Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
REAL-TIME, NON-INTRUSIVE EVALUATION OF
VOIP
USING GENETIC PROGRAMMING
A. Raja1 A. Azad2 C. Flanagan1 C. Ryan2
1Wireless Access Research Centre
Department of Electronic and Computer Engineering
2Bio-Computing and Developmental Systems
Department of Computer Science and Information Sysmtems
University of Limerick, Limerick, Ireland
College of Informatics & Electronics Postgraduate Research
Day 2007
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OUTLINE
1 MOTIVATION
Preamble
The Problem of Speech Quality Assessment
Voice Over IP
Research Goal
2 VOIP SIMULATION ENVIRONMENT
Simulation System
Network Traffic Characteristics
3 GP
4 GP EXPERIMENTS
5 TEST RESULTS
6 CONCLUSIONS
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OUTLINE
1 MOTIVATION
Preamble
The Problem of Speech Quality Assessment
Voice Over IP
Research Goal
2 VOIP SIMULATION ENVIRONMENT
Simulation System
Network Traffic Characteristics
3 GP
4 GP EXPERIMENTS
5 TEST RESULTS
6 CONCLUSIONS
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OUTLINE
1 MOTIVATION
Preamble
The Problem of Speech Quality Assessment
Voice Over IP
Research Goal
2 VOIP SIMULATION ENVIRONMENT
Simulation System
Network Traffic Characteristics
3 GP
4 GP EXPERIMENTS
5 TEST RESULTS
6 CONCLUSIONS
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OUTLINE
1 MOTIVATION
Preamble
The Problem of Speech Quality Assessment
Voice Over IP
Research Goal
2 VOIP SIMULATION ENVIRONMENT
Simulation System
Network Traffic Characteristics
3 GP
4 GP EXPERIMENTS
5 TEST RESULTS
6 CONCLUSIONS
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OUTLINE
1 MOTIVATION
Preamble
The Problem of Speech Quality Assessment
Voice Over IP
Research Goal
2 VOIP SIMULATION ENVIRONMENT
Simulation System
Network Traffic Characteristics
3 GP
4 GP EXPERIMENTS
5 TEST RESULTS
6 CONCLUSIONS
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OUTLINE
1 MOTIVATION
Preamble
The Problem of Speech Quality Assessment
Voice Over IP
Research Goal
2 VOIP SIMULATION ENVIRONMENT
Simulation System
Network Traffic Characteristics
3 GP
4 GP EXPERIMENTS
5 TEST RESULTS
6 CONCLUSIONS
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
PREAMBLE
VoIP – A paradigm shift
Bandwidth redundancy exploitation
QoS remains dominated by network/transport layer
degradations
Quality assessment ...
Reflects upon the operating conditions of the network
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
PREAMBLE
VoIP – A paradigm shift
Bandwidth redundancy exploitation
QoS remains dominated by network/transport layer
degradations
Quality assessment ...
Reflects upon the operating conditions of the network
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
PREAMBLE
VoIP – A paradigm shift
Bandwidth redundancy exploitation
QoS remains dominated by network/transport layer
degradations
Quality assessment ...
Reflects upon the operating conditions of the network
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
PREAMBLE
VoIP – A paradigm shift
Bandwidth redundancy exploitation
QoS remains dominated by network/transport layer
degradations
Quality assessment ...
Reflects upon the operating conditions of the network
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
PREAMBLE
VoIP – A paradigm shift
Bandwidth redundancy exploitation
QoS remains dominated by network/transport layer
degradations
Quality assessment ...
Reflects upon the operating conditions of the network
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
PREAMBLE
VoIP – A paradigm shift
Bandwidth redundancy exploitation
QoS remains dominated by network/transport layer
degradations
Quality assessment ...
