Voice Over IP Calls Research Articles

Enhanced Multiple Speakers’ Separation and Identification for VOIP Applications Using Deep Learning

Institutions have been adopting work/study-from-home programs since the pandemic began. They primarily utilise Voice over Internet Protocol (VoIP) software to perform online meetings. This research introduces a new method to enhance VoIP calls experience using deep learning. In this paper, integration between two existing techniques, Speaker Separation and Speaker Identification (SSI), is performed using deep learning methods with effective results as introduced by state-of-the-art research. This integration is applied to VoIP system application. The voice signal is introduced to the speaker separation and identification system to be separated; then, the “main speaker voice” is identified and verified rather than any other human or non-human voices around the main speaker. Then, only this main speaker voice is sent over IP to continue the call process. Currently, the online call system depends on noise cancellation and call quality enhancement. However, this does not address multiple human voices over the call. Filters used in the call process only remove the noise and the interference (de-noising speech) from the speech signal. The presented system is tested with up to four mixed human voices. This system separates only the main speaker voice and processes it prior to the transmission over VoIP call. This paper illustrates the algorithm technologies integration using DNN, and voice signal processing advantages and challenges, in addition to the importance of computing power for real-time applications.

CO-CAC: A new approach to Call Admission Control for VoIP in 5G/WiFi UAV-based relay networks

Voice over IP (VoIP) requires a Call Admission Control (CAC) mechanism in WiFi networks to preserve VoIP packet flows from excessive network delay or packet loss. Ideally, this mechanism should be integrated with the operational scenario, guarantee the quality of service of active calls, and maximize the number of concurrent calls. This paper presents a novel CAC scheme for VoIP in the context of a WiFi access network deployed with Unmanned Aerial Vehicles (UAVs) that relay to a backhaul 5G network. Our system, named Codec-Optimization CAC (CO-CAC), is integrated into each drone. It intercepts VoIP call control messages and decides on the admission of every new call based on a prediction of the WiFi network’s congestion level and the minimum quality of service desired for VoIP calls. To maximize the number of concurrent calls, CO-CAC proactively optimizes the codec settings of active calls by exchanging signaling with VoIP users.We have simulated CO-CAC in a 50m × 50m scenario with four UAVs providing VoIP service to up to 200 ground users with IEEE 802.11ac WiFi terminals. Our results show that without CAC, the number of calls that did not meet a minimum quality level during the simulation was 10% and 90%, for 50 and 200 users, respectively. However, when CO-CAC was in place, all calls achieved minimum quality for up to 90 users without rejecting any call. For 200 users, only 25% of call attempts were rejected by the admission control scheme. These results were narrowly worse when the ground users moved randomly in the scenario.

Performance Evaluation of Selected Adaptive Filters for Acoustic Echo Cancelation over Voice over Internet Protocol

Advancement of technology has increased the value of the telecommunications industry. One of the services with the rapid growth is Voice over Internet Protocol (VoIP). However, echo is a common disturbing effect in VoIP calls. Instead of suppressing the presence of echo in the VoIP communication channel, echo cancellation works better in full-duplex mode. This paper compares performances of some selected adaptive filters for cancelation of acoustic echo in VoIP channel. The framework for adaptive echo cancellation is built around finite impulse response and fourth-order infinite impulse response Chebyshev type II filters for the modeling of echo and acoustic environment, respectively. Selected adaptive algorithms for analysis are least mean square, recursive least square and frequency domain adaptive filter. The analysis is carried out in MATLAB 2018a environment. Echo return loss enhancement, error estimate and convergence rate are the performance indices employed for performance comparison of selected adaptive algorithms. It was found that the FDAF algorithm performed best based on computed error return loss enhancement and error estimate figures. In addition, FDAF converges faster than LMS and RLS with average time of 0.026431 s over 2048 filter lengths. Thus, FDAF shows a better promise over the two variants of time domain adaptive algorithm (LMS and RLS) analyzed in this paper.

