PERFORMANCE OF THE ETSI DISTRIBUTED SPEECH RECOGNITION ALGORITHM OVER GSM AND IP NETWORKS

Size: px
Start display at page:

Download "PERFORMANCE OF THE ETSI DISTRIBUTED SPEECH RECOGNITION ALGORITHM OVER GSM AND IP NETWORKS"

Transcription

1 PERFORMANCE OF THE ETSI DISTRIBUTED SPEECH RECOGNITION ALGORITHM OVER GSM AND IP NETWORKS Olav Skundberg 1, Jamil Y. Khan 2, Graham Wade 2 1 Sør-Trøndelag University College, Trondheim, Norway 2 School of Electrical Engineering & Computer Science, University of Newcastle, Callaghan, NSW 2308 ABSTRACT: The purpose of Distributed Speech Recognition (DSR) is to improve the performance of speech recognition services across communication networks. The DSR method is to extract feature vectors at a front-end terminal and transmit them as data with error protection to a back-end server. The ETSI STQ-AURORA DSR working group has standardised such a method. In this paper the ETSI DSR algorithm is tested over GSM and IP networks with varying bit error rates and packet loss conditions. A GSM channel with poor conditions (a bit error rate of 6.7e-3) is found to reduce the recognition performance by 6.3% compared to an errorfree signal. An IP network with poor conditions (15% packet loss) reduces the recognition performance by as little as 0.9%. The test results show that the ETSI DSR algorithm achieve good recognition performance over GSM and IP networks. 1. INTRODUCTION With the growth of telecommunication services and mobile and Internet applications, service providers probably will offer a significant number of new services based on speech recognition. These services may include automatic phone directories; call centre services and voice portals for information retrieval from the Internet. Currently used mobile terminals (mobile phones, PDA s etc.) have not got enough capacity to support medium or large-scale speech recognition tasks, therefore speech recognition tasks are performed on a centralised server. The mobile terminals traditionally would use a voice channel to connect to a centralised recognition server, but the performance of the recogniser could be poor because of the low bit rate voice coder and transmission errors [Pearce, 2000]. To overcome this hindrance, a new approach is to share some of the processing tasks between a front-end terminal and a back-end server. The DSR method is to extract speech feature vectors at front-end terminal and transmit them as data with error protection to a back-end speech recognition server. This paper evaluates the performance of the ETSI DSR algorithms over GSM and IP networks. The network conditions are varied to see how it affects recognition performance. GSM radio channel with bit errors IP network with packet loss Speech recognition server DSR front-end feature extraction and coding Gateway DSR backend decoding and error mitigation Figure 1. A mobile terminal communicating with a speech recognition server across GSM radio channel and IP packet network Accepted after abstract review page 468

2 2. DISTRIBUTED SPEECH RECOGNITION 2.1 DSR algorithms The STQ-AURORA DSR Working Group of European Telecommunications Standards Institute (ETSI) has standardised a DSR technique [ETSI 2000]. This paper is using the ETSI DSR V1.1.2 example software implementation. The software is distributed along with the ETSI standard and has three processing steps: Feature extraction, Compression and formatting, and Decoding and recovery. The codebooks used for compression and decompression is supplied with the ETSI DSR code DSR Feature vector extraction: The DSR method extracts speech feature vectors used for the recognition task from the original speech signal at a front-end terminal. The mel-frequency cepstral coefficients (MFCC) are extracted, where the vectors consist of 13 static cepstral coefficients and a log-energy coefficient. A vector is generated every 10 ms, independent of the sampling rate of the voice signal. DSR Compression and formatting: The extracted feature vectors are compressed in order to reduce the number of bits needed to represent them. The MFCC coefficients are grouped into pairs, where C0 and loge is a pair of its own. Each pair is quantised based on a weighted Euclidian distance and using its own codebook. The resulting index values are packed into a multiframe that contains frames from 24 samples along with multiframe header information and CRC codes. The header of a multiframe has 16 CRC code bits for error recovery, and each pair of frame indexes have 4 bits of CRC code to detect errors. The resulting transmission rate (including extra bits for header information and error protection) is 4.8 kbit/s. DSR Decoding and error recovery: At the receiving side (the back-end) the vectors are recovered and presented to the speech recognition system. Frames received with errors are replaced with a copy of the closest vector without errors. 2.2 The GSM channel GSM transmission channels can be characterised by varying bit error rate conditions. These are caused by several factors; signal strength (which normally depends on distance from base station), noise levels, the effect of signal reflections (multipaths) and the velocity of the mobile terminal. These physical conditions influence the Bit Error Rate (BER) of a transmission channel. Typical BER in a mobile radio channel varies from e-5 (good conditions) to e-3 (poor conditions). Several strategies have been advised to minimize the effect on the actual application from bit transmission errors. A method is to add redundancy bits before transmission. Depending on the coding of these bits, the receiver may be able detect if an error has occurred or not and can take action according to this situation. The erroneous data could be re-transmitted, but this would introduce an uncertain element of delay and that is generally not good in voice communication. Rather the receiver can do some interpolation for the erroneous data. The ETSI DSR standard specifies that for every two pair of compressed feature vectors, a 4-bit CRC code be added. This is used to determine if a frame pair has been received correct or not. In case of errors, the last correct frame is used to replace the first bad frame of the frame pair, and the first correct frame after the error is used to replace the last bad frame of the frame pair. This interpolation method is also used if there is a sequence of bad frame pairs. The GSM bit error masks used in this work are obtained from simulations with SystemView software ( The masks are used to introduce bit errors similar to that of a GSM transmission into the test files. 2.3 The IP network IP networks can be characterised by packet loss. One of the reasons for packet loss is congestion where network nodes could drop packets. This network behaviour, with typically bursty packet loss, can be modelled using a 2-state Markov Model [Riskin, 2001]. A packet is discarded with a probability Accepted after abstract review page 469

