VoIP Environment Research Articles

MiniatureVQNet: A Light-Weight Deep Neural Network for Non-Intrusive Evaluation of VoIP Speech Quality

In IP audio systems, audio quality is degraded by environmental noise, poor network quality, and encoding–decoding algorithms. Therefore, there is a need for a continuous automatic quality evaluation of the transmitted audio. Speech quality monitoring in VoIP systems enables autonomous system adaptation. Furthermore, there are diverse IP audio transmitters and receivers, from high-performance computers and mobile phones to low-memory and low-computing-capacity embedded systems. This paper proposes MiniatureVQNet, a single-ended speech quality evaluation method for VoIP audio applications based on a lightweight deep neural network (DNN) model. The proposed model can predict the audio quality independent of the source of degradation, whether noise or network, and is light enough to run in embedded systems. Two variations of the proposed MiniatureVQNet model were evaluated: a MiniatureVQNet model trained on a dataset that contains environmental noise only, referred to as MiniatureVQNet–Noise, and a second model trained on both noise and network distortions, referred to as MiniatureVQNet–Noise–Network. The proposed MiniatureVQNet model outperforms the traditional P.563 method in terms of accuracy on all tested network conditions and environmental noise parameters. The mean squared error (MSE) of the models compared to the PESQ score for ITU-T P.563, MiniatureVQNet-Noise, and MiniatureVQNet–Noise–Network was 2.19, 0.34, and 0.21, respectively. The performance of both the MiniatureVQNet–Noise–Network and MiniatureVQNet-Noise model depends on the noise type for an SNR greater than 0 dB and less than 10 dB. In addition, training on a noise–network-distorted speech dataset improves the model prediction accuracy in all VoIP environment distortions compared to training the model on a noise-only dataset.

Capture and Analysis of Malicious Traffic in VoIP Environments Using a Low Interaction Honeypot

The number of users of VoIP services is increasing every year. Consequently, VoIP systems get more attractive for attackers. This paper describes the implementation of a low interaction honeypot for monitoring illegal activities in VoIP environments. The honeypot operated during 92 days and collected 3502 events related to the SIP protocol. The analysis of the results allows understanding the modus operandi of the attacks targeted to VoIP infrastructures. These results may be used to improve defense mechanisms such as firewalls and intrusion detection systems.

A Quality Estimation of Synthesized Speech Transmitted over IP Networks

A design of the parametric models estimating a quality of synthesized speech transmitted through IP networks is presented in this paper. A Genetic Programming and Random Neural Network as machine learning techniques were deployed to design the models. A set of the quality-affecting parameters was used as an input to the designed parametric estimation models in order to estimate a quality of synthesized speech transmitted over IP networks (VoIP environment). The performance results obtained for the designed parametric estimation models have validated both genetic programming and random neural network as powerful techniques, delivering good accuracy and generalization ability; this makes them perspective candidates for quality estimation of this type of speech in the corresponding environment. The developed parametric models can be helpful for network operators and service providers in a planning phase or early-development stage of telecommunication services based on synthesized speech.

SPIT 차단을 위한 예측 평판도 기법에 대한 연구

본 논문에서는 실시간 동작 환경인 VoIP에 적용 가능한 스팸 대응 기법으로서 예측 평판도 시스템을 제안한다. VoIP 스탬을 차단하기 위한 연구가 다양하게 진행되고 있지만, VoIP 스팸 대응을 위한 기존 기법들은 사용자의 직접적인 개입으로 인한 사용자 불편성, 실시간 동작으로 인한 세션 설립 시간 지연 및 시스템 과부하 등과 같은 문제가 있다. 제안 기법은 발신자의 세션 설립 주기와 수신자의 통화시간을 기준으로 통계적 방법을 이용하여 평판도를 계산하는 시스템이다. 제안 기법은 사용자의 직접적인 개입이 없기 때문에 사용자의 불편성 문제를 해결할 수 있으며, 실시간 동작을 요구하지 않고 세션 설립 전에 통계적 방법으로 발신자의 평판도를 계산하기 때문에 실시간 동작 환경인 VoIP에서 효과적으로 SPIT에 대응할 수 있다.

