EP1745467A2 - Procede et dispositif permettant un acces acoustique a un ordinateur d'application - Google Patents

Procede et dispositif permettant un acces acoustique a un ordinateur d'application

Info

Publication number
EP1745467A2
EP1745467A2 EP05744814A EP05744814A EP1745467A2 EP 1745467 A2 EP1745467 A2 EP 1745467A2 EP 05744814 A EP05744814 A EP 05744814A EP 05744814 A EP05744814 A EP 05744814A EP 1745467 A2 EP1745467 A2 EP 1745467A2
Authority
EP
European Patent Office
Prior art keywords
application computer
interpreter
user
designed
input
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP05744814A
Other languages
German (de)
English (en)
Inventor
Tobias FÖRSTER
Christian FÖRSTER
Michael Junge
Karlheinz Lehrach
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Volkswagen AG
Original Assignee
8 HERTZ TECHNOLOGIES GmbH
Volkswagen AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 8 HERTZ TECHNOLOGIES GmbH, Volkswagen AG filed Critical 8 HERTZ TECHNOLOGIES GmbH
Publication of EP1745467A2 publication Critical patent/EP1745467A2/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
    • H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
    • H04M3/4938—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals comprising a voice browser which renders and interprets, e.g. VoiceXML
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems

Definitions

  • the invention relates to a device for acoustic access to at least one application computer according to the preamble of claim 1 and a corresponding method according to the preamble of claim 25.
  • DE 101 38 059 A1 discloses a device and a method for acoustic access by telephone to a computer network, comprising at least one application computer.
  • Files of the application computer are available with textual and / or graphic content. In this format, the files are suitable, for example, for playback on a screen.
  • the visual perception differs significantly from an acoustic perception.
  • a direct translation of the files using a text-to-speech (TTS) device and an acoustic reproduction of the “translation” is therefore usually difficult for a user to grasp intuitively.
  • TTS text-to-speech
  • An interpreter is therefore known from DE 101 38 059 A1, whereby the interpreter is designed in such a way that files of the application computer with textual and / or graphic content can be converted into a format that is suitable for a voice gateway comprising an automatic speech recognizer and a text-to-speech (TTS) device is therefore accessible via the phone without having to change the existing infrastructure of the computer network, but in order to obtain the desired information from the computer network, a user usually has to work through different levels of a menu.
  • TTS text-to-speech
  • the invention is therefore based on the technical problem of creating a method and a device for improved acoustic access to an application computer.
  • an interpreter comprises a dialog design, whereby a user can be guided ergonomically for access to the application computer.
  • Data and / or documents of one Application computers can be prepared by the interpreter for the format of an input and / or output unit and / or a voice browser.
  • the speech browser includes an automatic speech recognizer and a text-to-speech (TTS) facility.
  • TTS text-to-speech
  • the dialog design should create a dialog between the user and the machine that is intuitive, human, intelligent and / or entertaining.
  • the information obtained in the dialog enables the content of a document of the application computer to be suitably prepared in order to provide the user with the desired information as quickly as possible.
  • the application computer is designed, for example, as a server on an intranet and / or the Internet.
  • Data and / or documents of the application computer are available with textual and / or graphic content.
  • the application computer is designed as a control unit and / or is assigned to a control unit and that data from a special format of the control unit are to be converted into a format for human-machine communication.
  • the human-machine communication can be adapted to any format of the application computer without the need for changes in software and / or hardware of the application computer and / or the input and / or output unit.
  • the interpreter is designed with a “barge-in” function.
  • a “barge-in” is understood to mean an interruption of a text output by a voice input by a user. This enables the user to interrupt the dialog and / or output of information at any time.
  • the dialog design is adaptive.
  • the dialog between the user and the application program can be adapted to special preferences and / or idiosyncrasies of the user and / or to a specific application.
  • information can be made available even more quickly when the user accesses a particular application program again.
  • the speech recognizer is designed as a full-word recognizer, speaker-independent and / or with a vocabulary.
