DE10043271A1 - Method for voice recognition picks up a spoken word/word component to be processed electronically and converted to digital code before being compared with a data file of stored references. - Google Patents
Method for voice recognition picks up a spoken word/word component to be processed electronically and converted to digital code before being compared with a data file of stored references.Info
- Publication number
- DE10043271A1 DE10043271A1 DE2000143271 DE10043271A DE10043271A1 DE 10043271 A1 DE10043271 A1 DE 10043271A1 DE 2000143271 DE2000143271 DE 2000143271 DE 10043271 A DE10043271 A DE 10043271A DE 10043271 A1 DE10043271 A1 DE 10043271A1
- Authority
- DE
- Germany
- Prior art keywords
- word
- spoken
- speech recognition
- network
- converted
- 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.)
- Ceased
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
- H04M3/4931—Directory assistance systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/26—Devices for calling a subscriber
- H04M1/27—Devices whereby a plurality of signals may be stored simultaneously
- H04M1/271—Devices whereby a plurality of signals may be stored simultaneously controlled by voice recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
- H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
-
- 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
- H04M3/4936—Speech interaction details
Abstract
Description
Die vorliegende Erfindung betrifft ein Verfahren zur Spracherkennung, bei dem ein von einer sprechenden Person gesprochenes Wort oder ein Wortbestandteil aufgenommen, elektronisch verarbeitet und in einen digitalen Code umgesetzt wird, bevor es mit einer Datei enthaltend gespeicherte Bedeutungen verglichen wird, wobei die dem gesprochen Wort zuzuordnende Bedeutung weiterverarbeitet wird. Die Erfindung betrifft gleichfalls ein System zur Durchführung des Verfahrens.The present invention relates to a method for speech recognition, in which a Word or part of a word spoken by a speaking person recorded, electronically processed and converted into a digital code is compared before it is saved with a file containing stored meanings the meaning of the spoken word is further processed becomes. The invention also relates to a system for performing the Process.
Spracherkennungsysteme sind generell in verschiedenen Anwendungen bekannt. So werden heute beispielsweise Mobiltelephone mit speicherbaren Telephonbuch angeboten, wobei der Inhalt des Telephonbuches vom Benutzer über das Sprechen eines Namens abgerufen werden kann ("Name Dailling"). Nach der Vorgabe des Namens wählt das Telephon die Nummer des ausgewählten Teilnehmers automatisch an. Ein solches System ist für die Benutzung von Mobiltelephonen während anderer Beschäftigungen, beispielsweise während des Autofahrens, vorteilhaft.Speech recognition systems are generally known in various applications. So today, for example, cell phones with storable phone book offered, the content of the phone book by the user on the Speaking a name can be retrieved ("Name Dailling"). After Given the name, the telephone dials the number of the selected one Participant automatically. Such a system is for the use of Mobile phones during other activities, for example during the Driving, advantageous.
Nachteil der bekannten Systeme ist generell, daß sie vergleichsweise wenig intelligent sind und die sprachlichen Vorgaben ohne weiter "nachzudenken" weiterverarbeiten. So kommt es jedoch gezwungenermaßen zu Problemen, wenn beispielsweise der Benutzer das Wort "Mama" vorgibt, um die Mutter anzuwählen. The disadvantage of the known systems is generally that they are comparatively little are intelligent and the language requirements without "thinking" processed. However, this inevitably leads to problems if for example, the user specifies the word "mom" to dial the mother.
Gibt nämlich der Vater den Adressaten "Mama" vor, so will er die Oma sprechen, während das Kind seine Mutter wünscht.If the father specifies the addressee "mom", he wants to speak to the grandma, while the child wants his mother.
Aufgabe der vorliegenden Erfindung ist es, ein Verfahren zur Spracherkennung zu schaffen, das mit einfachen Mitteln umsetzbar ist und das mit hoher Zuverlässigkeit dem gesprochenen Wort die vom Nutzer gewollte Bedeutung zuordnet. Die Aufgabe ist es auch, ein System zur Durchführung des Verfahrens zu schaffen.The object of the present invention is to provide a method for speech recognition create that can be implemented with simple means and with high Reliability of the spoken word is the meaning the user wants assigns. The task is also to create a system to carry out the procedure to accomplish.