UTILITY BASED SCHEDULING AND CALL ADMISSION CONTROL FOR LONG TERM EVOLUTION NETWORKS

In this study, we propose to design a call admission control algorithm which schedules the channels for Real time and non-real time users. In Long Term Evolution (LTE) 3GPP Networks, several works were done on call admission control but these works rarely considers scheduling of resources to the real time and non-real time users.When the system meets traffic oriented performance degration, maximum resources are utilized for load balancing and to maintain the consistent quality. In order to avoid the channel degradation and improve the Quality of Service (QoS), the call requests are classified into New Call (NC) request and Handoff Call (HC) request and the type of services are classified as VoIP and video. Then based upon the Received Signal Strength (RSS) value, the channel is estimated as good channel or bad channel. Resource allocation is made for VoIP users based on traffic density. Then non-VoIP users and the non-real time users are allocated resource blocks using the channel condition based marginal utility function. When there are no sufficient resources to allocate, it allocates the resources of bad channel users there by degrading their service. We have designed the network topology with G (n) and B (n) for representing the available good and bad channels. We investigate the performance degradation when the real time, Non real Time, video and VOIP environments based on RSS threshold value.Comparison is made with the VOS in terms of the paramenters like throughput,bandwidth,delay,fairness and rate. Our proposed method provides good performance and quality.From our simulation results we show that this admission control algorithm provides channel quality and prioritizes the handover calls over new calls which allocates resources to all kinds of users.

향상된 Multi Gray-Leveling을 통한 VoIP 스팸 탐지 기법

In this paper, we propose an improved Multi Gray-Leveling scheme which reduces the problems of the existing Multi Gray-Leveling scheme suggested as a way of prevention against call spam in VoIP environment. The existing scheme having two different time period distinguishes the possibility of call spam by checking the call interval, so that it prevents the spammer`s avoidance controlling the call interval. This is the strength of the existing one but it can misunderstand the normal user as a spammer due to taking long term time period. To solve this problem, this paper proposes the upgrade scheme which utilizes the receiver`s action pattern as well as the caller`s action pattern. It has such a good strength that can do gray leveling via the collected information in the database of VoIP service provider without user`s direct involvement. Hence it can be a very effective way of VoIP spam detection.

IP 컨택센터에서 통화 녹음을 위한 VoIP 녹취 시스템

In this paper we describe a VoIP transcript system which is able to record call conversation between counselor and customer in an IP contact center based on IP telephony environment. The transcript system, designed and implemented in this paper, uses packet sniffering to capture packets without imposing network overhead on overall system. It can decode H.323 and SIP which are used to setup call sessions in VoIP environment and captures voice data and record without any loss of contents. Implemented transcript system can be integrated with CTI system in that it can manage and record call more effectively. It is designed generically so that it is implemented both on Windows and Linux environment.

Side effects of identity management in SIP VoIP environment

In this article, we summarize the security threats targeting SIP proxy servers or other infrastructures in NGN by misusing a specific signaling authentication mechanism, which has been proposed in RFC 4474 (Peterson and Jennings, 2006). This mechanism is designed to authenticate inter-domain SIP requests based on domain certificates to prevent identity theft. Nevertheless, despite its contribution, this protection raises some “side effects”, that actually lead to new vulnerabilities in both the availability and confidentiality of SIP services. We provide an overview of different attack possibilities and explain them in more detail, including attacks utilizing algorithm complexity, certificates storage, and certificates distribution. We also suggest some alternative design to prevent or reduce the attacks. SIP, VoIP, NGN, Authentication, Denial of Service, Timing attack.

Secure Group Key Management Scheme for Multicast Networks

This paper proposes a scheme to provide security to dynamic multicast VoIP systems efficiently. Security is usually provided by encrypting the media packets sent from a user to other users with the help of a shared key called the session encryption key. The most time consuming process in a dynamic multicast VoIP environment is the group key management. Whenever there is a change in the group membership, the key needs to be updated and the updated key has to be sent to all active members in the group. Hence, by decreasing the number of update messages required for an updated key, the performance of the system can be improved considerably, thus making the scheme more efficient. The proposed secure multicast key management scheme combines the advantages of logical-key tree structure and Chinese remainder theorem to achieve an effective scheme. This paper compares the efficiency of the proposed scheme with the existing schemes and the comparison shows that the proposed scheme performs better than the existing schemes in terms of reduction in key update messages.

Impact of Different Active-Speech-Ratios on PESQ's Predictions in Simulated VoIP Environment

In this work, we experimentally study how behaviour of the PESQ predictions varies with reference signal characteristic. In particular we investigate the impact of different Active-Speech-Ratios on speech quality prediction in simulated VoIP environment from objective and subjective testing point of view. This reference signal characteristic is defined very broadly by ITU-T Recommendation P.862.3. That is the reason to investigate an impact of this characteristic on speech quality prediction more in-depth. We assess the variability of PESQ's predictions with respect to Active-Speech-Ratio and network conditions, as well as their accuracy, by comparing the predictions with subjective assessments.