Design a Real-time Communication System using 3CX Software-based Private Branch Exchange Phone System on Raspberry Pi Device

With the advancement of technology, the telephone network has become the primary mode of communication worldwide, and private businesses have increased their reliance on telephone communication. Many organizations choose to establish their own service in order to manage internal calls. Voice over Internet Protocol (VoIP) is one of the emerging technologies that may provide low-cost service with high-quality and availability. VOIP technology enables the transfer of multimedia data such as audio and video. While some VoIP services require a computer or a dedicated VoIP phone, others allow you to make VoIP calls using your landline phone via a special adaptor. Rather than using a traditional private branch exchange (PBX), we used a Raspberry pi, which is a set of credit card-sized single-board computers, as a server for handling voice and video call communications over a wired or wireless LAN network while monitoring the entire system. Wireshark is a software application that is used to capture packets in a network and present information about certain packets in as much detail as possible.

Quality Evaluation of VoIP Codecs in Cellular Mobile Networks

Maintaining the Quality-of-Service (QoS) of Voice-over-Internet Protocol (VoIP) is a major problem due to the instability of network conditions. One factor that influences VoIP call quality is the employed codec. In this research, the influence of codec on the QoS of VoIP calls is evaluated under Wi-Fi, 2G, 3G and 4G networks. VoIP calls are established using PCMA, PCMU, GSM and G.722 codecs and QoS parameters including jitter, round trip time and packet loss are measured. QoS measurements are compared against considered networks and codecs. Results illustrate that there exists a codec that better suits each network with considerable advantages over other codecs and minimum drawbacks.

An Effective Machine Learning (ML) Approach to Quality Assessment of Voice Over IP (VoIP) Calls

This letter puts forward a supervised ML technique to determine the Quality of Experience (QoE) of VoIP calls. It takes its beginning from an investigation on VQmon, an enhanced E-model version that estimates the quality of IP-based voice calls adopting an objective approach. The current study demonstrates VQmon shortcomings via a comparison between the Mean Opinion Score (MOS) values this technique predicts and the actual average ratings collected from a subjective listening quality campaign. It proposes to deploy Ordinal Logistic Regression (OLR) for speech quality assessment, and results disclose that OLR outperforms popular ML algorithms, in accuracy and confusion matrices.

Effective Voice Frame Pruning Method to Increase VoIP Call Capacity

Voice over Internet Protocol (VoIP) is gradually dominating the telecommunication sector because it is free or inexpensive. However, one of the key problems of VoIP growth is inefficient bandwidth utilization. Several methods have been proposed to improve the VoIP bandwidth utilization, and they include VoIP packet aggregation and header compression. In this study, we investigate a new dimension to improve VoIP bandwidth utilization, that is, VoIP packet payload compression. The main idea of the proposed method, which is called the voice frame pruning (VFP) method, is to prune the leading/trailing zeros/ones of the VoIP packet payload on the basis of a certain mechanism. The VoIP packet payload is pruned at the sender side’s wide area network (WAN) gateway and restored to its original form at the receiver side’s WAN gateway. The implementation results of the proposed VFP method indicate good bandwidth savings based on the VoIP codec used. For example, the bandwidth savings of the LPC, G.723.1, and G.729 improved by up to approximately 5%, 8%, and 3.5%, respectively, thereby improving the VoIP bandwidth utilization and the capacity of VoIP calls.

VoIP-HDK – A novel channel allocation technique for QoS aware VoIP communication over heterogeneous networks

Abstract Channel allocation for VoIP (Voice over IP) is a critical problem in modern-day heterogeneous networks having diverse application requirements. Conventional stochastic and machine-learning based models that predict channel suitability for VoIP underperform under dynamic conditions. In contrast, this paper deploys VoIP-HDK2 – a novel technique that uses an efficient combination of K-Nearest Neighbors algorithm, 2-order Hidden Markov Model, Damerau-Levenshtein distance based model and K-Means Clustering technique to accurately predict and allocate channels with sufficient QoS (Quality of Service) guarantees to VoIP calls. The primary contribution of this paper lays both in the formulation of the proposed methodology involving tailor-made algorithms as well as complete test-bed based dataset creation, execution of VoIP-HDK2 and validation of its performance in terms of maintaining high quality VoIP calls. Comparative performance evaluation records significant reduction in call drops and packet-loss and enhancement in call quality and throughput for VoIP-HDK2 with respect to existing works in literature.