3 p if the previous packet was received ok, and if the previous packet was lost then the packet is discarded with a probability q. There are a number of methods to packetise a bit stream and send the packets across an IP network. The packet size can be varied. Redundant data can be added to recover from packet loss. IP packetising is not part of the ETSI DSR standard. In this work IP packets are numbered so that a loss can be detected by comparing the sequence numbers. If a packet is lost, it is replaced with a fixed pattern 0x01 (no interpolation) to let the ETSI DSR algorithms do the error mitigation. Packet sizes of 12 and 24 bytes of data (excluding TCP/IP header information) are tested. These are normal packet sizes for VoIP transmissions. A second algorithm that transmits an extra copy of the packet if it contains the multiframe header is tested under high loss conditions. We developed our own program to implement the IP network packet loss algorithms. 2.4 The speech recogniser The HTK (Hidden Markov Model Toolkit, speech recognition system is used to measure the performance of DSR. The HTK system compares the recognition output with the transcription of the voice input and calculates the word accuracy. The word accuracy is reduced with insertion, deletion and substitution errors. The HMM model: A sub-word monophone HMM is used with 3 states left-to-right with no skip transitions and with 1 Gaussian per state. Two pause models are defined according to the commonly used short pause between words and silence at the beginning and end of sentences. The energy measure is based on the loge component. Delta and Acceleration coefficients are used, bringing the total number of coefficients to 39. The MFCCs are extracted from the voice recordings with the ETSI DSR extraction program. The models are trained on unquantised vectors, discarding the C0 coefficient in the process. The corpus: Voice recordings for training the recogniser and testing the DSR performance were collected at Newcastle University. The recogniser is used for testing continuously spoken random numbers from one to nine. Sentences with random sequences of these numbers are recorded using a PC soundcard and microphone in an office environment. 2 female and 3 male persons are reading 50 sentences each, totalling 2879 words. 80% of the recordings (200 sentences) are used for training and 20% (50 sentences) are used for testing the performance. Feature extraction Bit stream coding GSM channel errors IP network packet loss Decoding and recovery Recognition A B C D E F Result Voice recordings Figure 2. A summary of the test bed showing the steps from recorded voice input at the DSR front-end to the final recognition result from the speech recogniser. Accepted after abstract review page 470

4 3. EXPERIMENTS 3.1 Performance of DSR over GSM channel The error masks from the GSM channel are obtained from simulations with a combination of signal loss, noise, number of multipaths and speed to get the various BER values. Table 1. The effect of GSM bit errors on recognition performance GSM Condition GSM BER % Word Accuracy No errors Medium 1.2e Medium/Poor 8.9e Poor 6.67e Performance of DSR over IP network The test files are modified with the bursty packet loss characteristics of IP networks according to Table 3, where Packet Loss Rate are experienced values. For algorithm 1, the packets are numbered and sent, and if a packet is lost it is replaced with a fixed error pattern (no interpolation by the receiver). IP packet sizes of 12 and 24 bytes of data are tested. A second algorithm, which in addition sends the packet twice if it contains the multiframe header, is tested only under very high packet loss rate conditions. Table 2. The effect of IP packet loss on recognition performance IP network characteristics % Word Accuracy Algorithm 1 % Word Accuracy Algorithm 2 p q Packet Loss 12 byte 24 byte 12 byte 24 byte Rate No loss % % % % % % % Performance of DSR over GSM and IP network in tandem The last test is to combine the GSM channel and IP network in tandem. The files modified to a certain BER from the GSM channel are further modified with packet loss in the range from 5-15 %. Table 3. The combined effect of GSM bit errors and IP packet loss on recognition performance GSM BER No IP loss 05% IP loss 10% IP loss 15% IP loss 1.2e e Accepted after abstract review page 471

5 4. CONCLUSIONS The purpose of this paper has been to test the performance of the ETSI DSR algorithm over GSM and IP networks. The training of the speech recogniser and testing of the performance has been done with locally collected data. To get more accurate and optimal results, more data is needed for training and testing. However, the results obtained for the ETSI DSR performance are showing good results even on the background of the small amount of data used. A GSM channel with poor conditions (a bit error rate of 6.7e-3) reduces the recognition performance by 6.3% compared to an errorfree signal. An IP network with normal conditions (packet loss less than 10%) reduces the recognition performance by 0.9%. Even under extremely poor IP network conditions (packet loss of 33%) the recogniser performance is reduced by as little as 5.6%. To get this result it is enough to use a simple packetising method where the packets are numbered (so that the receiver can detect if a packet is lost) and replace lost packets with a fixed error pattern without interpolation or re-transmission. A GSM radio channel and IP network may well be used in tandem. If the IP packet loss is less than 10%, then the effect of IP packet loss is insignificant also in combination with GSM bit errors. 5. FUTURE WORK There is obvious redundancy in the voice signal when a high IP packet loss of 33% is found to reduce the recognition performance by as little as 5.6%. New ways of compressing the feature vectors to obtain even lower bit rates can be designed. Also there are other and more elaborate ways to packetise the bit stream file across IP network and interpolate for lost packets at the receiver. Specifically, a new Frame Pair Alignment method can be tested where the multiframe header and feature vector frame pairs are aligned with the IP packet boundaries. 6. ACKNOWLEDGEMENTS Thank you to colleagues at Newcastle University and Sør-Trøndelag University College that have been very helpful with running the software on combined Windows and Linux platforms. Joshua Wall have written the programs for modifying the files with GSM bit errors and IP packet loss. Trym Holther and Gabriel Brabant have been very helpful with various steps in the process of speech recognition. This work has been supported by TISIP research and development foundation. 7. REFERENCES ETSI (2000), ETSI Standard ETSI ES v.1.1.2, ( Pearce, D. (2000) Enabling New Speech Driven Services for Mobile Devices. AVIOS 2000:The Speech Applications Conference, May 22-24, 2000 San Jose, CA, USA. Riskin, E. A. & Boulis C. & Otterson S. & Ostendorf M. (2001) Graceful Degradation of Speech Recognition Performance Over Lossy Packet Networks. Eurospeech 2001, September 3-7, 2001 Aalborg, Denmark Accepted after abstract review page 472

How To Recognize Voice Over Ip On Pc Or Mac Or Ip On A Pc Or Ip (Ip) On A Microsoft Computer Or Ip Computer On A Mac Or Mac (Ip Or Ip) On An Ip Computer Or Mac Computer On An Mp3

