Colombia, 23-24 September 2013 QoS assessment for mobile speech services including user interfaces in vehicles and hands-free communication Dr.-Ing. H. W. Gierlich Head of Telecom Division CITEL (PCC.I)/ ITU Forum on Information and Communication Technology Service: Quality, Control and Surveillance (Cartagena de Indias, Colombia, 23-24 September 2013)
29
Embed
Colombia, 23-24 September 2013 QoS assessment for mobile speech services including user interfaces in vehicles and hands-free communication Dr.-Ing. H.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Colombia, 23-24 September 2013
QoS assessment for mobile speech services including user interfaces in vehicles and
hands-free communication
Dr.-Ing. H. W. GierlichHead of Telecom Division
CITEL (PCC.I)/ ITU Forum on Information and
Communication Technology Service:
Quality, Control and Surveillance
(Cartagena de Indias, Colombia, 23-24 September 2013)
Colombia, 23-24 September 2013
2
Outline
IntroductionThe impact of terminal design on speech qualityAssessment methods and standards for mobile terminalsDriver distraction and speech services in carsSummary
Important: All signal processing is non-linear, time variant and
targeted to speech enhamcement
Speech Quality
Colombia, 23-24 September 2013 5
TESTINGTESTING…in general should be based on users perception…may be based on simple signals and procedures modelling aspects of users perception (e.g. loudness)…may be based on complex signals and advanced procedures modelling aspects of users perception (e. g. switching and double talk tests)…may be based on perceptual models using psychoacoustically motivated procedures (models of the human hearing)
USERS PERCEPTIONUSERS PERCEPTION…is subjective and generally different between subjects…is based on experience…is cultural dependant
Colombia, 23-24 September 2013
6
Outline
IntroductionThe impact of terminal design on speech qualityAssessment methods and standards for mobile terminalsDriver distraction and speech services in carsSummary
Speech Quality Evaluation
Colombia, 23-24 September 2013 7
Speech-Quality
EchoEchoPerformancePerformance
ReceivingReceiving
Double TalkDouble Talk
Quality of Quality of Background Background
Noise Transm.Noise Transm.
SendingSending
Terminal Testing
Bring the world to the lab:Simulate userSimulate user behaviourSimulate user environmentsSimulate network and access pointsSimulate network conditionsValdidate correct NTP access
Moste Important Test Parameters Enabling a Good QoS Performance
Basic acoustic tests e.g. Loudness Ratings (ITU-T P.79), Frequency response tests…Delay and echo testsSpeech quality tests – with and without background noiseConversational test including double talk, switching…Important: Test signals are mostly speech based – ITU-T P.501
Colombia, 23-24 September 2013 11
The Impcat of Delay on Conversational Dynamics
Colombia, 23-24 September 2013 12
Best case between fixed & mobile network (no satelite):~150 ms Worst case across networks:>> 500 ms
For superior conversational quality: delay < For superior conversational quality: delay < ~150 ms~150 ms(from the users perspective)
Network
Terminal A Terminal B0 ms 0 ms (.wav)
150 ms 150 ms (.wav)500 ms 500 ms
(.wav)
Conversational/Double Talk Test Signal
Colombia, 23-24 September 2013 13
Word fully masked, one speaker continuosly talking
Word in partially masked
Word conicident with the other channel speaker, Simulating delay and unwanted double talk
Double talk sentences
Receive
Send
Male Female Male Female
Short isolated words
Word in a speech pause
Summary of Quality Parameters Using „Quality Pies“ according to ITU-T P.505
IntroductionThe impact of terminal design on speech qualityAssessment methods and standards for mobile terminalsDriver distraction and speech services in carsSummary
Driver Distraction
Colombia, 23-24 September 2013 16
Physical/manual distractionPhysical/manual distractionManual operation of devicesManual operation of devices
Visual distraction Visual distraction Watching information other than roadWatching information other than road
Auditory distractionAuditory distractionFocusing on auditory events not related to Focusing on auditory events not related to the driving taskthe driving task
Cognitive distractionCognitive distractionOccupied by non driving related tasksOccupied by non driving related tasks
Technology Based Distraction in Cars
Colombia, 23-24 September 2013 17
Car entertainment systemsCar entertainment systems
Navigation systemsNavigation systems
Phones for speech communicationPhones for speech communication
Car information systemsCar information systems
Text messanging systemsText messanging systems
„„Texting while driving“Texting while driving“
::
To be Avoided
