Packet audio playout delay adjustment: performance bounds and algorithms

In packet audio applications, packets are buffered at a receiving site and their playout delayed in order to compensate for variable network delays. In this paper, we consider the problem of adaptively adjusting the playout delay in order to keep this delay as small as possible, while at the same time avoiding excessive “loss” due to the arrival of packets at the receiver after their playout time has already passed. The contributions of this paper are twofold. First, given a trace of packet audio receptions at a receiver, we present efficient algorithms for computing a bound on the achievable performance of any playout delay adjustment algorithm. More precisely, we compute upper and lower bounds (which are shown to be tight for the range of loss and delay values of interest) on the optimum (minimum) average playout delay for a given number of packet losses (due to late arrivals) at the receiver for that trace. Second, we present a new adaptive delay adjustment algorithm that tracks the network delay of recently received packets and efficiently maintains delay percentile information. This information, together with a “delay spike” detection algorithm based on (but extending) our earlier work, is used to dynamically adjust talkspurt playout delay. We show that this algorithm outperforms existing delay adjustment algorithms over a number of measured audio delay traces and performs close to the theoretical optimum over a range of parameter values of interest.     

VOIP动态缓出时延算法研究分析

在以包为单位进行数据传输合、语音应用程序(VOIP,Voice Over Internet Protocol)中,为了补偿数据包在网络传输中不可预知的网络传输延迟,在接收端首先必须把接收到的数据包缓存起来,缓存一定的时间再播放出来,以减少通话的抖动,得到比较满意的通话质量。文章主要研究动态缓出时延算法,力求使这个缓出时延尽可能小,同时尽可能减少包的丢失率。文章提出了一个有效动态缓出时延算法,该算法主要跟踪最近到达的数据包的网络传输时延求出其近似分布函数,并利用这些信息和延迟峰的侦测算法预测下一个语音峰的缓出时延。实验结果表明利用该算法可以在缓出时延和包丢失率之间达到最佳平衡,是一种理想、有效的算法。     

Adaptive playout scheduling and loss concealment for voice communication over IP networks

The quality of service limitation of today's Internet is a major challenge for real-time voice communications. Excessive delay, packet loss, and high delay jitter all impair the communication quality. A new receiver-based playout scheduling scheme is proposed to improve the tradeoff between buffering delay and late loss for real-time voice communication over IP networks. In this scheme the network delay is estimated from past statistics and the playout time of the voice packets is adaptively adjusted. In contrast to previous work, the adjustment is not only performed between talkspurts, but also within talkspurts in a highly dynamic way. Proper reconstruction of continuous playout speech is achieved by scaling individual voice packets using a time-scale modification technique based on the Waveform Similarity Overlap-Add (WSOLA) algorithm. Results of subjective listening tests show that this operation does not impair audio quality, since the adaptation process requires infrequent scaling of the voice packets and low playout jitter is perceptually tolerable. The same time-scale modification technique is also used to conceal packet loss at very low delay, i.e., one packet time. Simulation results based on Internet measurements show that the tradeoff between buffering delay and late loss can be improved significantly. The overall audio quality is investigated based on subjective listening tests, showing typical gains of 1 on a 5-point scale of the Mean Opinion Score.     

Playout buffering of speech packets based on a quality maximization approach

To combat jitter problems in voice streaming over packet networks, playout buffering algorithms are used at the receiver side. Most of the proposed solutions rely on two main operations: prediction of delay statistics for future packets; setting of the end-to-end delay so as to limit or avoid packet losses. In recent years, a new approach has been presented, which is based on using a quality model to evaluate the impact of both packet loss and delay on the voice quality. Such a model is used to find the buffer setting that maximizes the expected quality. In this paper, we present a playout buffering algorithm whose main contribution is the extension of the new quality-based approach to the case of voice communications affected by bursty packet losses. This work is motivated by two main considerations: most of IP telephony applications are characterized by bursty losses instead of random ones; the human perception of the speech quality is significantly affected by the temporal correlation of losses. To this purpose, we make use of the extensions proposed in the ETSI Tiphon for the ITU-T E-Model so as to incorporate the effects of loss burstiness on the perceived quality. The resulting playout algorithm estimates the characteristics of the loss process varying the end-to-end delay, weights the loss and the delay effects on the perceived quality, and maximizes the overall quality to find the optimal setting for the playout buffer. The experimental results prove the effectiveness of the proposed technique.     