OntoSPIT: SPIT management through ontologies

VoIP enables new ways for communication. At the same time, it provides new means, in terms of transmitting bulk unsolicited messages and calls, namely SPam over Internet telephony (SPIT). In this paper, we propose a conceptual model, based on an underlying ontology, which describes the SPIT domain. The ontology provides capabilities, such as modeling the SPIT phenomenon in a SIP-based VoIP environment, a common understanding of SPIT domain, as well as reusable SPIT-related knowledge interoperability, aggregation and reasoning. We demonstrate that the proposed ontology, combined with a set of SPIT identification criteria, as its underlying axioms and rules, could enhance the correlation and management of SPIT incidents. It could also support SPIT detection, thus facilitating the better protection of VoIP environments in a holistic, cooperative, and effective way.

Nonintrusive Measurement of Echo-Path Parameters in VoIP Environments

This paper proposes two echo-path delay measurement methods suitable for voice-over-Internet-protocol environments, where the echo suffers from excessive delay and nonlinear distortion. The proposed methods aim at greatly reducing the computational requirements while maintaining good measurement accuracy. The delay measurement is based on the cross correlation; the computation reduction is achieved by using either downsampled speeches or sparse speeches for the two methods, respectively. The echo-path loss is also measured by using the obtained delay information. The performance under codec distortion, packet loss, noise, and double talk conditions is examined through simulations and real field measurements. The results show that the proposed methods are effective and accurate

Performance Enhancement on Voice using VAD Algorithm and Cepstral Analysis

The Transport of Voice Over Network has been existing for a long time. Due to the bad quality of speech and absence of useful service, it has not yet been widely spread. The benefits of reduced cost and bandwidth savings of carrying voice over data network is associated with Quality of Service (QoS). Many different techniques and protocols are used to improve the quality of service in voice over data network. We review our data on the voice quality effects of background noise and the compression option of suppressing transmission during silence. Because the main problem of echo has emerged repeatedly in the VOIP environment, we review this issue in voice over data communication network is used to VAD algorithms and cepstral analysis of VOIP network performance.

Progressive multi gray-leveling: a voice spam protection algorithm

As voice over IP gains popularity, it is easy to imagine that Internet hacking and other security problems we currently face with email spam will attack the VoIP environment. In contrast to email protocols represented by SMTP, VoIP does not tolerate any negotiation in its signaling steps or screening content due to the delay limitation. Thus, it is difficult to implement voice spam protection or control algorithms by just mimicking popular email spam protection algorithms. This article proposes a voice spam control algorithm called progressive multi gray-leveling (PMG) that fits in VoIP settings. PMG progressively calculates the gray level of a caller and determines whether the call will be connected or blocked based on previous call patterns. Based on experiments, it turns out that PMG can learn a spammer's calling pattern and block massive spam attacks from them effectively

Implementing VoIP: a voice transmission performance progress report

Aiming to introduce voice over IP networks and services in ways that satisfy the voice quality expectations of our customers, we have been conducting laboratory studies of how VoIP transmission affects voice quality while also carefully monitoring and managing several field implementations of VoIP. This article summarizes much of what we have learned in this work, and we hope it provides a useful progress report on the industry's evolution to VoIP. We review our data on the voice quality effects of packet loss, delay, speech coders, packet loss concealment algorithms, and the compression option of suppressing transmission during silence. Because the familiar problem of echo has emerged repeatedly in the VoIP environment, we review this issue in some detail. Packet loss and delay variation measurements made on private VoIP networks are reviewed, and the data here are encouraging. We finish by making our case that the network planning tool known as the E-model is currently an inexact predictor of VoIP network performance.

Quality of Service in VoIP Communication

The focus of this paper lies in the practical aspects of voice over IP communication. VoIP configurations in the H.323 standard will be presented briefly. Following that, the fundamental protocol procedure of H.323 communication will be briefly explained. A further part of the paper will address the subject QoS (quality of service), and present the common measurement methods used in QoS. Results gained from experiments conducted in a VoIP environment will then follow. The investigations concentrate primarily on the load behavior of voice packets in relation to important parameters of this service. The results obtained are presented and evaluated in diagrams. The paper concludes with a summary.