一种高效的Internet上语音包丢失恢复技术

提出了一种高效的Internet上语音包丢失恢复技术,采用了基于奇偶校验码的加载式前向纠错编码(PPFEC)技术,可以在网络存在丢包情况下无损恢复大部分丢失帧信息。此外,本文将PPFEC技术与语音编码的错误隐藏技术相结合,提出了一种基于保护重要信息的FEC编码,得到更优的解码质量和带宽的性能折衷。客观音质实验表明,本文方法在各种丢包率情况下表现出良好的效果。     

突发大时延下的IP语音缓冲算法

当网络中存在突发大时延时,就会出现极大丢包率或极大端到端时延的情况,从而难以获得好的语音质量。对于这个问题,提出针对突发大时延存在下的自适应语音缓冲算法。算法通过控制语音包在语音缓冲队列中的位置来控制语音包的播放时间,从而可以尽量减小语音裂缝(Gap)的出现。算法将突发大时延存在下的最大丢包率可以扩大到20％,而一般的预测算法只能容忍5-10％的最大丢包率。通过基于听觉模型的客观音质评价(PESQ)仿真计算,以及实际应用表明本文的算法对有突发大时延存在的网络中的语音通信质量有一定的改善作用。     

一种基于RTP减少包丢失的控制算法及其在VoIP中的应用

本文首先考虑丢包率的控制方案，然后讨论VoIP网关对丢包率的监测，最后在简单带宽调整算法的基础上提出一种改进的控制算法——传输速率自适应调整算法，并将算法运用到VoIP系统中，提出一种自适应变速率语音编码器，来控制语音包的丢失。     

基于深度神经网络的语音增强研究

由于目前语音增强方法或算法难以对语音频谱在时频域上的结构化信息进行有效建模和利用。然而,深度学习中的RBM、DNN等模型擅长对数据中的结构化信息进行建模,而且具有从数据的低层结构化信息提取更高层的结构化信息的能力。基于分类深度神经网络的语音增强,该方法对于低信噪比非平稳语音增强可得到高可懂度的增强语音,但语音音质损失严重。基于DNN的最小均方误差回归拟合语音增强方案,该语音增强方案还说明大语音数据训练能保证DNN较充分学习到噪声语音谱和干净语音谱之间复杂的非线性关系。     

基于1D-Concatenate的信道估计DNN模型优化方法

为提高DNN模型在无线通信中信道估计精度,提出一种基于1D-Concatenate的信道估计DNN模型优化方法。该方法将Concatenate进行一维（1D）数据转换,以跳跃连接的方式引入DNN模型,抑制梯度消失问题,运用1D-Concatenate恢复网络训练过程中丢失的数据特征,提高DNN信道估计精度。为验证优化方法的有效性,选取较典型的基于DNN的无线通信信道估计模型进行对比仿真实验。实验结果表明,本文提出的优化方法对已有DNN模型的估计增益提升可达77.10%,在高信噪比下信道增益提升可达3 dB。该优化方法能有效提高DNN模型在无线通信中的信道估计精度,特别是高信噪比下提升效果显著。     

因特网中分组语音传输的丢包恢复技术浅述

在基于IP网络下进行语音通信的过程中，不可避免地会遇到数据包丢失现象，极大地影响了传输服务的质量。对此问题展开讨论，讲述了丢包的原因，对当前普遍采用的几种丢包恢复技术进行了介绍，通过比较提出了自己的观点。     

一种网络传输中实时音频数据丢包恢复的方法

为解决实时音频传输中数据丢包恢复延时长的问题,基于网络环境中音频相关性理论提出了一种实时音频数据丢包恢复的方法.该方法充分利用了语音信号帧间的相关性,并结合均值滤波与多项拟合算法,较好地实现了丢包数据的实时恢复.计算机仿真结果表明,该方法能够准确恢复丢失的音频数据,效果良好,具有延时小,占用带宽小等特点.     