实时语音的自适应回放算法

由于丢包和延时抖动的引入而使网络传输的实时语音质量让人难以接受，目前对丢包和延时抖动提出了很多的解决方案．但是却很少把这两者结合在一起进行研究。本文提出了一种新的自适应回放算法，通过监测接收和回放队列，结合丢包的自适应恢复技术，达到语音高质量的连续回放。实验证明，该算法能在严格的平均回放延时条件下努力减小由于超时而引起的丢包，获得较好的重建语音质量。     

Adaptive VoIP playout scheduling: assessing user satisfaction

Delay and packet loss dramatically affect the quality of voice-over-IP (VoIP) calls and depend on the playout buffer scheme implemented at the receiver. The choice of playout algorithm can't be based on statistical metrics without considering the perceived end-to-end conversational speech quality. The authors present a method for evaluating various playout algorithms that extends the E-model concept by estimating user satisfaction from time-varying transmission impairments. This article evaluates several playout algorithms and shows a correspondence between the authors' results and those obtained via statistical loss and delay metrics.     

A Garch-based adaptive playout delay algorithm for VoIP

Network delay, packet loss and network delay variability (jitter) are important factors that impact on perceived voice quality in VoIP networks. An adaptive playout buffer is used in a VoIP terminal to overcome jitter. Such a buffer-control must operate a trade-off between the buffer-induced delay and any additional packet loss rate. In this paper, a Garch-based adaptive playout algorithm is proposed which is capable of operating in both inter-talkspurt and intra-talkspurt modes. The proposed new model is based on a Garch model approach; an ARMA model is used to model changes in the mean and the variance. In addition, a parameter estimation procedure is proposed, termed Direct Garch whose cost function is designed to implement a desired packet loss rate whilst minimising the probability of consecutive packet losses occurring. Simulations were carried out to evaluate the performance of the proposed algorithm using recorded VoIP traces. The main result is as follows; given a target Packet Loss Rate (PLR) the Direct Garch algorithm produces parameter estimates which result in a PLR closer than other algorithms. In addition, the proposed Direct Garch algorithm offers the best trade-off between additional buffering delay and Packet Loss Rate (PLR) compared with other traditional algorithms.     

Delay reduction techniques for playout buffering

Receiver synchronization of continuous media streams is required to deal with delay differences and variations resulting from delivery over packet networks such as the Internet. This function is commonly provided using per-stream playout buffers which introduce additional delay in order to produce a playout schedule which meets the synchronization requirements. Packets which arrive after their scheduled playout time are considered late and are discarded. In this paper, we present the Concord algorithm, which provides a delay-sensitive solution for playout buffering. It records historical information and uses it to make short-term predictions about network delay with the aim of not reacting too quickly to short-lived delay variations. This allows an application-controlled tradeoff of packet lateness against buffering delay, suitable for applications which demand low delay but can tolerate or conceal a small amount of late packets. We present a selection of results from an extensive evaluation of Concord using Internet traffic traces. We explore the use of aging techniques to improve the effectiveness of the historical information and hence, the delay predictions. The results show that Concord can produce significant reductions in buffering delay and delay variations at the expense of packet lateness values of less than 1%     

Design and Experimental Evaluation of an Adaptive Playout Delay Control Mechanism for Packetized Audio for Use over the Internet

We describe the design and the experimental evaluation of a playout delay control mechanism we have developed in order to support unicast, voice-based audio communications over the Internet. The proposed mechanism was designed to dynamically adjust the talkspurt playout delays to the traffic conditions of the underlying network without assuming either the existence of an external mechanism for maintaining an accurate clock synchronization between the sender and the receiver during the audio communication, or a specific distribution of the audio packet transmission delays. Performance figures derived from several experiments are reported that illustrate the adequacy of the proposed mechanism in dynamically adjusting the audio packet playout delay to the network traffic conditions while maintaining a small percentage of packet loss.     

基于延迟预测的自适应媒体播放算法

针对AMP-Live模型中存在的问题,提出一种基于报文延迟预测的自适应媒体播放算法（NEWAMP）,采用未来信道和缓冲状态的预测值作为视频报文播放速率调整的依据,将速率变化的程度进一步细化,同时考虑应用要求的最大端到端延迟,提高算法性能,与传统播放算法相比,NEWAMP在保证报文因下溢和上溢而丢弃的概率足够小的前提下,缓冲延迟减小了约50%,而与普通AMP-Live方法相比,NEWAMP不仅减小了报文因下溢和上溢而丢弃的概率,还将缓冲延迟减小了约40%。实验结果证明了该算法的有效性。     

基于仿真分析的端到端最小包时延测量方法

端到端最小包时延作为反映端到端路径拓扑特征的基本指标得到广泛应用，但目前缺少对最小时延测量方法的研究。以仿真为手段定量分析了在不同路径长度下最小时延的可测性，并建立了反映探测包数量与路径长度关系的线性方程。以此为基础，提出一种基于仿真分析的最小时延测量方法。在互联网的实际测量表明该方法能以较小的测量开销获得较准确的最小时延测量结果。     