How To Recognize Voice Over Ip On Pc Or Mac Or Ip On A Pc Or Ip (Ip) On A Microsoft Computer Or Ip Computer On A Mac Or Mac (Ip Or Ip) On An Ip Computer Or Mac Computer On An Mp3 Recognizing Voice Over IP: A Robust Front-End for Speech Recognition on the World Wide Web. By C.Moreno, A. Antolin and F.Diaz-de-Maria. Summary By Maheshwar Jayaraman 1 1. Introduction Voice Over IP is

More information

Spot me if you can: Uncovering spoken phrases in encrypted VoIP conversations

Spot me if you can: Uncovering spoken phrases in encrypted VoIP conversations Spot me if you can: Uncovering spoken phrases in encrypted VoIP conversations C. Wright, L. Ballard, S. Coull, F. Monrose, G. Masson Talk held by Goran Doychev Selected Topics in Information Security and

More information

Clearing the Way for VoIP

Clearing the Way for VoIP Gen2 Ventures White Paper Clearing the Way for VoIP An Alternative to Expensive WAN Upgrades Executive Overview Enterprises have traditionally maintained separate networks for their voice and data traffic.

More information

GSM speech coding. Wolfgang Leister Forelesning INF 5080 Vårsemester 2004. Norsk Regnesentral

GSM speech coding. Wolfgang Leister Forelesning INF 5080 Vårsemester 2004. Norsk Regnesentral GSM speech coding Forelesning INF 5080 Vårsemester 2004 Sources This part contains material from: Web pages Universität Bremen, Arbeitsbereich Nachrichtentechnik (ANT): Prof.K.D. Kammeyer, Jörg Bitzer,

More information

Introduction to Packet Voice Technologies and VoIP

Introduction to Packet Voice Technologies and VoIP Introduction to Packet Voice Technologies and VoIP Cisco Networking Academy Program Halmstad University Olga Torstensson 035-167575 olga.torstensson@ide.hh.se IP Telephony 1 Traditional Telephony 2 Basic

More information

AUTOMATIC PHONEME SEGMENTATION WITH RELAXED TEXTUAL CONSTRAINTS

AUTOMATIC PHONEME SEGMENTATION WITH RELAXED TEXTUAL CONSTRAINTS AUTOMATIC PHONEME SEGMENTATION WITH RELAXED TEXTUAL CONSTRAINTS PIERRE LANCHANTIN, ANDREW C. MORRIS, XAVIER RODET, CHRISTOPHE VEAUX Very high quality text-to-speech synthesis can be achieved by unit selection

More information

Module 5. Broadcast Communication Networks. Version 2 CSE IIT, Kharagpur

Module 5. Broadcast Communication Networks. Version 2 CSE IIT, Kharagpur Module 5 Broadcast Communication Networks Lesson 9 Cellular Telephone Networks Specific Instructional Objectives At the end of this lesson, the student will be able to: Explain the operation of Cellular

More information

Web-Conferencing System SAViiMeeting

Web-Conferencing System SAViiMeeting Web-Conferencing System SAViiMeeting Alexei Machovikov Department of Informatics and Computer Technologies National University of Mineral Resources Mining St-Petersburg, Russia amachovikov@gmail.com Abstract

More information

Performance Evaluation of VoIP Services using Different CODECs over a UMTS Network

Performance Evaluation of VoIP Services using Different CODECs over a UMTS Network Performance Evaluation of VoIP Services using Different CODECs over a UMTS Network Jianguo Cao School of Electrical and Computer Engineering RMIT University Melbourne, VIC 3000 Australia Email: j.cao@student.rmit.edu.au

More information

Communication Networks. MAP-TELE 2011/12 José Ruela

Communication Networks. MAP-TELE 2011/12 José Ruela Communication Networks MAP-TELE 2011/12 José Ruela Network basic mechanisms Introduction to Communications Networks Communications networks Communications networks are used to transport information (data)

More information

Basic principles of Voice over IP

Basic principles of Voice over IP Basic principles of Voice over IP Dr. Peter Počta {pocta@fel.uniza.sk} Department of Telecommunications and Multimedia Faculty of Electrical Engineering University of Žilina, Slovakia Outline VoIP Transmission

More information

Mobile IP Network Layer Lesson 01 OSI (open systems interconnection) Seven Layer Model and Internet Protocol Layers

Mobile IP Network Layer Lesson 01 OSI (open systems interconnection) Seven Layer Model and Internet Protocol Layers Mobile IP Network Layer Lesson 01 OSI (open systems interconnection) Seven Layer Model and Internet Protocol Layers Oxford University Press 2007. All rights reserved. 1 OSI (open systems interconnection)

More information

Perceived Speech Quality Prediction for Voice over IP-based Networks

Perceived Speech Quality Prediction for Voice over IP-based Networks Perceived Speech Quality Prediction for Voice over IP-based Networks Lingfen Sun and Emmanuel C. Ifeachor Department of Communication and Electronic Engineering, University of Plymouth, Plymouth PL 8AA,

More information

QoS issues in Voice over IP

QoS issues in Voice over IP COMP9333 Advance Computer Networks Mini Conference QoS issues in Voice over IP Student ID: 3058224 Student ID: 3043237 Student ID: 3036281 Student ID: 3025715 QoS issues in Voice over IP Abstract: This

More information

Simple Voice over IP (VoIP) Implementation

Simple Voice over IP (VoIP) Implementation Simple Voice over IP (VoIP) Implementation ECE Department, University of Florida Abstract Voice over IP (VoIP) technology has many advantages over the traditional Public Switched Telephone Networks. In

More information

VoIP Technologies Lecturer : Dr. Ala Khalifeh Lecture 4 : Voice codecs (Cont.)

VoIP Technologies Lecturer : Dr. Ala Khalifeh Lecture 4 : Voice codecs (Cont.) VoIP Technologies Lecturer : Dr. Ala Khalifeh Lecture 4 : Voice codecs (Cont.) 1 Remember first the big picture VoIP network architecture and some terminologies Voice coders 2 Audio and voice quality measuring

More information

Voice over IP. Demonstration 1: VoIP Protocols. Network Environment

Voice over IP. Demonstration 1: VoIP Protocols. Network Environment Voice over IP Demonstration 1: VoIP Protocols Network Environment We use two Windows workstations from the production network, both with OpenPhone application (figure 1). The OpenH.323 project has developed

More information

Digital Speech Coding

Digital Speech Coding Digital Speech Processing David Tipper Associate Professor Graduate Program of Telecommunications and Networking University of Pittsburgh Telcom 2720 Slides 7 http://www.sis.pitt.edu/~dtipper/tipper.html

More information

Final Exam. Route Computation: One reason why link state routing is preferable to distance vector style routing.