Diese Aufgaben werden durch das Verfahren nach Anspruch 1 und das System nach Anspruch 4 gelöst.These tasks are achieved by the method according to claim 1 and the system solved according to claim 4.
Der erfindungsgemäße Gedanke liegt darin, bei der Zuordnung der Bedeutung zu dem entsprechenden über Sprache vorgegebenen Wort die Individualität des Sprechers zu erkennen, um damit mögliche individuelle Unterschiede in den Bedeutungen einzelner Worte stärker berücksichtigen zu können. Das Verfahren identifiziert die sprechende Person anhand der die Person charakterisierenden Aussprache einzelner Worte oder bestimmter systematischer Charakteristika. Dabei reicht es unter Umständen aus, die Person zumindest bezüglich eines oder einiger Merkmale, wie beispielsweise Alter, Geschlecht oder Gemütszustand zu identifizieren, um eine vernünftige Zuordnung der Bedeutungen zu gewährleisten. Bei der Zuordnung der Bedeutung zum vorgegebenen Wort oder zum Wortbestandteil berücksichtigt das Verfahren erfindungsgemäß eine der Person oder der Personengruppe individuell zuzuordnende Korrektur, die zu einer individualisierten Bedeutung des vorgegebenen Wortes führt.The idea of the invention is to assign the meaning to the corresponding word given by language the individuality of the Recognizing the speaker in order to identify possible individual differences in the To be able to take the meanings of individual words more into account. The procedure identifies the speaking person based on the characterizing person Pronunciation of individual words or certain systematic characteristics. It may be sufficient to at least refer to one or the person some characteristics, such as age, gender or mood identify in order to ensure a reasonable assignment of the meanings. When assigning the meaning to the given word or to According to the invention, the word component takes into account one of the person or the correction to be individually assigned to the group of people, which leads to a individualized meaning of the given word.
Das erfindungsgemäße Verfahren läßt sich generell zur Korrektur eines jeden Systems zur Spracherkennung einsetzen, da eine Individualisierung von Bedeutungen in jedem Fall zu einer höheren Treffsicherheit bei der Zuordnung führt. Beispielsweise kann jedes Diktierprogramm von der Erfindung profitieren, indem es zunächst den Nutzer identifiziert, bevor es die individuelle Zuordnung von Bedeutungen vornimmt. Besonders vorteilhaft ist es jedoch der Einsatz der individualisierenden Spracherkennung als Feature bei (Mobil)-Telephonen. Bei diesen kann der Name des anzurufenden Teilnehmers gesprochen werden (name dailling), und das erfindungsgemäße Verfahren setzt daraufhin den Namen in die entsprechende Netzkennung um. So wird mittels der Erfindung dem Wort "Mama" von einem Kind ausgesprochen die Bedeutung "Mutter" zugeordnet, während die Oma angewählt wird, wenn der Vater "Mama" vorgibt.The method according to the invention can generally be used to correct everyone Use systems for speech recognition because an individualization of Meanings in any case to a higher accuracy in the assignment leads. For example, any dictation program can benefit from the invention, by first identifying the user before making the individual assignment of meanings. However, it is particularly advantageous to use the individualizing voice recognition as a feature on (mobile) telephones. at the name of the subscriber to be called can be spoken to them (name dailling), and the inventive method then sets the name in the corresponding network identifier. So the word "mom" pronounced by a child the meaning "mother" while the Grandma is chosen when the father pretends "mom".