Reflects upon the operating conditions of the network
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
SPEECH QUALITY ASSESSMENT METHODOLOGIES
Two approaches to speech quality Assessment
1 Subjective Assessment
2 Objective Assessment
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
SUBJECTIVE ASSESSMENT OF SPEECH QUALITY
Speech quality is estimated by humans.
Advantage – Reliable results.
Limitations
1 Expensive
2 Time Consuming
3 Laborious
4 Lack of Repeatability
Mean Opinion Score (MOS) is the measure of quality.
1 – bad
5 – Excellent
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OBJECTIVE ASSESSMENT OF SPEECH QUALITY
A computer automated fast and reliable program is used to
assay human perception of speech quality
Two approaches:
1 Intrusive Assessment
2 Non-Intrusive Assessment
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OBJECTIVE ASSESSMENT OF SPEECH QUALITY
INTRUSIVE ASSESSMENT
The signal under test is compared against a corresponding
reference signal.
Advantages:
1 The most reliable artificial means of estimating speech
quality
2 Tests can be repeated easily
Limitations:
1 Consumes considerable computing resources.
2 Is not useful for continuous monitoring of quality due to
requirement of a reference signal.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OBJECTIVE ASSESSMENT OF SPEECH QUALITY
INTRUSIVE ASSESSMENT
The signal under test is compared against a corresponding
reference signal.
Advantages:
1 The most reliable artificial means of estimating speech
quality
2 Tests can be repeated easily
Limitations:
1 Consumes considerable computing resources.
2 Is not useful for continuous monitoring of quality due to
requirement of a reference signal.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OBJECTIVE ASSESSMENT OF SPEECH QUALITY
ITU-T P.862 (PESQ)
PESQ algorithm is the current ITU-T Recommendation for
intrusive speech quality estimation.
The speech signal is mapped from time domain to
time-frequency representation using the psychophysical
equivalents of frequency and intensity.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OBJECTIVE ASSESSMENT OF SPEECH QUALITY
ITU-T P.862 (PESQ)
It has shown a high correlation with various ITU-T
benchmark tests.
For 30 ITU-T subjective tests the Pearson’s Correlation
Coefficient (R) was 0.935
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OBJECTIVE ASSESSMENT OF SPEECH QUALITY
NON-INTRUSIVE ASSESSMENT
A challenging problem since a reference is not available.
Two approaches exist
1 Signal-based models
2 Parametric models
Signal-based models
Recent approaches are based on emulating
1 Human speech production model
2 Psychoacoustic processing of human ear
ITU-T P.563 is the current Recommendation.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OBJECTIVE ASSESSMENT OF SPEECH QUALITY
NON-INTRUSIVE ASSESSMENT
A challenging problem since a reference is not available.
Two approaches exist
1 Signal-based models
2 Parametric models
Signal-based models
Recent approaches are based on emulating
1 Human speech production model
2 Psychoacoustic processing of human ear
ITU-T P.563 is the current Recommendation.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
OBJECTIVE ASSESSMENT OF SPEECH QUALITY
PARAMETRIC MEASUREMENT OF VOIP QUALITY
Functions of transport layer metrics and other measurable
quantities.
Cogent metrics may be:
Packet Loss Rate
Variable delay – jitter
End-to-end delay
. . .
Aimed at Real-time and continuous evaluation of quality
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
VOICE OVER IP – VOIP
Packet based communication channel
Uses wire-line speech codecs
Linear Predictive Coding (LPC) is having vogue
Coded frames are packetized into RTP/UDP
Internet is used for transportation
The receiver does the reverse process
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
RESEARCH GOAL
Derivation of a VoIP listening Quality estimation model as a
function of transport layer metrics.
