2nd SPEAK! workshop: Speech Generation in Multimodal Information - - PowerPoint PPT Presentation
2nd SPEAK! workshop: Speech Generation in Multimodal Information Systems and Practical Applications Speech synthesis in the Intelligent Personal Communication Support System (IPCSS) Tom Pfeifer Technical University of Berlin e-mail:
2nd SPEAK! workshop: Speech Generation in Multimodal Information Systems and Practical Applications
Technical University of Berlin e-mail: pfeifer@fokus.gmd.de
bitmap format management in
control bitmap text page text bitmap header processing fax engine (email) adaption layouter may include font or postscript interpretetion formatting management in
control text fax OCR bitmap text fax cleaning, format adaption mail engine further conversion (e.g. TTS)
.
product manufacturer
system hardware platform supplemental hardware languages TrueTalk Entropic UNIX Sun, SGI E, VisualVoice Stylus Innovations DOS/WIN PC sound card pos- sible E, EASE Expert Systems Dialogic required E, TrueVoice Centigram UNIX, DOS Sun, PC E, Dialogic TTS Dialogic DOS PC Dialogic required E, DecTalk Digital E, Lernout & Houspie Lernout & Hous- pie OS/2, DOS/ WIN, etc. various E, Ger, F, NL, Esp,... Rhetorex TTS Rhetorex UNIX, OS/ 2, NT PC Rhetorex required E, BestSpeech Berkeley Speech- Technologies DOS, OS/2, UNIX PC etc. Dialogic, Rheto- rex, etc. possible E, Ger, F, I, J, NL, Rus Infovox Telia Promotor Infovox DOS PC Infovox 500 Ger Elan Informa- tique ELAN Informa- tique DOS PC Televox Psola- 8m Ger, F
speech sound, music movie picture graphic legible text audio (m, n, c, t) video (m, n, c, t) photograph (m, n, c) bitmap image vector image page description text numeric handwriting (postscript, (gif, tiff, fax, ...) tactile: skin
gustative: tongue vestibular: ear kinaesthetic: body haptic: skin auditory: ear human media channels technical representation conversion technical representation human media channels, visual: eye Braille vibration signal tactile image smell taste balance grasp force pressure force, movement thermic: skin any digital representation midi adobe acrobat) perception: generation of perceptible information: audio (m, n, c, t) video (m, n, c, t) photograph (m,n,c) bitmap image vector image page description text numeric handwriting (postscript, (gif, tiff, fax, ...) any digital representation midi adobe acrobat) technical systems written language spoken language video camera movie archive sensors for parameter drawings photo camera (natural, technical) any physical (temperature, pressure, velocity, humidity, voltage, (examples) composed document composed mail control data control data composed document composed mail parameters: m, n: media dependent parameters c: applied compression technique t: time, duration, etc. (frame/sampling rate, quantization, resolution, size, color depth, etc.)
personalizing telecommunications in customer premises networks (CPNs) or office environements
Telecommunications Management Networks (TMN)
Incoming
call logic evaluation
1st Mapping
Person to person
Call to:
user locating dynamic selection get comm. capabilities R507 Fax
2nd Mapping
Person to location
3rd Mapping
Location to virtual
4th Mapping
virtual communication
Call Accept (signal ‘off hook’)
Call Handling Address Resolution
VAP
communication endpoint (VAP) (processing of registration data) (e.g. Call Forwarding) endpoint (VAP) to Terminal (SAP) (dynamic selection of
SAP
terminal/service)
service generic precessing
User Presen-
Paging MM Mail Service MM Collabor. Service (MMC) PBX / ISDN Legend: PCSS Personal Communications Support System DUA Directory User Agent IDMIS Inter-Domain Management Information Service (MMM)
PCSS Applications PCSS Infrastructure
Communication Assistance Service User Location Information Service User Profile Management Service Manual User Registration Service Electronic Location Server
Core PCSS
User Profiles
DIT X.500 X.700 MIBs
IDMIS Electronic (e.g. Active Location Techniques Badges / IrSensor Net- work)
Client-API
Enabling Techno- logies
Object Type Must Contain Attributes (some) May Contain Attributes
pcssGenServiceUser- Profile
pcssPersonalIDKey, pcssProvidedServiceID, (inherited:) CN, surname pcssAuthenticationNumber, pcssPersonalNumPlanID , pcssPersonalScheduleID , pcssAutomaticRegisterID , pcssManualRegisterID , pcssPersonalCallLogicID, (inherited:) description, seeAlso, telephoneNumber, userPassword, userid, textEncodedORAddress, rfc822Mailbox, roomNumber, userClass, homePhone, homePostalAddress, secretary, personalTitle, preferredDeliveryMethod, businessCategory, otherMailbox, mobileTelephoneNumber, pagerTelephoneNumber,
mailPreferenceOption, personalSignature
PCSS
Non Service-specific User Data
POTS-Profile MMMS-Profile MMCS Profile
Legend: containment relationship
attribute(s) (sub-tree)
Manual. Sched.
MMCS-specific Data
Service-specific User Profile Extensions
User Profile
Generic
Personalization Data Registration General User Data Personalization Data Registration Data General User Data
PNP CRA
PID User Info Authentication ManuallyTo AutomaticallyTo ScheduledTo
Diary
Service User Profile Call Mgt. Data
callLogic
Set of Rules Conditions Actions
Generic Service User Profiles PCSS Zone VAP SAP
IDMIS (integrated X.500 / X.700 access)
PCSS-specific
User Registration
Management global PCSS data(X.500)
PCSS-MIB
System SystemID=sol ServiceProv. ServerID=ELSl . . . . . . = . . Managed System CN=SOL-MS
Services & PCSS User Agent-API
(provided as PCSS- specific MSCs / MFs)
User Profile Mgt Service
PCSS - Applications Framework
PID_to_SAP() PID_to_ZoneID()
supported telecommuni- cation services supported telecommuni- cation services supported telecommuni- cation services Communication Assistant Service
supported tele- services
Profiles Profiles Profiles