  • Whole word recognizers allow a user to request information in natural language and in complete sentences. Thanks to speaker independence, the system can be used by several speakers without a learning phase. However, it is also conceivable to at least partially adapt the speech recognizer to a speaker in order to take special speech properties of a user into account.
  • announcements that were not understood by the system are considered as "No-Match" files are stored in an audio format. The stored files are preferably assigned to a specific user. By evaluating the "No-Match" files, previously unknown words can be incorporated into a grammar and / or a user dictionary of the speech recognizer.
  • a WAV format is preferably used as the audio format.
  • the input and / or output unit is designed as a telephone.
  • Mobile phones and landline phones are widespread means of communication.
  • By using the telephone to access the application computer theoretically every telephone owner and / or user of a telephone system can access the application computer. In practice, access can be restricted using special dial-in codes and / or identification procedures.
  • a hands-free system and / or an output of an existing audio system can alternatively or additionally be used as an input and / or output unit.
  • Modern mobile phones are often designed with a display. Such an additional output option can be recognized by the system, so that in addition to a voice output, a graphical and / or textual output on the display is also conceivable.
  • the data of the application computer should preferably also be suitably adapted to the limited size of the display.
  • the phone communicates with the interpreter and the voice browser via a Bluetooth interface. It is conceivable that the interpreter and / or the voice browser automatically recognize an existing telephone in their environment and try to establish communication.
  • the input and / or output unit is designed as a one-button device.
  • the button is used to activate and / or deactivate the device. Access to information in the application program is only possible through language. This enables a particularly compact and simple design of the input and / or output unit.
  • the input and / or output unit, interpreter and voice browser can be made compact as one device.
  • the compact device can be designed with interfaces that enable connection of additional input and / or output units, for example a telephone and / or a loudspeaker.
  • the interpreter is designed as a multimodal interpreter, files of the application computer with textual and / or graphic content, files in the format of the language browser and / or files in a format of the input and / or output device can be converted into one another.
  • the interpreter thus forms the interface between different technologies. By adapting the interpreter, further technologies can be integrated into the communication without having to change existing structures.
  • the application computer is designed as a server. In principle, all files available on the Internet can be used via the application computer. This allows data to be managed and / or maintained centrally for an application.
  • the application computer is fed, for example, via a content provider. It is not necessary to adapt the data of the content provider for the voice-controlled input and / or output unit.
  • the input and / or output unit, the interpreter, the voice browser and / or the application computer can be integrated in a vehicle, “integrated” being understood to mean any short-term or longer-term, loose or fixed recording in a vehicle
  • integrated being understood to mean any short-term or longer-term, loose or fixed recording in a vehicle
  • an input and / or output unit designed as a telephone can be integrated into the vehicle at short notice without the need for a mechanical connection between the vehicle and the telephone the server is designed with an interpreter and a voice browser. If the server is connected to the Internet, the information in the Internet is available to the user in the vehicle. Instead of the radio connection to the server, it is also conceivable for the telephone to be an in Vehicle uses existing GPS and / or GSM antenna.
  • the connection between the phone and the The antenna can be implemented, for example, using a Bluetooth interface.
  • the interpreter and voice browser are integrated in the vehicle.
  • the communication between the input and / or output unit and the interpreter and / or the voice browser is conceivable using different protocols.
  • Speech signals are preferably transmitted via the VoicelntemetProtokol (VoIP), control signals for the input and / or output unit can be sent with TCP, for example.
  • VoIP VoicelntemetProtokol
  • control signals for the input and / or output unit can be sent with TCP, for example.
  • the application computer is also assigned to the vehicle. By integrating the application computer in the vehicle, fast communication is possible.
  • the application computer is preferably designed with an interface which allows the application computer to be integrated into an Internet. This enables information on the application computer to be updated from the outside. Is the application computer as Server configured, it is further conceivable that functions of the vehicle can be controlled via the application computer via the Internet. However, it must be ensured that only