Genetic Programming based Symbolic Regression is used
Using the PESQ algorithm as the reference system
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
VOIP SIMULATION ENVIRONMENT
PACKET LOSS SIMULATION – THE GILBERT ELLIOT MODEL
mlr = p
p+q (1)
mbl = 1
q (2)
clp = 1 − q (3)
mbl = 1
1−clp (4)
Where
mlr – mean loss rate
mbl – mean burst length
clp – conditional loss probability
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
VOIP SIMULATION ENVIRONMENT
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
NETWORK TRAFFIC PARAMETERS
No. Parameter Name Abbreviation
1 Bit-rate (kbps) br
2 mean loss rate mlr
3 mean burst length mbl
4 Packetization Interval (ms) PI
5 Frame duration (ms) fd
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
NETWORK TRAFFIC SCENARIOS
No. Parameter Range
1 br G.729 (8 kbps), G.723.1 (6.3 kbps),
AMR 7.4 and 12.2 kbps
2 mlr [0,2.5,3.5,. . . 15,20,25,. . . 40]%
3 mbl 10, 50, 60, 70 and 80%
4 PI 10-60 ms
5 fd 10, 20, 30 ms
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
A BRIEF INTRO
GP is a Machine Learning Technique inspired by biological
evolution. A branch of Evolutionary Algorithms.
Aimed at evolving program expressions/computer code.
Each individual encodes a symbolic expression.
Solution Representation.
A tree structure is the most popular representation.
Other representations include graphs and linear structures
such as arrays.
A readily compilable source code.
Primary application area is modeling.
Commercial Application - predicting stock index.
Scientific Application - modeling physical processes.
Engineering Application - reverse engineering, designing
circuitry, regression, classification.
Data Mining.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
A SIMPLIFIED GP BREEDING CYCLE
GP uses four steps to solve problems:
Generate an initial population of random compositions of
the functions and terminals of the problem (computer
programs).
Functions: plus, minus, times, divide, sin, cos, log, power, ,
sqrt.
Terminals: Can be variables (network traffic parameters) and
constants.
Execute each program in the population and assign it a
fitness value according to how well it solves the problem.
Minimization of MSE.
Copy the best existing programs (Selection).
Roulette Wheel Selection - Fitness Proportionate Selection.
Tournament Selection.
Create new computer programs by mutation and crossover.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
A SIMPLIFIED GP BREEDING CYCLE: A SYMBOLIC
REPRESENTATION
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
EXPERIMENTAL SETUP
GPLab
Four GP Experiments were performed with various
configurations
Commonalities
Each experiment constituted 50 runs
Each Run spanned 50 generations
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
GP EXPERIMENTS
COMMON PARAMETERS
Parameter Value
Initial Population Size 300
Selection LPP Tournament
Tournament Size 2
Genetic Operators Crossover and Subtree Mutation
Initial Operator probabilities 0.5 initial, adaptive onwards
Survival Half Elitism
Function Set +, -, *, /, sin, cos, log2, log10,
loge, sqrt, power,
Terminal Set Random numbers [0.0 . . . 1.0]
Integers [2 . . . 10]. mlrVAD,
mblVAD, PI, br, fd
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
GP EXPERIMENTS
EXPERIMENTAL DETAILS
Experiment 1:
Fitness function – Mean Squared Error MSE
Experiment 2:
Linear Scaling MSEs
MSEs(y, t) = 1/n
n
i
(ti − (a + byi))2
(5)
a = t − by, b =
cov(t, y)
var(y)
(6)
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
GP EXPERIMENTS
EXPERIMENTAL DETAILS
Experiment 1:
Fitness function – Mean Squared Error MSE
Experiment 2:
Linear Scaling MSEs
MSEs(y, t) = 1/n
n
i
(ti − (a + byi))2
(5)
a = t − by, b =
cov(t, y)
var(y)
(6)
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
GP EXPERIMENTS
EXPERIMENTAL DETAILS
Experiments 3 and 4
Selection criterion based on Gustafson et al. was used
Mating takes place between dissimilar individuals
Experiment 4:
The Maximum tree depth was reduced to 7 from 17
The results were treated to Mann-Whitney-Wilcoxon Test
for significance Analysis
Experiment 4 was found to be significantly better overall.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
GP EXPERIMENTS
EXPERIMENTAL DETAILS
Experiments 3 and 4
Selection criterion based on Gustafson et al. was used
Mating takes place between dissimilar individuals
Experiment 4:
The Maximum tree depth was reduced to 7 from 17
The results were treated to Mann-Whitney-Wilcoxon Test
for significance Analysis
Experiment 4 was found to be significantly better overall.