Final Exam. Route Computation: One reason why link state routing is preferable to distance vector style routing. UCSD CSE CS 123 Final Exam Computer Networks Directions: Write your name on the exam. Write something for every question. You will get some points if you attempt a solution but nothing for a blank sheet

More information

What is DECT? DECT stands for Digital Enhanced Cordless Telecommunications.

What is DECT? DECT stands for Digital Enhanced Cordless Telecommunications. DECT 6.0 vs 900 MHz vs 2.4GHz vs 5.8 GHz DECT 6.0 (1.9 GHz) 900 MHz 2.4 GHz 5.8 GHz FCC approved frequency for cordless telecommunication Baby monitors, microwave oven Wi-Fi electronics (routers), wireless

More information

AN ANALYSIS OF DELAY OF SMALL IP PACKETS IN CELLULAR DATA NETWORKS

AN ANALYSIS OF DELAY OF SMALL IP PACKETS IN CELLULAR DATA NETWORKS AN ANALYSIS OF DELAY OF SMALL IP PACKETS IN CELLULAR DATA NETWORKS Hubert GRAJA, Philip PERRY and John MURPHY Performance Engineering Laboratory, School of Electronic Engineering, Dublin City University,

More information

APPLYING MFCC-BASED AUTOMATIC SPEAKER RECOGNITION TO GSM AND FORENSIC DATA

APPLYING MFCC-BASED AUTOMATIC SPEAKER RECOGNITION TO GSM AND FORENSIC DATA APPLYING MFCC-BASED AUTOMATIC SPEAKER RECOGNITION TO GSM AND FORENSIC DATA Tuija Niemi-Laitinen*, Juhani Saastamoinen**, Tomi Kinnunen**, Pasi Fränti** *Crime Laboratory, NBI, Finland **Dept. of Computer

More information

Membering T M : A Conference Call Service with Speaker-Independent Name Dialing on AIN

Membering T M : A Conference Call Service with Speaker-Independent Name Dialing on AIN PAGE 30 Membering T M : A Conference Call Service with Speaker-Independent Name Dialing on AIN Sung-Joon Park, Kyung-Ae Jang, Jae-In Kim, Myoung-Wan Koo, Chu-Shik Jhon Service Development Laboratory, KT,

More information

Introduction, Rate and Latency

Introduction, Rate and Latency Introduction, Rate and Latency Communication Networks Why communicate? Necessary to support some application. Example Applications Audio communication Radio, Telephone Text communication Email, SMS (text

More information

APTA TransiTech Conference Communications: Vendor Perspective (TT) Phoenix, Arizona, Tuesday, 3.19.13. VoIP Solution (101)

APTA TransiTech Conference Communications: Vendor Perspective (TT) Phoenix, Arizona, Tuesday, 3.19.13. VoIP Solution (101) APTA TransiTech Conference Communications: Vendor Perspective (TT) Phoenix, Arizona, Tuesday, 3.19.13 VoIP Solution (101) Agenda Items Introduction What is VoIP? Codecs Mean opinion score (MOS) Bandwidth

More information

Broadband Networks. Prof. Dr. Abhay Karandikar. Electrical Engineering Department. Indian Institute of Technology, Bombay. Lecture - 29.

Broadband Networks. Prof. Dr. Abhay Karandikar. Electrical Engineering Department. Indian Institute of Technology, Bombay. Lecture - 29. Broadband Networks Prof. Dr. Abhay Karandikar Electrical Engineering Department Indian Institute of Technology, Bombay Lecture - 29 Voice over IP So, today we will discuss about voice over IP and internet

More information

Information Leakage in Encrypted Network Traffic

Information Leakage in Encrypted Network Traffic Information Leakage in Encrypted Network Traffic Attacks and Countermeasures Scott Coull RedJack Joint work with: Charles Wright (MIT LL) Lucas Ballard (Google) Fabian Monrose (UNC) Gerald Masson (JHU)

More information

Data Link Layer Overview

Data Link Layer Overview Data Link Layer Overview Date link layer deals with two basic issues: Part I How data frames can be reliably transmitted, and Part II How a shared communication medium can be accessed In many networks,

More information

Chapter 6: Broadcast Systems. Mobile Communications. Unidirectional distribution systems DVB DAB. High-speed Internet. architecture Container

Chapter 6: Broadcast Systems. Mobile Communications. Unidirectional distribution systems DVB DAB. High-speed Internet. architecture Container Mobile Communications Chapter 6: Broadcast Systems Unidirectional distribution systems DAB DVB architecture Container High-speed Internet Prof. Dr.-Ing. Jochen Schiller, http://www.jochenschiller.de/ MC

More information

PERFORMANCE OF THE GPRS RLC/MAC PROTOCOLS WITH VOIP TRAFFIC

PERFORMANCE OF THE GPRS RLC/MAC PROTOCOLS WITH VOIP TRAFFIC PERFORMANCE OF THE GPRS RLC/MAC PROTOCOLS WITH VOIP TRAFFIC Boris Bellalta 1, Miquel Oliver 1, David Rincón 2 1 Universitat Pompeu Fabra, Psg. Circumval lació 8, 83 - Barcelona, Spain, boris.bellalta,

More information

Mathematical Modelling of Computer Networks: Part II. Module 1: Network Coding

Mathematical Modelling of Computer Networks: Part II. Module 1: Network Coding Mathematical Modelling of Computer Networks: Part II Module 1: Network Coding Lecture 3: Network coding and TCP 12th November 2013 Laila Daniel and Krishnan Narayanan Dept. of Computer Science, University

More information

How To Understand The Differences Between A Fax And A Fax On A G3 Network

How To Understand The Differences Between A Fax And A Fax On A G3 Network The Fax on IP Networks White Paper February 2011 2 The Fax on IP Networks Contents Overview... 3 Group 3 Fax Technology... 4 G.711 Fax Pass-Through... 5 T.38 IP Fax Relay... 6 Network Design Considerations...