基于网络编码的多跳无线网络可靠组播

多跳无线网络中实现可靠组播面临许多挑战,数据丢失恢复是其中的核心问题之一。该文提出一种基于8GF(2)域的随机线性网络编码的多跳无线网络中高效可靠组播(Network Coding Reliable Multicast,NCRM)算法,克服了XOR编码方式的局限性,将原始数据包划分成不同"代"(generation)进行发送,恢复节点采用随机线性网络编码方式发送编码包,发生丢包的组播组成员发送携带丢包比特向量的NACK(Negative ACKnowledgement),经过邻居恢复、多跳恢复或源端恢复,完成可靠组播过程。该文建立了节点丢失恢复过程的齐次马尔科夫链数学模型,给出理论平均时延和重传跳数。NS2仿真结果验证了理论分析模型的准确性。数值结果表明,与PGM(PragmaticGeneral Multicast)和CoreRM可靠组播协议相比,NCRM算法显著改善了网络吞吐量和丢失恢复延时等性能。     

基于SIP协议的多媒体视讯业务承载质量研究——VoIP业务

语音通信是"三网融合"业务中的基础业务,在NGB网络中采用VoIP技术进行承载。作为一个分组交换网,NGB自身的统计时分特性会导致语音报文与其他业务报文复用并被传送到对端时,经历出不同的时延,甚至由于链路和设备的缺陷发生丢失,继而影响通信质量。本文将对IP网络的时延、时延变化、丢包和错包等性能之指标对VoIP的业务影响进行定性和定量分析。     

基于RNN和WFST译码的自动语音识别研究

文中利用Eesen框架声学建模简化了现有的自动语音识别(ASR),通过训练单个递归神经网络(RNN)来预测上下文无关的目标(音素或字符)。为了消除对预生成帧标签的需求,采用了连接时间分类(CTC)目标函数来推断语音和标签序列之间的对齐。同时,采用基于加权有限状态换能器(WFST)的广义译码方法,将词汇和语言模型有效地整合到CTC译码中。实验结果表明,与混合HMM/DNN模型相比,所提方法具有较低的误码率(WER),同时显著加快了译码速度。     

一种语音信号重建算法

为了减轻因信包丢失而造成的语音失真,提出了一种基于双边线性预测的信包丢失隐藏算法。这种方法利用丢失信包的前一信包或邻接信包(在后一信包可获得的情况下)预测丢失信包,通过线性加权双边线性预测的样点获得最终的重建信号,使用重叠相加和幅度调整操作平滑重建信号和真实信号之间的边界。经过非正式试听和ITU-T P.862协议所推荐的PESQ算法测试,该算法的重建语音信号质量与其他四种流行重建算法相比,有了较为明显的改善。     

Single-ended parametric voicing-aware models for live assessment of packetized VoIP conversations

The perceptual quality of VoIP conversations depends tightly on the pattern of packet losses, i.e., the distribution and duration of packet loss runs. The wider (resp. smaller) the inter-loss gap (resp. loss gap) duration, the lower is the quality degradation. Moreover, a set of speech sequences impaired using an identical packet loss pattern results in a different degree of perceptual quality degradation because dropped voice packets have unequal impact on the perceived quality. Therefore, we consider the voicing feature of speech wave included in lost packets in addition to packet loss pattern to estimate speech quality scores. We distinguish between voiced, unvoiced, and silence packets. This enables to achieve better correlation and accuracy between human-based subjective and machine-calculated objective scores.     

Adaptive Speech Streaming Based on Packet Loss Prediction Using Support Vector Machine for Software‐Based Multipoint Control Unit over IP Networks

An adaptive speech streaming method to improve the perceived speech quality of a software‐based multipoint control unit (SW‐based MCU) over IP networks is proposed. First, the proposed method predicts whether the speech packet to be transmitted is lost. To this end, the proposed method learns the pattern of packet losses in the IP network, and then predicts the loss of the packet to be transmitted over that IP network. The proposed method classifies the speech signal into different classes of silence, unvoiced, speech onset, or voiced frame. Based on the results of packet loss prediction and speech classification, the proposed method determines the proper amount and bitrate of redundant speech data (RSD) that are sent with primary speech data (PSD) in order to assist the speech decoder to restore the speech signals of lost packets. Specifically, when a packet is predicted to be lost, the amount and bitrate of the RSD must be increased through a reduction in the bitrate of the PSD. The effectiveness of the proposed method for learning the packet loss pattern and assigning a different speech coding rate is then demonstrated using a support vector machine and adaptive multirate‐narrowband, respectively. The results show that as compared with conventional methods that restore lost speech signals, the proposed method remarkably improves the perceived speech quality of an SW‐based MCU under various packet loss conditions in an IP network.     