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
ON DATA COLLECTION
Nortel ND speech database containing high quality signals
with speech from 2 male and 2 female speakers was used
for analysis.
A total of 3360 distorted speech files were created for each
combination of network traffic parameters.
1177 35% were used for training
503 15% were used for testing
1680 50% were used for speaker independent validation
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
VOIP QUALITY MONITORING MODELS
MOS − LQOGP = −2.46 × log(cos(log(br)) + mlrVAD
×(br + fd/10)) + 3.17 (7)
MOS − LQOGP = −2.99 × cos(0.91 × sin(mlrVAD)
+mlrVAD + 8) + 4.20 (8)
Equation (7) Equation(8)
Data MSEs σ MSEs σ
Training 0.0370 0.9634 0.0520 0.9481
Testing 0.0387 0.9646 0.0541 0.9501
Validation 0.0382 0.9688 0.0541 0.9531
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
SCATTER PLOTS
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
SCATTER PLOTS
ON PERFORMANCE OF ITU-T P.563
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
CONCLUSIONS
1 The model is a good approximation to PESQ.
2 Suitable for real-time and non-intrusive estimation of
speech quality whereas PESQ is NOT.
3 Simple models; depend on 3 and 1 variable respectively.
4 Performs significantly better than ITU-T P.563
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
FUTURE GOALS
To include wide band codecs in the research.
To develop a unified quality estimation model for narrow
and wide band telephony
Motivation VoIP Simulation Environment GP GP Experiments Test Results Conclusions
QUESTIONS

Realtime, Non-Intrusive Evaluation of VoIP Using Genetic Programming

  • 1.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions REAL-TIME, NON-INTRUSIVE EVALUATION OF VOIP USING GENETIC PROGRAMMING A. Raja1 A. Azad2 C. Flanagan1 C. Ryan2 1Wireless Access Research Centre Department of Electronic and Computer Engineering 2Bio-Computing and Developmental Systems Department of Computer Science and Information Sysmtems University of Limerick, Limerick, Ireland College of Informatics & Electronics Postgraduate Research Day 2007
  • 2.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OUTLINE 1 MOTIVATION Preamble The Problem of Speech Quality Assessment Voice Over IP Research Goal 2 VOIP SIMULATION ENVIRONMENT Simulation System Network Traffic Characteristics 3 GP 4 GP EXPERIMENTS 5 TEST RESULTS 6 CONCLUSIONS
  • 3.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OUTLINE 1 MOTIVATION Preamble The Problem of Speech Quality Assessment Voice Over IP Research Goal 2 VOIP SIMULATION ENVIRONMENT Simulation System Network Traffic Characteristics 3 GP 4 GP EXPERIMENTS 5 TEST RESULTS 6 CONCLUSIONS
  • 4.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OUTLINE 1 MOTIVATION Preamble The Problem of Speech Quality Assessment Voice Over IP Research Goal 2 VOIP SIMULATION ENVIRONMENT Simulation System Network Traffic Characteristics 3 GP 4 GP EXPERIMENTS 5 TEST RESULTS 6 CONCLUSIONS
  • 5.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OUTLINE 1 MOTIVATION Preamble The Problem of Speech Quality Assessment Voice Over IP Research Goal 2 VOIP SIMULATION ENVIRONMENT Simulation System Network Traffic Characteristics 3 GP 4 GP EXPERIMENTS 5 TEST RESULTS 6 CONCLUSIONS
  • 6.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OUTLINE 1 MOTIVATION Preamble The Problem of Speech Quality Assessment Voice Over IP Research Goal 2 VOIP SIMULATION ENVIRONMENT Simulation System Network Traffic Characteristics 3 GP 4 GP EXPERIMENTS 5 TEST RESULTS 6 CONCLUSIONS
  • 7.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OUTLINE 1 MOTIVATION Preamble The Problem of Speech Quality Assessment Voice Over IP Research Goal 2 VOIP SIMULATION ENVIRONMENT Simulation System Network Traffic Characteristics 3 GP 4 GP EXPERIMENTS 5 TEST RESULTS 6 CONCLUSIONS