ITTP-PG: A Novel Grouping Technique to Enhance VoIP Service Bandwidth Utilization

Recently, the field of telecommunications started to migrate to Voice over Internet Protocol (VoIP) service. VoIP service applications produce packets with short payload sizes to reduce packetization delay. That is, increasing the preamble size and expends the network link bandwidth. Packet grouping is a technique to enhance the employment of network link bandwidth. Numerous grouping techniques are suggested to enhance link bandwidth employment when using RTP/UDP protocols. Unlike previous research, this article suggests a packet grouping technique that works over the Internet Telephony Transport Protocol (ITTP), not RTP/UDP. This technique is called ITTP Packet Grouping (ITTP-PG). The ITTP-PG technique groups VoIP packets, which exist in the same route, in a single ITTP/IP preamble instead of an ITTP/IP preamble to each packet. Consequently, preamble size is diminished and network link bandwidth is saved. ITTP-PG also adds 3-byte runt-preamble to each packet to distinguish the grouped packets. The suggested ITTP-PG technique is simulated and compared with the conventional ITTP protocol (without grouping) using three elements, namely, the number of concurrent VoIP calls, preamble overhead, and bandwidth usage. Based on all these elements, the ITTP-PG technique outperforms the conventional ITTP protocol. For example, the result shows that bandwidth usage improved by up to 45.9% in the tested cases.

Identification of VoIP Speech With Multiple Domain Deep Features

Identifying whether a phone call comes from VoIP (Voice over Internet Protocol) is a challenging but less-investigated audio forensic issue. As shown in a previous study, existing feature based methods do not work well. In this paper, we propose a robust data-driven approach, called CNN-MLS (convolutional neural network based multi-domain learning scheme), to distinguish VoIP calls from mobile phone calls. To better explore the differences between VoIP and mobile phone calls, we first process data with high-pass filtering, and then extract deep features from both temporal domain and spectral domain. Two CNN architectures are designed for accepting data from respective domains, and some tricks such as auxiliary classifiers and individual subnet training are used for accelerating network convergence. The deep features are finally fused in a classification module for identifying the phone call type. The proposed method is evaluated on VPCID (VoIP Phone Call Identification Database) dataset, under various testing conditions. We pay particular attention to tests on data belonging to a source mismatched with the training sources. Experimental results show that, compared with existing methods, our method can achieve satisfactory and better accuracy on two-second-long inputs, implying that an alert may be activated shortly after a VoIP call is made.

Effectiveness of SIP Server Under SIP Flooding Attack During VoIP Calls

Voice over Internet Protocol (VoIP) service is increasingly one of the most widespread applications since few decades. Data traffic of VoIP service faces various challenges and threats. The Session Initiation Protocol (SIP) flooding attack is one of the popular threats to this service. Flooding attack is the most severe attack as it is easy to generate and capture the networks and nodes that further lead to Denial of Service attack. Therefore, the performance analysis of SIP servers requires more focus. In this paper, effectiveness of SIP server under SIP flooding attack is evaluated using various message scenarios by setting up an experimental test bed. The stress testing of SIP server is carried out with CPU and memory utilization check. The quality of VoIP calls is measured in term of three quality metrics jitter, delay and packet loss. It is observed that with the increase of simultaneous calls, quality of VoIP calls degraded.

VoIP Steganography Methods, a Survey

Abstract Achieving secured data transmission is not always an easy job. Secret data sharing requires confidentiality and Undetectability. Steganography is preferred than cryptography to achieve undetectability. Steganography hides the secret data inside the other file such as text, audio, video, so that the existence of the secret data is completely hidden. Recent research focuses much on utilizing Voice over Internet Protocol (VoIP) calls as a carrier for data hiding. VoIP calls are much preferred among internet users for its wide availability, dynamic time limit and low cost. This paper focuses on data hiding methods that uses VoIP as a carrier. The paper also analyzes the performance of the algorithms using the three metrics undetectability, bandwidth and robustness.

VoIP QoS Analysis over Asterisk and Axon Servers in LAN Environment

Voice over IP (VoIP) is a developing technology and a key factor in both the emerging cyberspace engineering and also an accomplishment to set up its position in the telecom industry. VoIP technology is based on internet technology; where data packets switching system is used rather than circuit switching. Whereas, an analog signal is changed over into the digital signals in the full-duplex transmission. VoIP technology is replaced with the conventional public switched telephone network (PSTN) system due to the high flexibility and low-cost. The purpose of this research work is to deliberate experimental and computational performance in the view of quality of service (QoS) parameters of VoIP over local area network (LAN) network. The VoIP systems implementation is based on two different operating system framework (Linux and Windows), whereas, Linux-based and Windows-based private branch exchanges (PBXs), such as Asterisk (Linux-open source) and Axon (window-close source) are configured, installed and verified. QoS factors (such as packet loss, delay, jitter, etc.) are observed over the Asterisk and Axon PBXs in a LAN domain with the assistance of Paessler switch activity grapher (PRTG) monitoring tool. The validations of results are looked at for QoS parameters crosswise over both PBXs with data load (i.e., file transfer and HTTP traffic) during VoIP calls. The productivity and execution of Axon and Asterisk have been equated and analyzed over experimental based outcomes.