  • the application computer is assigned to an office application, a help function, a route planner, a navigation system and / or an operating manual.
  • a help function is understood to be a function which provides information about the device for voice-controlled communication and its functions. Functions of the vehicle are stored in the operating manual.
  • the office application comprises an email module, an appointment module, an address book module and / or a telephone module.
  • E-mails can preferably be sent, received and forwarded by the e-mail module, the reception comprising a filter function.
  • a user can send emails from an existing address book to a recipient by naming the name.
  • the command to send the email can preferably be said in one sentence at the same time as the recipient.
  • the message is transmitted to the recipient in the form of a voice file, for example a WAV file.
  • the interpreter and / or the speech browser to translate the speech file into a suitable text file.
  • the user can also have eMails read out of his or her receiving folder by any external mail server to be defined in advance, for example a POP3 mail account.
  • the email as text is translated into a voice output by the voice browser.
  • the sender is read first to the user, then the subject line and then the text.
  • the user can preferably interrupt or continue at any time with appropriate voice commands.
  • the user can answer them immediately by voice commands within an email.
  • the reply mail can be sent as a WAV file and / or translated.
  • the email can also be forwarded to a recipient of the address book.
  • a filter function the reading function for emails can be filtered with additional information. The following information is conceivable as a filter, for example: "my eMails from yesterday", “... from today", from January 21, 2004 ", or” ... from my family "," ... my office ", "... of
  • the email module looks for the corresponding emails and reads them One after the other. The user can in turn navigate between the individual emails found using the “continue”, “back”, “the third” etc. commands.
  • the user is automatically informed of new emails, a sensitivity of a notification being adjustable.
  • the notification is only sent if a number of messages defined in advance has arrived.
  • the user is informed, for example, by phone about the presence of new messages.
  • the dialog between the application computer and the user after the critical number of emails has arrived can be started, for example, as follows. "You have XX new emails. Do you want to listen to this now? "The user is therefore free to listen to the emails or to postpone the listening to a later time.
  • a look-ahead window can be determined for the appointment module.
  • the user can specify a date on which he would like to call up his appointments.
  • a three-day preview can be offered by selecting today, tomorrow and the day after.
  • the days can be determined, for example, using a system time transferred during a login process.
  • the announcement of the appointments for a selected date takes place automatically, the user preferably being able to interrupt the announcement at any time by voice commands.
  • the appointment module is easy to maintain, for example, using a web interface.
  • appointments can also be entered by the user by voice.
  • the announcement of the user can be stored as a voice file under the desired date or can be translated into a suitable format for an entry in the appointment module by the voice browser and / or the interpreter.
  • the address module provides similar and / or the same name for selection.
  • the user can be connected by calling a name by phone and / or send an email.
  • the names are stored in the address module, and the addresses can be easily maintained using a web interface. Automatic contact generation is also possible.
  • the sender's name and the associated e-mail address of a received e-mail are saved if the e-mail was read, was not deleted directly and the name and address are completely available. Other criteria for storage can be defined by the user.
  • the user is given a selection list of the applicable persons from his address book, from which he can then choose.
  • the telephone module is designed with a hotword function.
  • the "hotword" enables the user to terminate the connection at any time using a voice command.
  • the help module comprises a function for "three-second silence" help, an error help and / or active help.
  • a "three-second silence” help recognizes that the user is undecided about the command to be entered is and supports him, for example, by announcing possible menu items.
  • Error help reacts if a command from the user is repeatedly misunderstood and, for example, establishes a direct connection to a call center.
  • the sensitivity can preferably be specified by the user.
  • Active help can be selected as a function by the user via a hotword and supports the user in the use of the voice application.