More information

Ericsson T18s Voice Dialing Simulator

Ericsson T18s Voice Dialing Simulator Ericsson T18s Voice Dialing Simulator Mauricio Aracena Kovacevic, Anna Dehlbom, Jakob Ekeberg, Guillaume Gariazzo, Eric Lästh and Vanessa Troncoso Dept. of Signals Sensors and Systems Royal Institute of

More information

Voice Over IP Per Call Bandwidth Consumption

Voice Over IP Per Call Bandwidth Consumption Over IP Per Call Bandwidth Consumption Interactive: This document offers customized voice bandwidth calculations with the TAC Bandwidth Calculator ( registered customers only) tool. Introduction Before

More information

Wireless LAN Concepts

Wireless LAN Concepts Wireless LAN Concepts Wireless LAN technology is becoming increasingly popular for a wide variety of applications. After evaluating the technology, most users are convinced of its reliability, satisfied

More information

School Class Monitoring System Based on Audio Signal Processing

School Class Monitoring System Based on Audio Signal Processing C. R. Rashmi 1,,C.P.Shantala 2 andt.r.yashavanth 3 1 Department of CSE, PG Student, CIT, Gubbi, Tumkur, Karnataka, India. 2 Department of CSE, Vice Principal & HOD, CIT, Gubbi, Tumkur, Karnataka, India.

More information

How To Analyze The Security On An Ipa Wireless Sensor Network

How To Analyze The Security On An Ipa Wireless Sensor Network Throughput Analysis of WEP Security in Ad Hoc Sensor Networks Mohammad Saleh and Iyad Al Khatib iitc Stockholm, Sweden {mohsaleh, iyad}@iitc.se ABSTRACT This paper presents a performance investigation

More information

Transport Layer Protocols

Transport Layer Protocols Transport Layer Protocols Version. Transport layer performs two main tasks for the application layer by using the network layer. It provides end to end communication between two applications, and implements

More information

Objectives of Lecture. Network Architecture. Protocols. Contents

Objectives of Lecture. Network Architecture. Protocols. Contents Objectives of Lecture Network Architecture Show how network architecture can be understood using a layered approach. Introduce the OSI seven layer reference model. Introduce the concepts of internetworking

More information

White Paper. PESQ: An Introduction. Prepared by: Psytechnics Limited. 23 Museum Street Ipswich, Suffolk United Kingdom IP1 1HN

White Paper. PESQ: An Introduction. Prepared by: Psytechnics Limited. 23 Museum Street Ipswich, Suffolk United Kingdom IP1 1HN PESQ: An Introduction White Paper Prepared by: Psytechnics Limited 23 Museum Street Ipswich, Suffolk United Kingdom IP1 1HN t: +44 (0) 1473 261 800 f: +44 (0) 1473 261 880 e: info@psytechnics.com September

More information

Performance Evaluation of AODV, OLSR Routing Protocol in VOIP Over Ad Hoc

Performance Evaluation of AODV, OLSR Routing Protocol in VOIP Over Ad Hoc (International Journal of Computer Science & Management Studies) Vol. 17, Issue 01 Performance Evaluation of AODV, OLSR Routing Protocol in VOIP Over Ad Hoc Dr. Khalid Hamid Bilal Khartoum, Sudan dr.khalidbilal@hotmail.com

More information

Hardware Implementation of Probabilistic State Machine for Word Recognition

Hardware Implementation of Probabilistic State Machine for Word Recognition IJECT Vo l. 4, Is s u e Sp l - 5, Ju l y - Se p t 2013 ISSN : 2230-7109 (Online) ISSN : 2230-9543 (Print) Hardware Implementation of Probabilistic State Machine for Word Recognition 1 Soorya Asokan, 2

More information

Wide Area Networks. Learning Objectives. LAN and WAN. School of Business Eastern Illinois University. (Week 11, Thursday 3/22/2007)

Wide Area Networks. Learning Objectives. LAN and WAN. School of Business Eastern Illinois University. (Week 11, Thursday 3/22/2007) School of Business Eastern Illinois University Wide Area Networks (Week 11, Thursday 3/22/2007) Abdou Illia, Spring 2007 Learning Objectives 2 Distinguish between LAN and WAN Distinguish between Circuit

More information

Multimedia Communications Voice over IP

Multimedia Communications Voice over IP Multimedia Communications Voice over IP Anandi Giridharan Electrical Communication Engineering, Indian Institute of Science, Bangalore 560012, India Voice over IP (Real time protocols) Internet Telephony

More information

Objective Speech Quality Measures for Internet Telephony

Objective Speech Quality Measures for Internet Telephony Objective Speech Quality Measures for Internet Telephony Timothy A. Hall National Institute of Standards and Technology 100 Bureau Drive, STOP 8920 Gaithersburg, MD 20899-8920 ABSTRACT Measuring voice

More information

IBM Research Report. CSR: Speaker Recognition from Compressed VoIP Packet Stream

IBM Research Report. CSR: Speaker Recognition from Compressed VoIP Packet Stream RC23499 (W0501-090) January 19, 2005 Computer Science IBM Research Report CSR: Speaker Recognition from Compressed Packet Stream Charu Aggarwal, David Olshefski, Debanjan Saha, Zon-Yin Shae, Philip Yu

More information

A Network Performance Application for Modeling, Simulation, and Characterization of Packet Network Behavior

A Network Performance Application for Modeling, Simulation, and Characterization of Packet Network Behavior A Network Performance Application for Modeling, Simulation, and Characterization of Packet Network Behavior Christopher M. White, Edward J. Daniel, and Keith A. Teague School of Electrical and Computer

More information

First Semester Examinations 2011/12 INTERNET PRINCIPLES

First Semester Examinations 2011/12 INTERNET PRINCIPLES PAPER CODE NO. EXAMINER : Martin Gairing COMP211 DEPARTMENT : Computer Science Tel. No. 0151 795 4264 First Semester Examinations 2011/12 INTERNET PRINCIPLES TIME ALLOWED : Two Hours INSTRUCTIONS TO CANDIDATES

