spoken language interaction in telecommunication at enst/cnrs-ltci gérard chollet, richard croce,...
TRANSCRIPT
![Page 1: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/1.jpg)
Spoken Language Interaction in Telecommunication
at ENST/CNRS-LTCI
Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ,
Marc SIGELLE, Pascal VAILLANT, François YVON (chollet,croce,petrovsk,sigelle,vaillant)@tsi.enst.fr
[email protected]/CNRS-LTCI
46 rue Barrault75634 PARIS cedex 13
http://www.tsi.enst.fr/~chollet
![Page 2: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/2.jpg)
Outline
What is ENST/CNRS-LTCI ?
Research and application topics:
The SIROCCO project The EUREKA !2340 MAJORDOME project VoIP, VoiceXML, Human-Computer Interaction
Perspectives
![Page 3: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/3.jpg)
ENST:ENST: Ecole Nationale Supérieure des Ecole Nationale Supérieure des TélécommunicationsTélécommunications
http://www.enst.frhttp://www.enst.fr
CNRS:CNRS: Centre National de la Recherche ScientifiqueCentre National de la Recherche Scientifiquehttp://www.cnrs.frhttp://www.cnrs.fr
LTCI:LTCI: Laboratoire de Traitement et Communication Laboratoire de Traitement et Communication de l’Informationde l’Information
Our affiliations
![Page 4: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/4.jpg)
What is ENST?Ecole Nationale de
Télécommunications
• classed among the
‘Grandes Ecoles d'Ingénieurs’.
• 250 state certified engineers
each year .
• part of ‘Groupement des Ecoles
de Télécommunications’
![Page 5: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/5.jpg)
GET : Groupement des Ecoles de Télécommunication
ENST ENST-Bretagne in Brest Institut National des Télécommunications
in Évry Eurecom in Sophia-Antipolis ENIC (Ecole Nouvelle d’Ingénieurs
en Télécoms) in Lille Institut des Applications Avancées de
l’Internet in Marseille
![Page 6: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/6.jpg)
Academic departments within ENST
COMELEC : Communications, Electronic, VLSI, …
INFRES :Computer Science, Networking, NLP, …
TSI : Signal and Image Processing, Speech, …
EGSH : Economy, Management, Social Sciences, …
![Page 7: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/7.jpg)
TSI Department :Signal and Image Processing
"Image Processing and Understanding" "Statistical Signal Processing Applied to
Communications" "Perception, Learning and Modelling"
Very Low Bit Rate Speech Coding Speech Recognition, Speaker Verification
"Coding" Speech and Sound compression
"Audio, Acoustics and Waves" acoustical antennas, audio protheses
![Page 8: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/8.jpg)
SIROCCO project Unlimited Vocabulary Speech Recognition
INRIA (IRISA et LORIA), LIA, IRIT, ENST-LTCIhttp://www.irisa.fr/sirocco/
![Page 9: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/9.jpg)
SIROCCO
Unlimited vocabulary speech recognition system
French lexicon (MathLex) with 64kwords (AUF task)
Feature extraction with Spro (G. Gravier) Context-dependent HMM phone models Word pronunciation graph Uses CMU-Toolkit for Language modeling Beam search for word hypothesis Rescoring of word hypothesis by A*
![Page 10: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/10.jpg)
«MAJORDOME»
Unified Messaging System
Eureka Projet no 2340
EDFHolistique
D. Bahu-Leyser, G. Chollet, R. Croce, K. Hallouli , J. Kharroubi, D. Kofman, L. Likforman, E. Matta-Sanchez, D. Petrovska, M. Sigelle, P. Vaillant, F. Yvon
![Page 11: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/11.jpg)
Majordome’s Functionalities
• Speaker verification
• Dialogue
• Routing
• Updating the agenda
• Automatic summary
Voice
Fax
![Page 12: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/12.jpg)
Overview of Majordome
Background tasks (server-side only): sorting and filtering messages from different
sources (E-mail, voice, fax, SMS,…); extracting relevant information for reporting
to user (names of senders, subject,…).
Dialogue with the user: over phone or Web. The system presents the state of the mailbox,
the type of messages, their sender, subject, and may sum them up or read them on request;
The users access their mailbox, addressbook, time schedule, or URIs (Web addresses).
![Page 13: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/13.jpg)
Voice technology in Majordome
Server side background tasks:continuous speech recognition applied to voice messages upon reception Detection of sender name and subject
User interaction: Speaker’s identification Speech recognition (receiving users’
commands through voice interaction) Text-to-speech synthesis (reading text
summaries, E-mails or faxes)
![Page 14: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/14.jpg)
Voice Over IP Platform
Network
192.168.223.0/1
1
Network 192.168.222.0/11
Visioconference
VTHD
Renater
UnisphereERX-700
1Gbps (FO Interne)
ENST-Paris
RTC/RNIS
Intranet
GK
PBX
GW IPVR
1Gbps
Cisco Catalyst
6507
Salle C-234
Salle C-234
Salle PBX
Salle C-234
Network192.168.111.0/11
VideoServer
DistanceLearningService
![Page 15: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/15.jpg)
‘Majordome’ partners
![Page 16: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/16.jpg)
Majordome / NetCentrex project
IP-VR NetCentrexRecorder Machine
Usual #NetCentrex #
Calling person
Is the called person here ?
Vocal E-mail
Usual user called
PABX /Gateway ENST-Call Control Server-Application Server
No response
NetCentrex user called
![Page 17: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/17.jpg)
Majordome / NetCentrex project
Usual #NetCentrex #
IP-VR NetCentrex
Calling person
PABX /Gateway ENST-Call Control Server-Application Server
Usual user called
Voice Interactive call
• Speaker verification
• Dialogue
•Vocal e-mail
• Routing
• Updating the agenda
• Automatic summary
No response
NetCentrex user called
![Page 18: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/18.jpg)
A framework: A L I S P
A utomaticL anguageI ndependentS peechP rocessing
with applications in Speech Coding, Synthesis, Recognition,
Speaker Verification and Language Identification
![Page 19: Spoken Language Interaction in Telecommunication at ENST/CNRS-LTCI Gérard CHOLLET, Richard CROCE, Dijana PETROVSKA-DELACRETAZ, Marc SIGELLE, Pascal VAILLANT,](https://reader036.vdocuments.us/reader036/viewer/2022070305/55142e77550346e7488b5e48/html5/thumbnails/19.jpg)
Perspectives
The application context of the Majordome project could be of interest to COST-278.
The Majordome/NetCentrex platform could be made available to interested partners.
HTK, ISIP and SIROCCO softwares are available as freeware. One of them will be used on the NetCentrex platform.