  • the route planner comprises a query function for querying traffic jam and / or danger reports.
  • the basis for the reports are, for example, nationwide traffic reports from a state police registration office and / or route information from websites.
  • the user in a vehicle has the option of querying traffic-related information according to the criteria of street, state, city and / or route.
  • the general information is filtered according to these entries.
  • the system can then output the traffic reports found by voice.
  • the interactive user manual comprises at least one outline and a key word index.
  • the content of the operating instructions can thus be searched by keyword and / or subject area.
  • the interactive operating instructions can be individualized by user settings and / or at least one bookmark. This enables a user to mark certain topics in the operating instructions and select the marked topics directly at a later time.
  • the user settings also make it conceivable that a depth of information corresponding to a user's interest can be preset.
  • step-by-step instructions can be output by the interactive operating instructions. Using step-by-step instructions, a user can be given step-by-step instructions on how to use certain applications in the vehicle.
  • the interactive operating instructions can be generated and / or updated by a transcoder.
  • the transcoder automatically generates existing pages of a manual, for example in XML, into corresponding information for reproduction by voice and / or on a display unit. This makes it easy to expand the operating instructions at any time.
  • the interactive operating instructions can be adapted to a specific vehicle.
  • information about certain design variants for example engine variants, four-door / two-door, etc., is taken into account and the user is specifically informed about his vehicle.
  • the interactive operating instructions can be adapted to a user. In this way, for example, different drivers of a vehicle can be informed differently.
  • a possible adjustment is, for example, a setting according to which texts are read out automatically or only after a voice command.
  • FIG. 1 is a schematic representation of a technology architecture for acoustic access to an application computer
  • Fig. 4 shows a detail page of the interactive instruction manual
  • the input and output unit 1 schematically shows a technology architecture for acoustic access to an application computer 4, comprising an input and output unit 1, an interpreter 2 and a voice browser 3.
  • the input and output unit 1 is equipped with a Microphone 12, a speaker 14, a display unit 16 and an antenna 18 are formed.
  • the input and output unit can be, for example, a commercially available mobile phone, a pocket PC and / or a PDA.
  • the voice browser 3 is designed with a voice recognition 32, a text-to-speech voice output 34, an audio playback 36 and an audio recording 38.
  • the input and output unit 1 communicates through channels 21 ⁇ - 21 3 with the interpreter 2, wherein the channels are used to transmit different signals.
  • the transmission takes place by radio using the antenna 18.
  • Speech signals are transmitted over channel 2 ⁇ .
  • the associated protocol is the Voicelntemet protocol.
  • Signals for building information on the display unit 16 are transmitted via the channel 21 2 .
  • These are HTML signals that are transmitted via http.
  • Signals for controlling the input and output unit are transmitted via channel 21 3 in accordance with TCP.
  • the input and output unit 1 receives commands from a user for the application computer 4. The commands can be entered as voice commands.
  • commands can also be entered by touching the display unit 16.
  • the commands recorded by the input and output unit 1 are transmitted to the interpreter 2.
  • Commands that were entered as voice commands are generally not understandable by the application computer 4. They are therefore fed to the voice browser 3 before being forwarded to the application computer 4.
  • the speech command 32 can be converted into a signal for the application computer 4 by means of the speech recognition 32. It is conceivable that the signal of the voice browser 3 is appropriately processed by the interpreter 2 before it is forwarded to the application computer 4.
  • the interpreter 2 takes into account characteristics of the input and / or output unit which are not known to the application computer 4 for the preparation.
  • interpreter 2 can be forwarded either directly or after a corresponding preparation by interpreter 2.
  • the voice browser 3 and the interpreter 2 communicate via a channel 23. They are preferably designed as a common component. If the interpreter 2 and the speech browser 3 are designed separately, the input and / or output unit 1 can be controlled by the interpreter 2 and / or by the speech browser 3.
  • the interpreter 2 and / or the voice browser 3 is preferably designed in such a way that any mobile phone can be connected.
  • the connection is made, for example, via Bluetooth, an interpreter 2 and / or voice browser 3 present in a vehicle automatically recognizing a mobile phone in the transmission area and establishing a corresponding connection.