More information

Calculating Bandwidth Requirements

Calculating Bandwidth Requirements Calculating Bandwidth Requirements Codec Bandwidths This topic describes the bandwidth that each codec uses and illustrates its impact on total bandwidth. Bandwidth Implications of Codec 22 One of the

More information

Appendix C GSM System and Modulation Description

Appendix C GSM System and Modulation Description C1 Appendix C GSM System and Modulation Description C1. Parameters included in the modelling In the modelling the number of mobiles and their positioning with respect to the wired device needs to be taken

More information

Technical Training Seminar on Troubleshooting the Triple Play Services for CCTA Member Companies August 24, 25, 26, 2010 San Juan, Puerto Rico

Technical Training Seminar on Troubleshooting the Triple Play Services for CCTA Member Companies August 24, 25, 26, 2010 San Juan, Puerto Rico Technical Training Seminar on Troubleshooting the Triple Play Services for CCTA Member Companies August 24, 25, 26, 2010 San Juan, Puerto Rico Mario Sebastiani Tony Holmes Seminar Overview Digital Troubleshooting

More information

Assessing the quality of VoIP transmission affected by playout buffer scheme and encoding scheme

Assessing the quality of VoIP transmission affected by playout buffer scheme and encoding scheme Assessing the quality of VoIP transmission affected by playout buffer scheme and encoding scheme Miroslaw Narbutt, Mark Davis Communications Network Research Institute Dublin Institute of Technology Wireless

More information

Applicability of UDP-Lite for Voice over IP in UMTS Networks

Applicability of UDP-Lite for Voice over IP in UMTS Networks Applicability of -Lite for Voice over IP in UMTS Networks Frank Mertz, Ulrich Engelke, Peter Vary RWTH Aachen University, Institute of Communication Systems and Data Processing (IND) D-5256 Aachen, Germany

More information

The OSI model has seven layers. The principles that were applied to arrive at the seven layers can be briefly summarized as follows:

The OSI model has seven layers. The principles that were applied to arrive at the seven layers can be briefly summarized as follows: 1.4 Reference Models Now that we have discussed layered networks in the abstract, it is time to look at some examples. In the next two sections we will discuss two important network architectures, the

More information

An Analysis of Error Handling Techniques in Voice over IP

An Analysis of Error Handling Techniques in Voice over IP An Analysis of Error Handling Techniques in Voice over IP Martin John Lipka ABSTRACT The use of Voice over IP (VoIP) has been growing in popularity, but unlike its wired circuit-switched telephone network

More information

Data Link Layer(1) Principal service: Transferring data from the network layer of the source machine to the one of the destination machine

Data Link Layer(1) Principal service: Transferring data from the network layer of the source machine to the one of the destination machine Data Link Layer(1) Principal service: Transferring data from the network layer of the source machine to the one of the destination machine Virtual communication versus actual communication: Specific functions

More information

Performance Issues of TCP and MPEG-4 4 over UMTS

Performance Issues of TCP and MPEG-4 4 over UMTS Performance Issues of TCP and MPEG-4 4 over UMTS Anthony Lo A.Lo@ewi.tudelft.nl 1 Wiskunde end Informatica Outline UMTS Overview TCP and MPEG-4 Performance Summary 2 1 Universal Mobile Telecommunications

More information

Requirements of Voice in an IP Internetwork

Requirements of Voice in an IP Internetwork Requirements of Voice in an IP Internetwork Real-Time Voice in a Best-Effort IP Internetwork This topic lists problems associated with implementation of real-time voice traffic in a best-effort IP internetwork.

More information

1. Overview. 2. F-bit Utilization

1. Overview. 2. F-bit Utilization 1. Overview... 1 2. F-bit Utilization... 1 3. T1 Line Signal... 2 4. T1 Alarm Conditions... 3 5. 64 kbps Channel Characteristics... 3 6. Timeslot Handling... 3 7. Unframed Mode... 4 1. Overview The T1

More information

Speech Recognition on Cell Broadband Engine UCRL-PRES-223890

Speech Recognition on Cell Broadband Engine UCRL-PRES-223890 Speech Recognition on Cell Broadband Engine UCRL-PRES-223890 Yang Liu, Holger Jones, John Johnson, Sheila Vaidya (Lawrence Livermore National Laboratory) Michael Perrone, Borivoj Tydlitat, Ashwini Nanda

More information

Protocols and Architecture. Protocol Architecture.

Protocols and Architecture. Protocol Architecture. Protocols and Architecture Protocol Architecture. Layered structure of hardware and software to support exchange of data between systems/distributed applications Set of rules for transmission of data between

More information

SIP Trunking and Voice over IP

SIP Trunking and Voice over IP SIP Trunking and Voice over IP Agenda What is SIP Trunking? SIP Signaling How is Voice encoded and transported? What are the Voice over IP Impairments? How is Voice Quality measured? VoIP Technology Confidential

More information

Audio and Video for the Internet

Audio and Video for the Internet RTP Audio and Video for the Internet Colin Perkins TT rvaddison-wesley Boston San Francisco New York Toronto Montreal London Munich Paris Madrid Capetown Sydney 'lokyo Singapore Mexico City CONTENTS PREFACE

More information

WAN Performance Analysis A Study on the Impact of Windows 7

WAN Performance Analysis A Study on the Impact of Windows 7 A Talari Networks White Paper WAN Performance Analysis A Study on the Impact of Windows 7 Test results demonstrating WAN performance changes due to upgrading to Windows 7 and the network architecture and

More information

Operational Ver. 0.03 Recommendation January 2011

Operational Ver. 0.03 Recommendation January 2011 TETRA Association TOR001 Operational Ver. 0.03 Recommendation January 2011 Source: TETRA Association Technical Forum Keywords: DMO Air Interface, Operational Recommendation TETRA Association; TETRA Operational

More information

Bandwidth usage of common networking applications

Bandwidth usage of common networking applications Bandwidth usage of common networking applications Overview Bandwidth vs. bandwidth Networking stack review Basic rules for calculating bandwidth usage Examples Calculating bandwidth usage for VOIP Calculating

More information

Transport and Network Layer

Transport and Network Layer Transport and Network Layer 1 Introduction Responsible for moving messages from end-to-end in a network Closely tied together TCP/IP: most commonly used protocol o Used in Internet o Compatible with a