基于双边线性预测的信包丢失隐藏算法

本文提出了一种基于双边线性预测的信包丢失隐藏算法。该方法利用丢失信包的前一信包或邻接信包(在后一信包可获得的情况下)预测丢失信包。线性加权双边线性预测的样点获得最终的重建信号。使用重叠相加和幅度调整操作平滑重建信号和真实信号之间的边界。经过非正式试听和ITU-T P.862协议所推荐的PESQ算法测试,本文建议算法的重建语音信号质量,与其他四种流行重建算法相比有了较为明显的改善。     

Effects of Packet Losses in Waveform Coded Speech and Improvements Due to an Odd-Even Sample-Interpolation Procedure

We have studied the effects of random packet losses in digital speech systems based on 12-bit PCM and 4-bit adaptive DPCM coding. The effects are a function of packet lengthBand probability of packet loss PL. We have also studied tbe benefits of an odd-even sample-interpolation procedure that mitigates these effects (at the cost of increased decoding delay). The procedure is based on arranging a2B-block of codewords into twoB-sample packets, an odd-sample packet and an even-sample packet. If one of these packets is lost, the odd (or even) samples of the2B-block are estimated from the even (or odd) samples by means of adaptive interpolation. Perceptual considerations indicate that packet lengths most robust to losses are in the range 16-32 ms, irrespective of whether interpolation is used or not. With these packet lengths, tolerable PLvalues, which are strictly input-speech-dependent, can be as high as 2 to 5 percent without interpolation and 5 to 10 percent with interpolation. These observations are based on a computer simulation with three sentence-length speech inputs, and on informal listening tests.     

一种基于机会式网络编码的高效广播重传方法

为了提高无线广播网络中数据传输的效率,该文提出了一种新颖的基于机会式网络编码的重传方法。将机会式网络编码技术应用于丢包的重传,并采用高效的丢包组合策略生成重传包。根据网络终端的丢包情况,首先创建丢包的哈希表,再根据哈希表快速选择满足一定编码条件的丢包以生成重传数据包,从而在提高重传性能的同时,有效地降低了重传方法的复杂度。仿真结果表明该方法相比已有算法能有效地减少重传次数,并提高重传包发送和接收的效率。     

Accurate method for analysis of a packet speech multiplexer

A packet speech multiplexer is analysed using a fluid approximation for the flow of packets in and out of the multiplexer. Delay distributions and fractional packet loss are determined with a small amount of computation. Comparisons with a simulation using real speech show the analysis to be accurate.     

Queueing analysis of delay constrained voice traffic in a packetswitching system

Unlike data traffic, the voice packet stream from a node has very high correlation between consecutive packets. In addition, in order for the speech to be properly reconstructed, a delay constraint must be satisfied. A queueing model that accurately predicts packet loss probabilities for such a system is presented. Analytical results are obtained from an embedded bivariate Markov chain and are validated by a simulation program. Based on this model, the impact of the delay constraint, talkspurt detection thresholds, and packet size on packet loss are studied. Two schemes, named `instant' and `random', for discarding late packets are considered. Simulation results show that better performance can be obtained by using the latter scheme     

支持WiMAX节点灵活休眠的两阶段可靠多播策略

节能是无线网络的一个重要课题.针对IEEE 802.16e标准第2类节能模型中监听窗口长度固定会导致一些空闲移动站因得不到及时休眠而浪费能量这一不足,该文提出"两阶段可靠多播策略",让基站在第1阶段多播数据包,在第2阶段对第1阶段丢失的数据包进行网络编码并重播.该策略让移动站一旦空闲就进入休眠,实现了时延约束下数据包的可靠传递.仿真试验表明,该策略可以降低能耗,且移动站的占空比、能耗、吞吐率、丢包率等指标均优于传统的重传与确认方案.     

Analysis of packet loss processes in high-speed networks

The packet loss process in a single-server queueing system with a finite buffer capacity is analyzed. The model used addresses the packet loss probabilities for packets within a block of a consecutive sequence of packets. An analytical approach is presented that yields efficient recursions for the computation of the distribution of the number of lost packets within a block of packets of fixed or variable size for several arrival models and several numbers of sessions. Numerical examples are provided to compare the distribution obtained with that obtained using the independence assumption to compute the loss probabilities of packets within a block. The results show that forward error correction schemes become less efficient due to the bursty nature of the packet loss processes; real-time traffic might be more sensitive to network congestion than was previously assumed; and the retransmission probability of ATM messages has been overestimated by the use of the independence assumption