  • the interpreter 2 and / or the voice browser 3 are arranged outside the vehicle.
  • the connection to the mobile phone is made, for example, via UMTS, GSM or similar connections.
  • the application computer 4 is assigned, for example, to route planning for a vehicle, office applications in a vehicle and / or an interactive operating manual in a vehicle. Depending on the application, the application computer 4 is preferably arranged in the vehicle or outside the vehicle. An application computer 4, which is assigned to an office application, is preferably located outside the vehicle, for example on a desk in an office space of the user. The user can select the computer by voice from anywhere.
  • the input and output unit 1, the interpreter 2 and the voice browser 3 can be designed, for example, as a device via which the application computer is selected. In addition, it is also conceivable for the user to use a mobile phone or a similar input and output unit 1 to select a control center in which the interpreter 2 and the voice browser 3 are located and through which the connection to the application computer 4 is established.
  • the input and output unit 1, the interpreter 2, the voice browser 3 and the application computer 4 are preferably located in the vehicle.
  • An input and / or output unit, if present, is additionally a display integrated in the vehicle and / or an existing hands-free system.
  • an external arrangement of the application computer 4 can also be more advantageous, in particular because of possible updates.
  • the start page comprises a menu line 50 and an information area 52.
  • possible menu sub-items are shown optically.
  • the possible menu sub-items in the example shown are "reading aloud”, “structure”, “keywords”, “bookmarks”, “settings” and “help”.
  • Help gives the user assistance in handling the interactive operating manual.
  • the “Settings” enables the user to choose, for example, whether a text displayed should be read out to him automatically or only if this is desired by voice command. After a one-time reading, the reading process can be repeated at any time with the voice command "Read out" from menu line 50.
  • the system greets the user optically and acoustically with the text "Welcome to the electronic manual”.
  • the table of contents of the interactive operating instructions is opened by the voice commands "Please show the outline”, “Please outline”, “Show outline”, "I want to see the outline” or a similar voice command.
  • Fig. 3 shows the display of the outline on a display unit for the interactive user guide.
  • the display of the outline again comprises the menu line 50 and an information area 54.
  • the table of contents of the interactive operating instructions is reproduced on the information area 54.
  • the items “Driving” and “Ignition lock” have been opened, as well as the subitems “Electronic immobilizer”, “Positions of the ignition key”, “Switching off the engine”, “Starting the engine”, “Ignition key emergency unlocking” and “Ignition key positions” "Ignition key withdrawal lock".
  • the driver changes to the detail page shown in FIG. 4.
  • the display of the structure comprises a menu line 56 and an information area 58.
  • the menu line 56 shows the user command options. These include the option of to jump back to the higher level, to memorize the displayed page and / or to scroll through the detailed pages.
  • the positions of the ignition key are visually displayed to him on information area 58. A description of the individual positions is also shown Have the ignition key described acoustically.
  • FIG. 5 shows the display of an index directory on a display unit for the interactive operating manual.
  • the display of the index directory again comprises the menu line 50 and an information area 59.
  • a keyword index of the interactive operating instructions is reproduced on the information area 59.
  • keywords with the first letter “A” namely “automatic transmission”, “Automatic transmission with Tiptronic” and “Automatic distance control ADR” are displayed.
  • a corresponding voice command for example "go to letter P", changes the display accordingly.
  • the display unit is designed as a touchscreen, navigation in the interactive operating manual by touching the screen is also conceivable in addition to the voice command. This is particularly advantageous for "scrolling" in longer text passages.
  • a further input unit is conceivable, which is designed, for example, as a push-turn knob, and through which the user can select appropriate menu items and scroll through test voltages.
  • the possibility of input commands by voice it is easy to give. The user is guided ergonomically through dialogues with the system in order to further improve the ease of use. Since, for example, "scrolling" can also be useful for the office functions described, one is generally used Combined input via language and control element such as rotary pushbutton or touch screen is preferred.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • User Interface Of Digital Computer (AREA)
  • Input From Keyboards Or The Like (AREA)