  • 8.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions PREAMBLE VoIP – A paradigm shift Bandwidth redundancy exploitation QoS remains dominated by network/transport layer degradations Quality assessment ... Reflects upon the operating conditions of the network
  • 9.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions PREAMBLE VoIP – A paradigm shift Bandwidth redundancy exploitation QoS remains dominated by network/transport layer degradations Quality assessment ... Reflects upon the operating conditions of the network
  • 10.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions PREAMBLE VoIP – A paradigm shift Bandwidth redundancy exploitation QoS remains dominated by network/transport layer degradations Quality assessment ... Reflects upon the operating conditions of the network
  • 11.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions PREAMBLE VoIP – A paradigm shift Bandwidth redundancy exploitation QoS remains dominated by network/transport layer degradations Quality assessment ... Reflects upon the operating conditions of the network
  • 12.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions PREAMBLE VoIP – A paradigm shift Bandwidth redundancy exploitation QoS remains dominated by network/transport layer degradations Quality assessment ... Reflects upon the operating conditions of the network
  • 13.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions PREAMBLE VoIP – A paradigm shift Bandwidth redundancy exploitation QoS remains dominated by network/transport layer degradations Quality assessment ... Reflects upon the operating conditions of the network
  • 14.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions SPEECH QUALITY ASSESSMENT METHODOLOGIES Two approaches to speech quality Assessment 1 Subjective Assessment 2 Objective Assessment
  • 15.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions SUBJECTIVE ASSESSMENT OF SPEECH QUALITY Speech quality is estimated by humans. Advantage – Reliable results. Limitations 1 Expensive 2 Time Consuming 3 Laborious 4 Lack of Repeatability Mean Opinion Score (MOS) is the measure of quality. 1 – bad 5 – Excellent
  • 16.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OBJECTIVE ASSESSMENT OF SPEECH QUALITY A computer automated fast and reliable program is used to assay human perception of speech quality Two approaches: 1 Intrusive Assessment 2 Non-Intrusive Assessment
  • 17.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OBJECTIVE ASSESSMENT OF SPEECH QUALITY INTRUSIVE ASSESSMENT The signal under test is compared against a corresponding reference signal. Advantages: 1 The most reliable artificial means of estimating speech quality 2 Tests can be repeated easily Limitations: 1 Consumes considerable computing resources. 2 Is not useful for continuous monitoring of quality due to requirement of a reference signal.
  • 18.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OBJECTIVE ASSESSMENT OF SPEECH QUALITY INTRUSIVE ASSESSMENT The signal under test is compared against a corresponding reference signal. Advantages: 1 The most reliable artificial means of estimating speech quality 2 Tests can be repeated easily Limitations: 1 Consumes considerable computing resources. 2 Is not useful for continuous monitoring of quality due to requirement of a reference signal.
  • 19.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OBJECTIVE ASSESSMENT OF SPEECH QUALITY ITU-T P.862 (PESQ) PESQ algorithm is the current ITU-T Recommendation for intrusive speech quality estimation. The speech signal is mapped from time domain to time-frequency representation using the psychophysical equivalents of frequency and intensity.
