A Speech Processing Solution in a 3G Media Server Miikka Rautapää Nokia Networks

advertisement
A Speech Processing Solution in a
3G Media Server
Miikka Rautapää
Nokia Networks
Supervisor: Professor Raimo Kantola
04.11.2003
Abbreviations














AEC
ALC
AMR
AMR-WB
BSS
DSP
EC
EFR
FR
MIPS
NS
RAN
TFO
TrFO
Acoustic Echo Cancellation
Adaptive Level Control
Adaptive Multi-Rate (speech codec)
Wideband AMR (speech codec)
Base Station System
Digital Signal Processor
Echo Cancellation
Enhanced Full Rate (speech codec)
Full Rate (speech codec)
Million Instructions Per Second
Noise Suppression
Radio Access Network
Tandem Free Operation
Transcoder Free Operation
Agenda








Problem Description
Speech processing applications
3G Network
MGW architecture
Speech processing media server
Testing
Results
Conclusions & Future Work
Problem Description
The problem
 MGW provides services for different interfaces
 Every service has own speech processing
applications
BSS
Control
PSTN
IP
RAN
The objective
 Find a solution to share speech processing
applications for all MGW terminations regardless
of their interfaces
Used methodology
 Case: own solution for the media gateway project
ATM
Speech Processing Applications








Speech coding
Tandem coding avoidance (e.g. TFO, TrFO)
Speech enhancements (e.g. EC, AEC, NS, ALC)
Speech synthesis
Speech recognition
Conferencing, Announcements, Interactive voice
response
Etc…
Need lots of processing power
3G Network (1/2)

Next-generation
network

Media gateway (MGW)


routes traffic between
packet network and
circuit-switched network.
Media server


processes, manages, and
delivers the media
resources.
Open, scalable architecture
3G Network (2/2)

3GPP release 4 network



MGW
MSC Server
IP/ATM backbone
Simplified architecture of the 3GPP release 4 network
MGW Architecture

Interfaces




ATM, RAN
PSTN, BSS
IP
DSP Unit


Control
processor
DSP chips
DSP software
MGW
applications provide different
user plane framing protocols for different
interfaces, and different supplementary
services (e.g. announcements) for other
MGW applications.
MGW server processes provide basic
functions for MGW applications.
DSP Platform provides connection
management, timer services and basic
operating system functions.
Speech Processing Media Server


Integrated part of the MGW
DSP
Serves MGW applications with
different speech processing
applications





FR, EFR, AMR
ALC
V-model design
Client/server
Signalling interface
* Own contribution
Testing




Unit, integration and system testing
True media gateway hardware
Bit-exact tests
Performance measurements


Codecs
Overhead (control code)
Results

510 test cases (passed)
Control Codecs
60
436

ALC
8
Multi channel
6
Performance measurements
(encoder&decoder)
FR
MIPS 2.2
EFR
AMR
DTX Overhead
11.1 8.0-11.1 0.2 0.16-0.24
Conclusions

Speech processing applications



Media server



Optimised as enhanced services platform
Integrated to the MGW
DSP


Several applications
Need lots of processing power
Layered software (applications – servers – platform)
Results


510 test cases
Performance depends on application algorithms
Future Work

Other applications (e.g. AMR-WB, AEC)


Easy to integrate
Interface


Signalling
Function calls
Download