Als System wird der erfindungsgemäße Gedanke dadurch realisiert, daß die Spracherkennungseinheit ein Verifikationsmodul aufweist, das anhand des gesprochenen Wortes zumindest ein Merkmal des anrufenden Teilnehmers, wie beispielsweise sein Alter und/oder sein Geschlecht, registriert und dieses als Korrektur berücksichtigt bei der Umsetzung des Wortes in die Netzkennung. Dabei umfaßt das System ein Datenleitungsnetz, insbesondere das Internet oder ein Telephonnetz, mit einer Vielzahl individueller Anschlüsse, wobei ein Teilnehmer sich über einen Anschluß in das Netz einwählen und vermittels einer Netzkennung eine Verbindung zum Anschluß eines anderen Teilnehmers herstellen kann. Es ist besonders vorteilhaft, das Verifikationsmodul mit einer intelligenten Elektronik eines Telephones, wie sie in den modernen Telephonen üblich ist, zu realisieren. In einer anderen vorteilhaften Ausführungsform ist die Spracherkennung und das Verifikationsmodul nicht im Telephon dezentral, sondern zentral von einem Server realisiert sind, der an das Datenleitungsnetz angeschlossen ist.As a system, the inventive idea is realized in that the Speech recognition unit has a verification module, which is based on the spoken word at least one feature of the calling party, such as for example, its age and / or gender, registered and this as Correction taken into account when converting the word into the network identifier. there the system comprises a data line network, in particular the Internet or a Telephone network, with a large number of individual connections, one subscriber dial into the network via a connection and use a network identifier can establish a connection to the connection of another subscriber. It is the verification module with intelligent electronics is particularly advantageous a telephone, as is common in modern telephones. In another advantageous embodiment, the speech recognition and that Verification module not decentralized in the telephone, but centrally from a server are realized, which is connected to the data line network.
Neben der verbesserten Treffsicherheit der gewünschten Bedeutung hat die Erfindung folgende weitere Vorteile: Über die Identifizierung des anrufenden Teilnehmers ist es möglich, für spezielle Personengruppen (Jugendliche oder Rentner) besondere Tarife einzuführen. Bestimmte Netzkennungen, z. B. 0190- Hotlines, können über die Identifizierung auch gesperrt werden. Vorteilhaft ist, daß der Nutzer jederzeit über seine Sprache einen präzisen Zugriff auf seine im Telephonbuch gespeicherten Nummern hat.In addition to the improved accuracy of the desired meaning, the Invention following further advantages: On the identification of the calling Participant, it is possible for special groups of people (young people or Pensioners) to introduce special tariffs. Certain network identifiers, e.g. B. 0190- Hotlines can also be blocked using identification. It is advantageous that the user has precise access to his im at any time via his language Phone book has stored numbers.
Claims (6)
- -
- -
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE2000143271 DE10043271A1 (en) | 2000-09-02 | 2000-09-02 | Method for voice recognition picks up a spoken word/word component to be processed electronically and converted to digital code before being compared with a data file of stored references. |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE2000143271 DE10043271A1 (en) | 2000-09-02 | 2000-09-02 | Method for voice recognition picks up a spoken word/word component to be processed electronically and converted to digital code before being compared with a data file of stored references. |
Publications (1)
Publication Number | Publication Date |
---|---|
DE10043271A1 true DE10043271A1 (en) | 2002-10-02 |
Family
ID=7654747
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
DE2000143271 Ceased DE10043271A1 (en) | 2000-09-02 | 2000-09-02 | Method for voice recognition picks up a spoken word/word component to be processed electronically and converted to digital code before being compared with a data file of stored references. |
Country Status (1)
Country | Link |
---|---|
DE (1) | DE10043271A1 (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE3834869A1 (en) * | 1988-10-13 | 1990-04-26 | Telefonbau & Normalzeit Gmbh | Method for the speech-dependent identification of individuals |
DE4317372A1 (en) * | 1992-05-26 | 1993-12-02 | Ricoh Kk | Acoustic and visual input speech recognition system - monitors lip and mouth movements by video camera to provide motion vector input to neural network based speech identification unit. |
DE19707973A1 (en) * | 1997-02-27 | 1998-05-20 | Siemens Ag | Speech-controlled input method for networked computer |
US5946658A (en) * | 1995-08-21 | 1999-08-31 | Seiko Epson Corporation | Cartridge-based, interactive speech recognition method with a response creation capability |