  • 20.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OBJECTIVE ASSESSMENT OF SPEECH QUALITY ITU-T P.862 (PESQ) It has shown a high correlation with various ITU-T benchmark tests. For 30 ITU-T subjective tests the Pearson’s Correlation Coefficient (R) was 0.935
  • 21.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OBJECTIVE ASSESSMENT OF SPEECH QUALITY NON-INTRUSIVE ASSESSMENT A challenging problem since a reference is not available. Two approaches exist 1 Signal-based models 2 Parametric models Signal-based models Recent approaches are based on emulating 1 Human speech production model 2 Psychoacoustic processing of human ear ITU-T P.563 is the current Recommendation.
  • 22.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OBJECTIVE ASSESSMENT OF SPEECH QUALITY NON-INTRUSIVE ASSESSMENT A challenging problem since a reference is not available. Two approaches exist 1 Signal-based models 2 Parametric models Signal-based models Recent approaches are based on emulating 1 Human speech production model 2 Psychoacoustic processing of human ear ITU-T P.563 is the current Recommendation.
  • 23.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions OBJECTIVE ASSESSMENT OF SPEECH QUALITY PARAMETRIC MEASUREMENT OF VOIP QUALITY Functions of transport layer metrics and other measurable quantities. Cogent metrics may be: Packet Loss Rate Variable delay – jitter End-to-end delay . . . Aimed at Real-time and continuous evaluation of quality
  • 24.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions VOICE OVER IP – VOIP Packet based communication channel Uses wire-line speech codecs Linear Predictive Coding (LPC) is having vogue Coded frames are packetized into RTP/UDP Internet is used for transportation The receiver does the reverse process
  • 25.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions RESEARCH GOAL Derivation of a VoIP listening Quality estimation model as a function of transport layer metrics. Genetic Programming based Symbolic Regression is used Using the PESQ algorithm as the reference system
  • 26.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions VOIP SIMULATION ENVIRONMENT PACKET LOSS SIMULATION – THE GILBERT ELLIOT MODEL mlr = p p+q (1) mbl = 1 q (2) clp = 1 − q (3) mbl = 1 1−clp (4) Where mlr – mean loss rate mbl – mean burst length clp – conditional loss probability
  • 27.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions VOIP SIMULATION ENVIRONMENT
  • 28.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions NETWORK TRAFFIC PARAMETERS No. Parameter Name Abbreviation 1 Bit-rate (kbps) br 2 mean loss rate mlr 3 mean burst length mbl 4 Packetization Interval (ms) PI 5 Frame duration (ms) fd
  • 29.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions NETWORK TRAFFIC SCENARIOS No. Parameter Range 1 br G.729 (8 kbps), G.723.1 (6.3 kbps), AMR 7.4 and 12.2 kbps 2 mlr [0,2.5,3.5,. . . 15,20,25,. . . 40]% 3 mbl 10, 50, 60, 70 and 80% 4 PI 10-60 ms 5 fd 10, 20, 30 ms
  • 30.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions A BRIEF INTRO GP is a Machine Learning Technique inspired by biological evolution. A branch of Evolutionary Algorithms. Aimed at evolving program expressions/computer code. Each individual encodes a symbolic expression. Solution Representation. A tree structure is the most popular representation. Other representations include graphs and linear structures such as arrays. A readily compilable source code. Primary application area is modeling. Commercial Application - predicting stock index. Scientific Application - modeling physical processes. Engineering Application - reverse engineering, designing circuitry, regression, classification. Data Mining.
  • 31.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions A SIMPLIFIED GP BREEDING CYCLE GP uses four steps to solve problems: Generate an initial population of random compositions of the functions and terminals of the problem (computer programs). Functions: plus, minus, times, divide, sin, cos, log, power, , sqrt. Terminals: Can be variables (network traffic parameters) and constants. Execute each program in the population and assign it a fitness value according to how well it solves the problem. Minimization of MSE. Copy the best existing programs (Selection). Roulette Wheel Selection - Fitness Proportionate Selection. Tournament Selection. Create new computer programs by mutation and crossover.