Hadoop平台下基于优化X-means算法的大数据聚类研究

针对WSNs中现有路由算法存在的各种不足,本文提出了一种基于占空比间隔优化的延迟约束路由算法。具体来说,在提出的算法中,首先,将端到端延迟分布估计为占空比间隔和潜在转发器数量的函数,在给定的网络模型和参数下,其分布可以近似地估计。然后,选择满足延迟约束成功率(Delay-Constrained Success Ratio,DCSR)要求的占空比间隔最大值,每个节点独立地调度其休眠和唤醒时间,发送端节点将数据包转发给潜在转发器中最先唤醒的节点,从而确保数据包以要求的概率即DCSR到达接收器,同时最大化占空比间隔；仿真实验结果表明,提出的路由算法不仅能够满足要求的DSCR,并在ETE延迟、数据包交付率和实际得到的DCSR方面都优于现有的先进算法。     

一种基于支持向量回归的互联网端到端延迟预测算法

互联网端到端延迟是指IP分组沿着互联网中一条确定路径进行传输的延迟,端到端延迟的精确预测是大量网络活动的基础,从网络协议设计到网络监测,再从确保端到端QoS性能到各种实时业务性能提升。提出一种新的端到端延迟的预测方法,主要贡献有:a)将互联网端到端延迟预测的问题转换为多元回归的预测问题,提出了基于多元回归的端到端延迟预测框架;b)采用支持向量回归SVR方法来求解端到端延迟的多元回归问题,提出了基于SVR的互联网端到端延迟预测算法。最后使用互联网采集的RTT数据来验证提出的算法,实验结果表明,提出的预测算法具有快速和精确特点,是一种适合实际应用的预测算法。     

Adaptive playout scheduling algorithm tailored for real-time packet-based voice conversations over wireless ad-hoc networks

The effective provision of real-time, packet-based voice conversations over multi-hop wireless ad-hoc networks faces several stringent constraints not found in conventional packet-based networks. Indeed, MANETs (mobile ad-hoc networks) are characterized by mobility of all nodes, bandwidth-limited channel, unreliable wireless transmission medium, etc. This environment will surely induce a high delay variation and packet loss rate impairing dramatically the user experienced quality of conversational services such as VoIP. Indeed, such services require the reception of each media unit before its deadline to guarantee a synchronous playback process. This requirement is typically achieved by artificially delaying received packets inside a de-jitter buffer. To enhance the perceptual quality the buffering delay should be adjusted dynamically throughout the vocal conversation.In this work, we describe the design of a playout algorithm tailored for real-time, packet-based voice conversations delivered over multi-hop wireless ad-hoc networks. The designed playout algorithm, which is denoted MAPA (mobility aware playout algorithm), adjusts the playout delay according to node mobility, which characterizes mobile ad-hoc networks, and talk-spurt, which is an intrinsic feature of voice signals. The detection of mobility is done in service passively at the receiver using several metrics gathered at the application layer. The perceptual quality is estimated using an augmented assessment approach relying on the ITU-T E-Model paradigm while including the time varying impairments observed by users throughout a packet-based voice conversation. Simulation results show that the tailored playout algorithm significantly outperforms conventional playout algorithms, specifically over a MANET with a high degree of mobility.     

基于路径探索的车载自组网贪婪路由算法

为了提高城市中车辆间信息的传输效率，实现车辆间的信息共享，针对目前车载自组网（VANET）中基于地理位置转发的多跳单播路由算法没有考虑城市场景的特殊性，不能很好地适应城市中车辆的高度动态性，使车辆之间的数据包可能在错误的路径上传播，造成丢包率较高、时延较长的问题，提出了一种新的基于路径探索的贪婪路由算法。首先，以数据包传输时延为标准，运用人工蜂群算法对数字地图规划出的多条路由路径进行探索。其次，优化数据包在车辆之间的多跳转发方式。仿真结果表明，与贪婪周边无状态路由（GPSR）协议和最大持续时间最小角的GPSR（MM-GPSR）改进算法比较，在最好情况下，所提算法的数据包到达率分别提高了13.81%和9.64%，而该算法的数据包平均端到端时延分别降低了61.91%和27.28%。     

联合车速–队列感知的路边单元分组调度随机优化

路边单元(RSU)是车联网中为其无线覆盖范围内过往车辆提供信息服务的基础设施,路边单元间的分组传输可通过移动车辆"存储–载带–转发"的方式进行,其传输过程中分组的端到端时延由源RSU缓存中的排队时延与车辆载带过程的传播时延两部分组成.为使RSU间分组传输过程中平均端到端时延最小化,本文提出一种联合车速–队列感知的路边单元分组调度随机优化方法,该方法根据源RSU缓存队列长度和经过源RSU覆盖范围的车辆速度状态作分组调度决策.通过马尔科夫决策(MDP)框架对分组传输过程中的平均排队时延和平均传播时延进行分析,建立一个非线性平均端到端时延最小化问题并求解.仿真结果表明,所提出的RSU分组调度随机优化方法可以显著降低RSU间分组传输过程中的平均端到端时延,并提高系统中分组传输的吞吐量.     