US6081782A (en) * | 1993-12-29 | 2000-06-27 | Lucent Technologies Inc. | Voice command control and verification system |
US6088669A (en) * | 1997-01-28 | 2000-07-11 | International Business Machines, Corporation | Speech recognition with attempted speaker recognition for speaker model prefetching or alternative speech modeling |
-
2000
- 2000-09-02 DE DE2000143271 patent/DE10043271A1/en not_active Ceased
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE3834869A1 (en) * | 1988-10-13 | 1990-04-26 | Telefonbau & Normalzeit Gmbh | Method for the speech-dependent identification of individuals |
DE4317372A1 (en) * | 1992-05-26 | 1993-12-02 | Ricoh Kk | Acoustic and visual input speech recognition system - monitors lip and mouth movements by video camera to provide motion vector input to neural network based speech identification unit. |
US5771306A (en) * | 1992-05-26 | 1998-06-23 | Ricoh Corporation | Method and apparatus for extracting speech related facial features for use in speech recognition systems |
US6081782A (en) * | 1993-12-29 | 2000-06-27 | Lucent Technologies Inc. | Voice command control and verification system |
US5946658A (en) * | 1995-08-21 | 1999-08-31 | Seiko Epson Corporation | Cartridge-based, interactive speech recognition method with a response creation capability |
US6088669A (en) * | 1997-01-28 | 2000-07-11 | International Business Machines, Corporation | Speech recognition with attempted speaker recognition for speaker model prefetching or alternative speech modeling |
DE19707973A1 (en) * | 1997-02-27 | 1998-05-20 | Siemens Ag | Speech-controlled input method for networked computer |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0166318B1 (en) | Device for the recognition and translation of dial information and also of control information for services of a telephone exchange | |
DE69333645T2 (en) | Voice-controlled communication system with common subscriber identifiers | |
DE69635015T2 (en) | AUTOMATIC VOCABULAR GENERATION FOR LANGUAGE-BASED VOICE BASED ON A TELECOMMUNICATIONS NETWORK | |
DE69629873T2 (en) | Method and device for controlling a telephone using voice commands | |
EP1282296A2 (en) | Method and device for establishing a conference circuit | |
DE3338484A1 (en) | PARTICIPANTS INTERCOM | |
DE60018349T2 (en) | Generation of a name dictionary from recorded telephone greetings for speech recognition | |
DE19751123C1 (en) | Device and method for speaker-independent language name selection for telecommunications terminal equipment | |
EP1016312A2 (en) | Method and device for automatic translation of messages in a communications system | |
DE10043271A1 (en) | Method for voice recognition picks up a spoken word/word component to be processed electronically and converted to digital code before being compared with a data file of stored references. | |
EP0295470A2 (en) | Method for a calculator controlled switching device especially for a so called key telephone exchange with the possibility of call transfer | |
EP1232657B1 (en) | Method for creating a dialling directory in a network terminal and a communication network for a method of this type | |
DE102006011121A1 (en) | Hands-free electronics and method for operating hands-free electronics | |
EP1444855A1 (en) | Resetting sent information | |
DE10106914A1 (en) | Automated R call | |
DE4228997C2 (en) | Method for establishing telephone connections in a telephone switching system | |
DE3328059C2 (en) | Method for the selection on the receiving side of data or voice connections running via an exchange of a telecommunications or telephone system | |
WO2000004695A1 (en) | Method and device for operating a telecommunications terminal with acoustic emission of identification data | |
DE10022089A1 (en) | Automatic call priority control method for automatic call distribution unit identifies priority caller and controls call handling dependent on priority level | |
DE3826100A1 (en) | Controlled telephone barring device | |
DE10046208A1 (en) | Voice filter system for a telephone network which categorises voice messages | |
EP1302928A1 (en) | Method for speech recognition, particularly of names, and speech recognizer | |
DE10138151A1 (en) | Telephone conference system has communications exchange station with subscriber authentication device for comparing transmitted and stored codes before connection establishment | |
DE60026955T2 (en) | Acoustic identification of caller and called for mobile communication device | |
DE19937453A1 (en) | Centralised telephone book device and method determines caller identification for accessing personalised telephone book with entries updated or selected for automatic call connection via speech recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
OM8 | Search report available as to paragraph 43 lit. 1 sentence 1 patent law | ||
8110 | Request for examination paragraph 44 | ||
8131 | Rejection |