  • 32.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions A SIMPLIFIED GP BREEDING CYCLE: A SYMBOLIC REPRESENTATION
  • 33.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions EXPERIMENTAL SETUP GPLab Four GP Experiments were performed with various configurations Commonalities Each experiment constituted 50 runs Each Run spanned 50 generations
  • 34.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions GP EXPERIMENTS COMMON PARAMETERS Parameter Value Initial Population Size 300 Selection LPP Tournament Tournament Size 2 Genetic Operators Crossover and Subtree Mutation Initial Operator probabilities 0.5 initial, adaptive onwards Survival Half Elitism Function Set +, -, *, /, sin, cos, log2, log10, loge, sqrt, power, Terminal Set Random numbers [0.0 . . . 1.0] Integers [2 . . . 10]. mlrVAD, mblVAD, PI, br, fd
  • 35.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions GP EXPERIMENTS EXPERIMENTAL DETAILS Experiment 1: Fitness function – Mean Squared Error MSE Experiment 2: Linear Scaling MSEs MSEs(y, t) = 1/n n i (ti − (a + byi))2 (5) a = t − by, b = cov(t, y) var(y) (6)
  • 36.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions GP EXPERIMENTS EXPERIMENTAL DETAILS Experiment 1: Fitness function – Mean Squared Error MSE Experiment 2: Linear Scaling MSEs MSEs(y, t) = 1/n n i (ti − (a + byi))2 (5) a = t − by, b = cov(t, y) var(y) (6)
  • 37.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions GP EXPERIMENTS EXPERIMENTAL DETAILS Experiments 3 and 4 Selection criterion based on Gustafson et al. was used Mating takes place between dissimilar individuals Experiment 4: The Maximum tree depth was reduced to 7 from 17 The results were treated to Mann-Whitney-Wilcoxon Test for significance Analysis Experiment 4 was found to be significantly better overall.
  • 38.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions GP EXPERIMENTS EXPERIMENTAL DETAILS Experiments 3 and 4 Selection criterion based on Gustafson et al. was used Mating takes place between dissimilar individuals Experiment 4: The Maximum tree depth was reduced to 7 from 17 The results were treated to Mann-Whitney-Wilcoxon Test for significance Analysis Experiment 4 was found to be significantly better overall.
  • 39.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions ON DATA COLLECTION Nortel ND speech database containing high quality signals with speech from 2 male and 2 female speakers was used for analysis. A total of 3360 distorted speech files were created for each combination of network traffic parameters. 1177 35% were used for training 503 15% were used for testing 1680 50% were used for speaker independent validation
  • 40.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions VOIP QUALITY MONITORING MODELS MOS − LQOGP = −2.46 × log(cos(log(br)) + mlrVAD ×(br + fd/10)) + 3.17 (7) MOS − LQOGP = −2.99 × cos(0.91 × sin(mlrVAD) +mlrVAD + 8) + 4.20 (8) Equation (7) Equation(8) Data MSEs σ MSEs σ Training 0.0370 0.9634 0.0520 0.9481 Testing 0.0387 0.9646 0.0541 0.9501 Validation 0.0382 0.9688 0.0541 0.9531
  • 41.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions SCATTER PLOTS
  • 42.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions SCATTER PLOTS ON PERFORMANCE OF ITU-T P.563
  • 43.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions CONCLUSIONS 1 The model is a good approximation to PESQ. 2 Suitable for real-time and non-intrusive estimation of speech quality whereas PESQ is NOT. 3 Simple models; depend on 3 and 1 variable respectively. 4 Performs significantly better than ITU-T P.563
  • 44.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions FUTURE GOALS To include wide band codecs in the research. To develop a unified quality estimation model for narrow and wide band telephony
  • 45.
    Motivation VoIP SimulationEnvironment GP GP Experiments Test Results Conclusions QUESTIONS