundary representation meshes, or even multiple pictorial views of a given inspirational prototype. This approach combines traditional \forward" 3D modeling tools with a system of user-guided extraction modules and optimization routines. With a few cursor strokes users can express their preferences regarding the type of modeling primitives to be used in a particular area of the given prototype to be approximated, and they can also select the degree of parameterization associated with each modeling routine. The results are then pliable, structured descriptions that are well suited to implement the particular design modications intended by the user.

关键词：用户引导逆3D建模；用户交互；3D建模工具

查看摘要 索取原文[157页]

A fundamental problem in computer vision is that of inferring the intrinsic, 3D structure of the world from flat, 2D images of that world. Traditional methods for recovering scene properties such as shape, reflectance, or illumination rely on multiple observations of the same scene to overconstrain the problem. Recovering these same properties from a single image seems almost impossible in comparison—there are an infinite number of shapes, paint, and lights that exactly reproduce a single image. However, certain explanations are more likely than others: surfaces tend to be smooth, paint tends to be uniform, and illumination tends to be natural.We therefore pose this problem as one of statistical inference, and define an optimization problem that searches for the most likely explanation of a single image. Our technique can be viewed as a superset of several classic computer vision problems (shape-from-shading, intrinsic images, color constancy, illumination estimation, etc) and outperforms all previous solutions to those constituent problems.

关键词：场景属性；经典计算机视觉问题；解决方案

查看摘要 索取原文[20页]

Matrix multiplication is one of the most fundamental algorithmic problems in numerical linear algebra, distributed computing, scienti c computing, and high-performance computing. Parallelization of matrix multiplication has been extensively studied (e.g., [21, 12, 24, 2, 51, 39, 36, 23, 45, 61]). It has been addressed using many theoretical approaches, algorithmic tools, and software engineering methods in order to optimize performance and obtain faster and more ecient parallel algorithms and implementations. To design ecient parallel algorithms, it is necessary not only to load balance the computation, but also to minimize the time spent communicating between processors.

关键词：通信模式；矩阵乘法；递推算法；数字线性代数；分布式计算；

查看摘要 索取原文[91页]

The proliferation of large clusters supporting online web workloads or large compute-intensive jobs has made cluster power management very important [1]. An analysis of utilization traces of production clusters reveal that a majority of them have a scope for (a) under-provisioning of electrical support infrastructure, leading to savings in capital expenditure, and (b) energy savings, leading to savings in operational expenditure; both with minimal impact on average job performance. Existing software techniques which tackle either of these problems have seen scant adoption because they do not address key problems and constraints relevant in production clusters.In this thesis, we first investigate possible reductions in cluster power infrastructure provisioning. It is possible that the lower provisioned power level is exceeded due to software behaviors on rare occasions and could cause the entire cluster infrastructure to breach the safety limits. A mechanism to cap servers to stay within the provisioned budget is needed, and processor frequency scaling based power capping methods are readily available for this purpose。

关键词：生产集群；电源管理；服务器

查看摘要 索取原文[71页]

In 2001, the International Civil Aviation Organization (ICAO), an agency of the United Nations with international aviation oversight, adopted a new standard in Annexes 6 (Operation of Aircraft), 11 (Air Traffic Services), and 14 (Aerodromes), requiring that all 192 contracting states establish safety management system (SMS) requirements. According to ICAO, "safety is increasingly viewed as the outcome of the management of certain organizational processes, which have the objective of keeping the safety risks of the consequences of hazards in operational contexts under organizational control.

关键词：电子信息；安全管理系统；经验

查看摘要 索取原文[4页]