Abstract

L'invention concerne un dispositif et un procédé permettant un accès acoustique à au moins un ordinateur d'application (4), ledit dispositif présentant: au moins une interface pour au moins une unité d'entrée et/ou de sortie acoustique; un navigateur vocal qui comprend au moins un dispositif de reconnaissance vocale automatique (32) et un dispositif TTS (34) effectuant une synthèse de la parole à partir du texte; ainsi qu'un interpréteur (2) conçu de sorte que des fichiers de l'ordinateur d'application (4) puissent être convertis dans un format approprié pour le navigateur vocal (2) et/ou l'unité d'entrée et/ou de sortie (1). L'interpréteur (2) est conçu de manière à permettre un dialogue de sorte qu'un utilisateur peut être guidé de manière ergonomique pour avoir accès à l'ordinateur d'application.
EP05744814A 2004-04-29 2005-04-25 Procede et dispositif permettant un acces acoustique a un ordinateur d'application Withdrawn EP1745467A2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE200410021454 DE102004021454A1 (de) 2004-04-29 2004-04-29 Verfahren und Vorrichtung für einen akustischen Zugang zu einem Anwendungsrechner
PCT/EP2005/004555 WO2005106847A2 (fr) 2004-04-29 2005-04-25 Procede et dispositif permettant un acces acoustique a un ordinateur d'application

Publications (1)

Publication Number Publication Date
EP1745467A2 true EP1745467A2 (fr) 2007-01-24

Family

ID=34968370

Family Applications (1)

Application Number Title Priority Date Filing Date
EP05744814A Withdrawn EP1745467A2 (fr) 2004-04-29 2005-04-25 Procede et dispositif permettant un acces acoustique a un ordinateur d'application

Country Status (3)

Country Link
EP (1) EP1745467A2 (fr)
DE (1) DE102004021454A1 (fr)
WO (1) WO2005106847A2 (fr)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1826965B1 (fr) 2006-02-24 2008-08-20 Cycos Aktiengesellschaft Serveur de messages et procédé pour la notification d'un utilisateur concernant la réception d'un message électronique
DE102007037567A1 (de) * 2007-08-09 2009-02-12 Volkswagen Ag Verfahren zur multimodalen Bedienung mindestens eines Gerätes in einem Kraftfahrzeug
DE102008028477B4 (de) * 2008-06-13 2019-12-12 Volkswagen Ag Verfahren zur Hilfestellung eines Nutzers bei der Benutzung eines Sprachbediensystems und Sprachbediensystem
DE102008028478B4 (de) * 2008-06-13 2019-05-29 Volkswagen Ag Verfahren zur Einführung eines Nutzers in die Benutzung eines Sprachbediensystems und Sprachbediensystem
DE102011116187A1 (de) * 2011-10-14 2013-04-18 Volkswagen Aktiengesellschaft Verfahren und Vorrichtung zum Bereitstellen einer Nutzerschnittstelle
DE102016110850A1 (de) * 2016-06-14 2017-12-14 Dr. Ing. H.C. F. Porsche Aktiengesellschaft Bedieneinheit für ein Kraftfahrzeug und Verfahren zum Bedienen einer Bedieneinheit eines Kraftfahrzeugs

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19941973C5 (de) * 1999-09-03 2012-05-16 Volkswagen Ag Verfahren und Vorrichtung zur aktiven Hilfestellung eines Kraftfahrzeugführers in einem Kraftfahrzeug
US6629134B2 (en) * 1999-09-16 2003-09-30 Xerox Corporation Context sensitive web-based user support
WO2001078245A1 (fr) * 2000-04-06 2001-10-18 Tom North Service d'envoi de messages courts ameliore
US6560576B1 (en) * 2000-04-25 2003-05-06 Nuance Communications Method and apparatus for providing active help to a user of a voice-enabled application
US6539358B1 (en) * 2000-05-24 2003-03-25 Delphi Technologies, Inc. Voice-interactive docking station for a portable computing device
DE10138059A1 (de) * 2001-08-03 2003-02-13 Deutsche Telekom Ag Konvertierungseinrichtung und Konvertierungsverfahren für einen akustischen Zugang zu einem Computernetzwerk
US6791529B2 (en) * 2001-12-13 2004-09-14 Koninklijke Philips Electronics N.V. UI with graphics-assisted voice control system
DE10239172A1 (de) * 2002-08-21 2004-03-04 Deutsche Telekom Ag Verfahren zum sprachgesteuerten Zugriff auf Informationen mit Berücksichtigung inhaltlicher Beziehungen