More information

Implementing an In-Service, Non- Intrusive Measurement Device in Telecommunication Networks Using the TMS320C31

Implementing an In-Service, Non- Intrusive Measurement Device in Telecommunication Networks Using the TMS320C31 Disclaimer: This document was part of the First European DSP Education and Research Conference. It may have been written by someone whose native language is not English. TI assumes no liability for the

More information

RESOURCE ALLOCATION FOR INTERACTIVE TRAFFIC CLASS OVER GPRS

RESOURCE ALLOCATION FOR INTERACTIVE TRAFFIC CLASS OVER GPRS RESOURCE ALLOCATION FOR INTERACTIVE TRAFFIC CLASS OVER GPRS Edward Nowicki and John Murphy 1 ABSTRACT The General Packet Radio Service (GPRS) is a new bearer service for GSM that greatly simplify wireless

More information

IJMIE Volume 2, Issue 7 ISSN: 2249-0558

IJMIE Volume 2, Issue 7 ISSN: 2249-0558 Evaluating Performance of Audio conferencing on Reactive Routing Protocols for MANET Alak Kumar Sarkar* Md. Ibrahim Abdullah* Md. Shamim Hossain* Ahsan-ul-Ambia* Abstract Mobile ad hoc network (MANET)

More information

Video-Conferencing System

Video-Conferencing System Video-Conferencing System Evan Broder and C. Christoher Post Introductory Digital Systems Laboratory November 2, 2007 Abstract The goal of this project is to create a video/audio conferencing system. Video

More information

Simulative Investigation of QoS parameters for VoIP over WiMAX networks

Simulative Investigation of QoS parameters for VoIP over WiMAX networks www.ijcsi.org 288 Simulative Investigation of QoS parameters for VoIP over WiMAX networks Priyanka 1, Jyoteesh Malhotra 2, Kuldeep Sharma 3 1,3 Department of Electronics, Ramgarhia Institue of Engineering

More information

1 Introduction to mobile telecommunications

1 Introduction to mobile telecommunications 1 Introduction to mobile telecommunications Mobile phones were first introduced in the early 1980s. In the succeeding years, the underlying technology has gone through three phases, known as generations.

More information

Efficient Data Recovery scheme in PTS-Based OFDM systems with MATRIX Formulation

Efficient Data Recovery scheme in PTS-Based OFDM systems with MATRIX Formulation Efficient Data Recovery scheme in PTS-Based OFDM systems with MATRIX Formulation Sunil Karthick.M PG Scholar Department of ECE Kongu Engineering College Perundurau-638052 Venkatachalam.S Assistant Professor

More information

GSM Network and Services

GSM Network and Services GSM Network and Services GPRS - sharing of resources 1 What is the problem? Many data applications are very bursty in its traffic pattern: http, smtp, pop, telnet,... Why reserve physical resources at

More information

VoIP Bandwidth Calculation

VoIP Bandwidth Calculation VoIP Bandwidth Calculation AI0106A VoIP Bandwidth Calculation Executive Summary Calculating how much bandwidth a Voice over IP call occupies can feel a bit like trying to answer the question; How elastic

More information

Robust Methods for Automatic Transcription and Alignment of Speech Signals

Robust Methods for Automatic Transcription and Alignment of Speech Signals Robust Methods for Automatic Transcription and Alignment of Speech Signals Leif Grönqvist (lgr@msi.vxu.se) Course in Speech Recognition January 2. 2004 Contents Contents 1 1 Introduction 2 2 Background

More information

4. H.323 Components. VOIP, Version 1.6e T.O.P. BusinessInteractive GmbH Page 1 of 19

4. H.323 Components. VOIP, Version 1.6e T.O.P. BusinessInteractive GmbH Page 1 of 19 4. H.323 Components VOIP, Version 1.6e T.O.P. BusinessInteractive GmbH Page 1 of 19 4.1 H.323 Terminals (1/2)...3 4.1 H.323 Terminals (2/2)...4 4.1.1 The software IP phone (1/2)...5 4.1.1 The software

More information

CSMA/CA. Information Networks p. 1

CSMA/CA. Information Networks p. 1 Information Networks p. 1 CSMA/CA IEEE 802.11 standard for WLAN defines a distributed coordination function (DCF) for sharing access to the medium based on the CSMA/CA protocol Collision detection is not

More information

Attenuation (amplitude of the wave loses strength thereby the signal power) Refraction Reflection Shadowing Scattering Diffraction

Attenuation (amplitude of the wave loses strength thereby the signal power) Refraction Reflection Shadowing Scattering Diffraction Wireless Physical Layer Q1. Is it possible to transmit a digital signal, e.g., coded as square wave as used inside a computer, using radio transmission without any loss? Why? It is not possible to transmit

More information

Enabling Speech Based Access to Information Management Systems over Wireless Network

Enabling Speech Based Access to Information Management Systems over Wireless Network Enabling Speech Based Access to Information Management Systems over Wireless Network M. Bagein, O. Pietquin, C. Ris and G. Wilfart 1 Faculté Polytechnique de Mons - TCTS Lab. Parc Initialis - Av. Copernic,

More information

Introduction VOIP in an 802.11 Network VOIP 3

Introduction VOIP in an 802.11 Network VOIP 3 Solutions to Performance Problems in VOIP over 802.11 Wireless LAN Wei Wang, Soung C. Liew Presented By Syed Zaidi 1 Outline Introduction VOIP background Problems faced in 802.11 Low VOIP capacity in 802.11

More information

Myanmar Continuous Speech Recognition System Based on DTW and HMM

Myanmar Continuous Speech Recognition System Based on DTW and HMM Myanmar Continuous Speech Recognition System Based on DTW and HMM Ingyin Khaing Department of Information and Technology University of Technology (Yatanarpon Cyber City),near Pyin Oo Lwin, Myanmar Abstract-

More information

Curso de Telefonía IP para el MTC. Sesión 2 Requerimientos principales. Mg. Antonio Ocampo Zúñiga