Delay and link utilization aware routing protocol for wireless multimedia sensor networks

Wireless Multimedia Sensor Networks (WMSNs) consist of networks of interconnected devices involved in retrieving multimedia content, such as, video, audio, acoustic, and scalar data, from the environment. The goal of these networks is optimized delivery of multimedia content based on quality of service (QoS) parameters, such as delay, jitter and distortion. In multimedia communications each packet has strict playout deadlines, thus late arriving packets and lost packets are treated equally. It is a challenging task to guarantee soft delay deadlines along with energy minimization, in resource constrained, high data rate WMSNs. Conventional layered approach does not provide optimal solution for guaranteeing soft delay deadlines due to the large amount of overhead involved at each layer. Cross layer approach is fast gaining popularity, due to its ability to exploit the interdependence between different layers, to guarantee QoS constraints like latency, distortion, reliability, throughput and error rate. The paper presents a channel utilization and delay aware routing (CUDAR) protocol for WMSNs. This protocol is based on a cross-layer approach, which provides soft end-to-end delay guarantees along with efficient utilization of resources. Extensive simulation analysis of CUDAR shows that it provides better delay guarantees than existing protocols and consequently reduces jitter and distortion in WMSN communication.     

一种双参数拓扑推测方法

针对采用单一性能参数推测网络拓扑结构算法的问题, 如有效性与网络负载有关以及测量节点性能参数时大多需要节点间时钟的同步等, 在现有的测量方法基础上, 提出了一种不需要节点间时钟同步可以测量端到端时延抖动和丢包相关性的紧接分组对序列测量方法, 同时设计了一种综合端到端时延抖动和丢包相关性的双参数拓扑推测算法, 该算法能够适应不同的网络负载环境。最后通过NS-2仿真实验验证了该算法的有效性和准确性。     

面向异构业务的基于数据包优先权的组播算法

由于基于IEEE 802.15.4标准的无线传感网络WSNs(Wireless Sensor Networks)未引用业务优先机制,确保异构业务的服务质量QoS(Quality of Service)存在挑战.为此,提出面向异构业务的基于数据包优先权的组播算法POMT(Priority-Oriented Multicast Transmission algorithm for heterogeneous traffic).POMT算法通过减少队列、媒体接入控制MAC(Medium Access Control)和传输时延,减少端到端传输时延,并为优先数据包提供可靠的组播传输.基于异构业务类型,POMT算法选择不同的信道竞争窗口尺寸.此外,POMT算法利用两类确认包和重传机制,保证数据包传输的可靠性.实验数据表明,相比于传统的CSMA/CA策略,POMT算法控制了端到端传输时延和提高了数据包传递率,并降低了碰撞概率.     

一种用于无线网络中实时业务的跨层调度算法

就同时包含了有线链路和无线链路的异构网络上的实时应用,提出了一种满足其端到端服务质量(QoS)需求的无线网络MAC(media access control)层调度算法(real-time cross-layer scheduling algorithm for real-time application,简称RTCLA).该算法采用跨层的思想,结合了自适应调制编码(adaptive modulation and coding,简称AMC)技术和选择性自动请求重传(selective repeat-automatic repeat request,简称SR-ARQ)技术,在满足应用的系统误包率(packet error rate,简称PER)要求、尽可能减少基站中等待超时分组数目的前提下,提高系统吞吐性能和频谱利用率.通过仿真来验证算法分组超时率、平均系统有效吞吐率和公平性3个方面的性能,并与改进的比例公平算法(modifiedpro portional fair,简称MPF)、最早到期优先(earliest deadline first,简称EDF)和改进的最大加权延时优先(modified largest weighted delay first,简称M-LWDF)等3种广泛使用的算法进行了比较.仿真结果还表明,综合考虑实时应用的严格时延要求和无线网络资源稀缺以及信道的时变特性,RTCLA更适合于对时延敏感的实时应用,尤其是分组超时率性能方面表现突出.此外,仿真结果还表明,RTCLA在稳定性方面的表现与其他3种算法基本相同.