Colombia, 23-24 September 2013 18
In general all activities distracting In general all activities distracting from the driving task, esp.:from the driving task, esp.:
Visual cues which require different focus Visual cues which require different focus than roadthan road
Non intuitive manual operation of the car Non intuitive manual operation of the car
Loading the human auditory system by Loading the human auditory system by distracting cuesdistracting cues
Unnatural and low quality dialogs and Unnatural and low quality dialogs and communications communications
Driving Task
Colombia, 23-24 September 2013 19
The driving taskThe driving task
=> Auditory Channel and Speech => Auditory Channel and Speech “available”“available”
mostly occupied: mostly occupied: visual systemvisual system
mainly involved: mainly involved: hands and legshands and legs
involved: involved: auditory systemauditory system
not involved: not involved: talkingtalking
Speech Based Services in Cars
Colombia, 23-24 September 2013 20
o The main speech applications:The main speech applications:
• Speech recognition systemsSpeech recognition systems• Speech dialog systemsSpeech dialog systems• Text to speech systemsText to speech systems• Speech enhancement for Speech enhancement for
communication systemscommunication systems• Hands-free communicationHands-free communication• Enhanced in-car communication Enhanced in-car communication
systems between passengerssystems between passengers
Superior Sound Quality & Intelligibility in the Car
Colombia, 23-24 September 2013 23
o Wideband services in mobile networks available soon->->
o Enabling wideband telephony (100 Hz- 8 kHz) in cars• Fullband• Narrow band (car)• Wideband (car)
o Efficient use of the high quality audio systems in Efficient use of the high quality audio systems in cars:cars:• Getting superior sound quality• Increasing speech intelligibility• Increasing naturalness of a conversation• Reduce drivers distraction due to poor speech sound quality
Colombia, 23-24 September 2013 24
Bluetooth Link
Phoneadapter &antennaamplifier
Radio Link
Hands-free signal
processing
Caraudio
system
Car Hands-Free Testing
Colombia, 23-24 September 2013 25
analysisanalysis
Mobiles Sound Playback System (can be installed in any
vehicle)
Subwoofer
HFTACQUA
BackgroundNoise
Generatorand Analyzer
MFE VIUSBFrontend
PEQ IVProgrammableEqualizer
PEQ IVProgrammableEqualizer
PEQ IVProgrammableEqualizer
Radio Tester
(Analog)
(Digital)AES / EBU
(Digital)AES / EBU
(Digital)USB
(Digital)AES / EBU
Subwoofer
HFT
Subwoofer
HFTACQUA
BackgroundNoise
Generatorand Analyzer
MFE VIUSBFrontend
PEQ IVProgrammableEqualizer
PEQ IVProgrammableEqualizer
PEQ IVProgrammableEqualizer
Radio Tester
(Analog)
(Digital)AES / EBU
(Digital)AES / EBU
(Digital)USB
(Digital)AES / EBU
Test System
ITU-T Standards Contributing to Reduced Drivers Distraction
Colombia, 23-24 September 2013 26
ITU-T standards for Hands-Free Communication:ITU-T standards for Hands-Free Communication:
• ITU-T P.1100 for narrowband hands-freeITU-T P.1100 for narrowband hands-free• ITU-T P.1110 for wideband hands-freeITU-T P.1110 for wideband hands-free
ITU-T standards work ITU-T standards work in FG CarCOMin FG CarCOM::• New work on subsystem requirements for Hands-Free New work on subsystem requirements for Hands-Free
Systems in CarsSystems in Cars
ITU-T standards for Dialog Systems:ITU-T standards for Dialog Systems:
• P.851: Subj. evaluation of dialog systemsP.851: Subj. evaluation of dialog systems• Suppl. 24 to P. Rec.: Parameters describing Suppl. 24 to P. Rec.: Parameters describing
the interaction with spoken dialog systemsthe interaction with spoken dialog systems
The Main Section in ITU-T P.1100 & P.1110
Colombia, 23-24 September 2013 27
Definition of the test arrangement in a carDescription of a digital interface concept for development and debuggingMicrophone test specification for separate microphones in a carMeasurement parameters and requirements for hands-free terminalsBluetooth test interface for validation of telephone performanceSubjective test strategy for car to car communication
Conclusions and Recommendations
Mobile terminal testing is essential to provide sufficient or even superior QoE to the user – many operator have specific terminal standards for their suppliers A variety of parameters contribute to the overall (conversational) speech qualityNetwork conditions have to be considered in the testingLow driver distraction is essential to offer mobile services Speech based operation is the key to the success of mobile services in carsBoth, terminals and networks have to be thoroughly engineered and adapted to each other
Colombia, 23-24 September 2013
28
Tandeming of Signal Processing in Terminals & Networks