Curso de Telefonía IP para el MTC. Sesión 2 Requerimientos principales. Mg. Antonio Ocampo Zúñiga Curso de Telefonía IP para el MTC Sesión 2 Requerimientos principales Mg. Antonio Ocampo Zúñiga Factors Affecting Audio Clarity Fidelity: Audio accuracy or quality Echo: Usually due to impedance mismatch

More information

Network Simulation Traffic, Paths and Impairment

Network Simulation Traffic, Paths and Impairment Network Simulation Traffic, Paths and Impairment Summary Network simulation software and hardware appliances can emulate networks and network hardware. Wide Area Network (WAN) emulation, by simulating

More information

A study of Skype over IEEE 802.16 networks: voice quality and bandwidth usage

A study of Skype over IEEE 802.16 networks: voice quality and bandwidth usage Iowa State University Digital Repository @ Iowa State University Graduate Theses and Dissertations Graduate College 2011 A study of Skype over IEEE 802.16 networks: voice quality and bandwidth usage Kuan-yu

More information

WebEx. Network Bandwidth White Paper. WebEx Communications Inc. - 1 -

WebEx. Network Bandwidth White Paper. WebEx Communications Inc. - 1 - WebEx Network Bandwidth White Paper WebEx Communications Inc. - 1 - Copyright WebEx Communications, Inc. reserves the right to make changes in the information contained in this publication without prior

More information

Turkish Radiology Dictation System

Turkish Radiology Dictation System Turkish Radiology Dictation System Ebru Arısoy, Levent M. Arslan Boaziçi University, Electrical and Electronic Engineering Department, 34342, Bebek, stanbul, Turkey arisoyeb@boun.edu.tr, arslanle@boun.edu.tr

More information

VOIP over Space Networks

VOIP over Space Networks VOIP over Space Networks C. Okino, W. Kwong, J. Pang, J. Gao, and L. Clare Jet Propulsion Laboratory California Institute of Technology Presented at The Fifth Space Internetworking Workshop 2006 Hanover,

More information

VoIP 101. E911-Enhanced 911- Used for providing emergency service on cellular and internet voice calls.

VoIP 101. E911-Enhanced 911- Used for providing emergency service on cellular and internet voice calls. If you ve been researching phone systems for awhile, you ve probably heard the term VoIP. What s the definition? Do you need certain hardware for it to work? There are a few questions that should be answered

More information

2. What is the maximum value of each octet in an IP address? A. 128 B. 255 C. 256 D. None of the above

2. What is the maximum value of each octet in an IP address? A. 128 B. 255 C. 256 D. None of the above 1. How many bits are in an IP address? A. 16 B. 32 C. 64 2. What is the maximum value of each octet in an IP address? A. 128 B. 255 C. 256 3. The network number plays what part in an IP address? A. It

More information

White Paper. ETSI Speech Quality Test Event Calling Testing Speech Quality of a VoIP Gateway

White Paper. ETSI Speech Quality Test Event Calling Testing Speech Quality of a VoIP Gateway White Paper ETSI Speech Quality Test Event Calling Testing Speech Quality of a VoIP Gateway A white paper from the ETSI 3rd SQTE (Speech Quality Test Event) Version 1 July 2005 ETSI Speech Quality Test

More information

Introduction to Metropolitan Area Networks and Wide Area Networks

Introduction to Metropolitan Area Networks and Wide Area Networks Introduction to Metropolitan Area Networks and Wide Area Networks Chapter 9 Learning Objectives After reading this chapter, you should be able to: Distinguish local area networks, metropolitan area networks,

More information

High-Level Data Link Control

High-Level Data Link Control High-Level Data Link Control This class of data link layer protocols includes High-level Data Link Control (HDLC), Link Access Procedure Balanced (LAPB) for X.25, Link Access Procedure for D-channel (LAPD)

More information

JOURNAL OF TELECOMMUNICATIONS, VOLUME 2, ISSUE 2, MAY 2010 126. Simulink based VoIP Analysis. Hardeep Singh Dalhio, Jasvir Singh, M.

JOURNAL OF TELECOMMUNICATIONS, VOLUME 2, ISSUE 2, MAY 2010 126. Simulink based VoIP Analysis. Hardeep Singh Dalhio, Jasvir Singh, M. 126 Simulink based VoIP Analysis Hardeep Singh Dalhio, Jasvir Singh, M. Mian Abstract Voice communication over internet not be possible without a reliable data network, this was first available when distributed

More information

Artificial Neural Network for Speech Recognition

Artificial Neural Network for Speech Recognition Artificial Neural Network for Speech Recognition Austin Marshall March 3, 2005 2nd Annual Student Research Showcase Overview Presenting an Artificial Neural Network to recognize and classify speech Spoken

More information

BCS THE CHARTERED INSTITUTE FOR IT. BCS HIGHER EDUCATION QUALIFICATIONS BCS Level 5 Diploma in IT COMPUTER NETWORKS

BCS THE CHARTERED INSTITUTE FOR IT. BCS HIGHER EDUCATION QUALIFICATIONS BCS Level 5 Diploma in IT COMPUTER NETWORKS BCS THE CHARTERED INSTITUTE FOR IT BCS HIGHER EDUCATION QUALIFICATIONS BCS Level 5 Diploma in IT COMPUTER NETWORKS Friday 2 nd October 2015 Morning Answer any FOUR questions out of SIX. All questions carry

More information

Discussion Paper Category 6 vs Category 5e Cabling Systems and Implications for Voice over IP Networks

Discussion Paper Category 6 vs Category 5e Cabling Systems and Implications for Voice over IP Networks Discussion Paper Category 6 vs Category 5e Cabling Systems and Implications for Voice over IP Networks By Galen Udell Belden CDT Networking 2006 Category 6 vs Category 5e Cabling Systems and Implications

More information

Optimizing Converged Cisco Networks (ONT)

Optimizing Converged Cisco Networks (ONT) Optimizing Converged Cisco Networks (ONT) Module 3: Introduction to IP QoS Introducing QoS Objectives Explain why converged networks require QoS. Identify the major quality issues with converged networks.

More information

Classes of multimedia Applications

Classes of multimedia Applications Classes of multimedia Applications Streaming Stored Audio and Video Streaming Live Audio and Video Real-Time Interactive Audio and Video Others Class: Streaming Stored Audio and Video The multimedia content

More information