An Intelligent Framework Prototype for Monitoring Students in Virtual Classroom

<p>Virtual classroom is one of the fastest growing educational technologies used by many industries and institutions. Today, Voice over Internet Protocol (VoIP) cloud is become a most accepted replacement to different virtual classroom technologies such as internet chat, internet radio, web conferencing, traditional video conferencing and peer to peer VoIP calls. It provides greater flexibility, reliability and cost efficient telecommunication features and operates on comparatively lesser bandwidth. Involvement of new technology in virtual classroom makes it more reliable to teachers and students. Still it follows traditional methods to monitor students by invigilator whether it may be inside the classroom or home study. A secure framework for virtual classroom is developed to not only monitor student’s activities continuously but also the amount of time spent by each student and provide security against unsecure unauthorized login. An effective monitoring System based on Liveness Face Detection techniques is proposed to add more flexibility to conduct virtual classroom and also increases the level of securities of each student’s accounts.</p>

A novel blind traffic analysis technique for detection of WhatsApp VoIP calls

SummaryNowadays social media plays a key role in interpersonal communication. Instant messaging applications, such as WhatsApp, are used by billions of users every day. Such application has recently been upgraded to support voice calls, whose traffic is transported over the top of network operators, as many other Voice over Internet Protocol (VoIP) services. In this work, we have characterized WhatsApp voice calls through blind traffic detection, which allows to differentiate WhatsApp calls from other applications, such as sharing video, photo, or messaging. Traditional techniques for detection of VoIP calls cannot be applied to the WhatsApp case because the traffic is obfuscated. Actually, our proposal only takes into account the WhatsApp traffic stream statistical features, and not the packet content. From the operators' point of view, the benefits of such a tool are manifold: from traffic prioritization to bespoke marketing campaigns to users that heavily produce WhatsApp voice calls.

ELF exposure from mobile and cordless phones for the epidemiological MOBI-Kids study

This paper describes measurements and computational modelling carried out in the MOBI-Kids case-control study to assess the extremely low frequency (ELF) exposure of the brain from use of mobile and cordless phones. Four different communication systems were investigated: Global System for Mobile (GSM), Universal Mobile Telecommunications System (UMTS), Digital Enhanced Cordless Telecommunications (DECT) and Wi-Fi Voice over Internet Protocol (VoIP). The magnetic fields produced by the phones during transmission were measured under controlled laboratory conditions, and an equivalent loop was fitted to the data to produce three-dimensional extrapolations of the field. Computational modelling was then used to calculate the induced current density and electric field strength in the brain resulting from exposure to these magnetic fields. Human voxel phantoms of four different ages were used: 8, 11, 14 and adult. The results indicate that the current densities induced in the brain during DECT calls are likely to be an order of magnitude lower than those generated during GSM calls but over twice that during UMTS calls. The average current density during Wi-Fi VoIP calls was found to be lower than for UMTS by 30%, but the variability across the samples investigated was high. Spectral contributions were important to consider in relation to current density, particularly for DECT phones. This study suggests that the spatial distribution of the ELF induced current densities in brain tissues is determined by the physical characteristics of the phone (in particular battery position) while the amplitude is mainly dependent on communication system, thus providing a feasible basis for assessing ELF exposure in the epidemiological study. The number of phantoms was not large enough to provide definitive evidence of an increase of induced current density with age, but the data that are available suggest that, if present, the effect is likely to be very small.