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
CACCIA G; LANCINI R; PESCHIERA G: "Multimodal browsing using XML/XSL architecture", INFORMATION TECHNOLOGY, RESEARCH AND EDUCATION, 2003, PROCEEDINGS, ITR E2003, 11 August 2003 (2003-08-11), PISCATAWAY, NJ, USA, IEEE, pages 194 - 197, XP010685435 *

Also Published As

Publication number Publication date
WO2005106847A2 (fr) 2005-11-10
WO2005106847A3 (fr) 2006-03-16
DE102004021454A1 (de) 2005-11-24

Similar Documents

Publication Publication Date Title
EP0852051B1 (fr) Procede de commande automatique d'au moins un appareil par des commandes vocales ou par dialogue vocal en temps reel et dispositif pour la mise en oeuvre de ce procede
DE60033122T2 (de) Benutzeroberfläche zur Text-zu-Sprache-Umsetzung
DE60217241T2 (de) Fokussierte Sprachmodelle zur Verbesserung der Spracheingabe von strukturierten Dokumenten
EP1324314B1 (fr) Système pour la reconnaissance de la parole et méthode d'opération d'un tel système
US9529787B2 (en) Concept search and semantic annotation for mobile messaging
DE102009017177B4 (de) Spracherkennungsanordnung und Verfahren zur akustischen Bedienung einer Funktion eines Kraftfahrzeuges
DE202016008260U1 (de) Erlernen von Aussprachen einer personalisierten Entität
DE10338512A1 (de) Unterstützungsverfahren für Sprachdialoge zur Bedienung von Kraftfahrzeugfunktionen
DE112014002747T5 (de) Vorrichtung, Verfahren und grafische Benutzerschnittstelle zum Ermöglichen einer Konversationspersistenz über zwei oder mehr Instanzen eines digitalen Assistenten
DE212014000045U1 (de) Sprach-Trigger für einen digitalen Assistenten
DE102012019178A1 (de) Verwendung von Kontextinformationen zum Erleichtern der Verarbeitung von Befehlen bei einem virtuellen Assistenten
EP1745467A2 (fr) Procede et dispositif permettant un acces acoustique a un ordinateur d'application
DE102014204108A1 (de) Voice Interface Systems and Methods
DE112011103447T5 (de) Durch implizite Zuordnung und Polymorphismus gesteuerte Mensch-Maschine-Wechselwirkung
DE102006029251B4 (de) Verfahren und System für einen Telefonbuchtransfer
DE102012210986B4 (de) System mit einer Mobilkommunikationsvorrichtung und einem Fahrzeugstereosystem und Verfahren zum Betrieb des Systems
EP1251680A1 (fr) Service d'annuaire à commande vocale pour connection a un Réseau de Données
EP1330817B1 (fr) Reconnaissance vocale robuste avec organisation de banque de donnees
DE102009030263A1 (de) Bedienverfahren für ein menübasiertes Bedien- und Informationssystem eines Fahrzeugs
EP1321851B1 (fr) Méthode et système pour l'utilisation de marqueurs sélectionnables par un utilisateur comme points d'entrée dans la structure d'un menu d'un système de dialogue de parole
DE102006051331A1 (de) Verfahren zur Auswahl eines Fahrziels
DE102019219406A1 (de) Kontext-sensitives sprachdialogsystem
EP1125278A1 (fr) Systeme de traitement de donnees ou terminal de communication dote d'un dispositif de reconnaissance vocale et procede de reconnaissance de certains objets acoustiques
DE60125597T2 (de) Vorrichtung für die Dienstleistungsvermittlung
DE102009058151B4 (de) Verfahren zum Betreiben eines Sprachdialogsystems mit semantischer Bewertung und Sprachdialogsystem dazu

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20061129

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU MC NL PL PT RO SE SI SK TR

RIN1 Information on inventor provided before grant (corrected)

Inventor name: FOERSTER, CHRISTIAN

Inventor name: FOERSTER, TOBIAS

Inventor name: JUNGE, MICHAEL

Inventor name: LEHRACH, KARLHEINZ

DAX Request for extension of the european patent (deleted)
17Q First examination report despatched

Effective date: 20070830

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: VOLKSWAGEN AKTIENGESELLSCHAFT

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20100115