VoIP 네트워크 내의 Fraud와 SIM Box Fraud 검출 방법에 대한 연구

Voice over IP (VoIP) is a technology for the delivery of voice communications and multimedia sessions over Internet Protocol (IP) networks. Instead of being transmitted over a circuit-switched network, however, the digital information is packetized, and transmission occurs in the form of IP packets over a packet-switched network which consist of several layers of computers. VoIP Service that used the various techniques has many advantages such as a voice Service, multimedia and additional service with cheap cost and so on. But the various frauds arises using VoIP because VoIP has the existing vulnerabilities at the Internet and based on complex technologies, which in turn, involve different components, protocols, and interfaces. According to research results, during in 2012, 46 % of fraud calls being made in VoIP. The revenue loss is considerable by fraud call. Among we will analyze for Toll Bypass Fraud by the SIM Box that occurs mainly on the international call, and propose the measures that can detect. Typically, proposed solutions to detect Toll Bypass fraud used DPI(Deep Packet Inspection) based on a variety of detection methods that using the Signature or statistical information, but Fraudster has used a number of countermeasures to avoid it as well. Particularly a Fraudster used countermeasure that encrypt VoIP Call Setup/Termination of SIP Signal or voice and both. This paper proposes the solution that is identifying equipment of Toll Bypass fraud using those countermeasures. Through feature of Voice traffic analysis, to detect involved equipment, and those behavior analysis to identifying SIM Box or Service Sever of VoIP Service Providers.

VoIP Based Tele-medicine Call Center–Issues, Challenges and Proposed Solution

In recent years, medical call centers have started using IP telephony services to minimize the overhead telecom expenses. However, the advent of Voice-Over-IP (VoIP) technology has also created a major discontinuity in telecommunication sector due to illegal VoIP or gray calls, causing a great impact on the voice market. This brought few challenges to the countries’ regulatory bodies. In this paper, we spell out one of the key challenges: in order to mitigate illegal VoIP calls, whether the regulatory body should allow IP telephony to be practiced for both domestic and international voice driven tele-medical consultation center operation combined or separately. We propose architecture and schemes for a medical call center. We also propose some guidelines and/or policies for both call center operator and the telecom regulatory authority. The proposed architecture and schemes are implemented in a pilot project basis in two phases and the test bed result is presented in this article.

Empirical Study of Achievable Bandwidth Capacity of VoIP Infrastructure in an Intranet with Open Source Tools

This paper presents an empirical study of achievable bandwidth/concurrent calls capacity of an open source Voice over Internet Protocol (VoIP) Server deployed on an Intranet with open source tools. Network readiness in IPv4 and IPv6 environments was evaluated using Iperf while VoIP calls were simulated with open source SIPp (Session Initiation Protocol performance-tester). Voipmonitor, another open source software, was used to measure the bandwidth capacity and maximum concurrent calls handling capacity of the Asterisk Server over fast Ethernet Local Area Network. It can be deduced that the concurrent calls capacity of a VoIP server is dependent on a number of factors such as the VoIP readiness / bandwidth of the network and hardware specifications of the VoIP server. The result from experimental values shows that the achievable bandwidth otherwise called TCP throughput (for the 100Mbps LAN) for IPv4 and IPv6 traffics in dual stack configuration is 86.8Mbps and 87.4Mbps respectively. While that of UDP bandwidth measurement gives 50Mbps, jitter value of 1.794ms and packet loss of 0.59% for IPv4 traffic and 49.7Mbps bandwidth, 0.592ms jitter with packet loss of 0.22% for IPv6 traffic. At the maximum concurrent calls handling capacity, the processor of the VoIP server was observed to have 100% loading or utilization measure. It is recommended that the VoIP server should not be loaded continuously at this maximum processor load for optimum performance and longevity of life.

Quality assessment and usage behavior of a mobile voice-over-IP service

Voice-over-IP (VoIP) services offer users a cheap alternative to the traditional mobile operators to make voice calls. Due to the increased capabilities and connectivity of mobile devices, these VoIP services are becoming increasingly popular on the mobile platform. Understanding the user’s usage behavior and quality assessment of the VoIP service plays a key role in optimizing the Quality of Experience (QoE) and making the service to succeed or to fail. By analyzing the usage and quality assessments of a commercial VoIP service, this paper identifies device characteristics, context parameters, and user aspects that influence the usage behavior and experience during VoIP calls. Whereas multimedia services are traditionally evaluated by monitoring usage and quality for a limited number of test subjects and during a limited evaluation period, this study analyzes the service usage and quality assessments of more than thousand users over a period of 120 days. This allows to analyze evolutions in the usage behavior and perceived quality over time, which has not been done up to now for a widely-used, mobile, multimedia service. The results show a significant evolution over time of the number of calls, the call duration, and the quality assessment. The time of the call, the used network, and handovers during the call showed to have a significant influence on the users’ quality assessments.