[go: up one dir, main page]

DE19636452A1 - Multiple user speech input system - Google Patents

Multiple user speech input system

Info

Publication number
DE19636452A1
DE19636452A1 DE1996136452 DE19636452A DE19636452A1 DE 19636452 A1 DE19636452 A1 DE 19636452A1 DE 1996136452 DE1996136452 DE 1996136452 DE 19636452 A DE19636452 A DE 19636452A DE 19636452 A1 DE19636452 A1 DE 19636452A1
Authority
DE
Germany
Prior art keywords
user
vocabulary
words
voice
speech
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Withdrawn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
DE1996136452
Other languages
German (de)
Inventor
Dietmar Kirsten
Dietmar Koehler
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.)
KOEHLER, DIETMAR, DIPL.-ING, 04600 ALTENBURG, DE K
Original Assignee
Altenburger Industrienaehmaschinen GmbH
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 Altenburger Industrienaehmaschinen GmbH filed Critical Altenburger Industrienaehmaschinen GmbH
Priority to DE1996136452 priority Critical patent/DE19636452A1/en
Publication of DE19636452A1 publication Critical patent/DE19636452A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • 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
    • G10L17/00—Speaker identification or verification techniques
    • 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
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • G10L2015/0631—Creating reference templates; Clustering

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Machine Translation (AREA)

Abstract

The speech recognition system (1) accepts spoken inputs from several users, and the process begins with entry of a spoken identification word that is compared 1 with a stored value 2. This results in access to one of several user specific speech pattern vocabularies held in memory 3. The number of words held in the vocabulary can be selected by the user, as can the associated meanings. There can be an optical display (5) provided with the system.

Description

Beschrieben wird ein System zur Spracheingabe, welches ein sprecherabhängiges Sprach­ erkennungssystem nutzt um Sprachbefehle mit hoher Sicherheit zu erkennen. Eine starke Sprecherabhängigkeit durch exakten Vergleich des gesprochenen Wortes mit dem zuvor vom Sprecher erzeugten Muster, welches im Sprachmustervokabular hinterlegt ist, wirkt sich dabei positiv auf die Erkennungssicherheit aus. Umgebungslärm, Sprache dritter Person in der Nähe des Sprechers und vom Sprecher gesprochene Worte, welche nicht im Sprach­ mustervokabular hinterlegt sind, werden vom Spracherkennungssystem dabei weitgehend ignoriert. Diese Eigenschaften sind besonders wichtig, wenn das Spracherkennungssystem als Eingabesystem an der Schnittstelle Mensch-Maschine Einsatz findet.A system for speech input is described, which is a speaker-dependent language recognition system uses to recognize voice commands with high security. A strong Speaker dependence through exact comparison of the spoken word with the previous one Pattern generated by the speaker, which is stored in the speech pattern vocabulary, has an effect thereby positively on the recognition security. Environmental noise, third party language in close to the speaker and words spoken by the speaker that are not in the speech The vocabulary is largely used by the speech recognition system ignored. These properties are particularly important when using the speech recognition system is used as an input system at the human-machine interface.

Ein entscheidender Nachteil dabei ist, daß das System nur von einer Person genutzt werden kann.A key disadvantage is that the system can only be used by one person can.

Um diesen Nachteil zu umgehen, werden bekannterweise (z. B. DE 38 03 220 A1) für jedes zu erkennende Wort Sprachmuster verschiedener Sprecher hinterlegt. Ein entscheidender Nachteil hierbei ist, daß sich die Größe des Sprachmustervokabulars mit der Anzahl der potentiellen Nutzer multipliziert. Das hat zur Folge, daß sich die Erkennungssicherheit im gleichen Maße verringert.To avoid this disadvantage, it is known (e.g. DE 38 03 220 A1) for each Word to be recognized Language patterns of different speakers are stored. A crucial one The disadvantage here is that the size of the speech pattern vocabulary varies with the number of multiplied potential users. As a result, the detection security in the reduced to the same extent.

Zur Schaffung eines Mehrnutzersystems ohne den Nachteil der Verringerung der Er­ kennungssicherheit wird erfindungsgemäß für jeden potentiellen Nutzer ein eigenes Sprach­ mustervokabular gespeichert. Im Betriebsfall ist dann nur das Sprachmustervokabular des jeweiligen Nutzers aktiv.To create a multi-user system without the disadvantage of reducing Er According to the invention, security of identification becomes a separate language for each potential user Sample vocabulary saved. In the operating case, only the language pattern vocabulary of active user.

Die Zuordnung des nutzereigenen Sprachmustervokabulars zum jeweiligen Nutzer erfolgt erfindungsgemäß über ein, vom Nutzer bei Beginn zu sprechendes Identifikationswort. Die Identifikationsworte aller potentiellen Nutzer befinden sich in einem gemeinsamen Sprachmustervokabular, welches zu Beginn immer als erstes solange aktiv ist, bis ein Identifikationswort erkannt und damit das entsprechende nutzereigenen Sprachmuster­ vokabular aktiviert wird. Um den Nutzer vom erfolgten Vokabularwechsel zu informieren, wird erfindungsgemäß ein Begrüßungstext über eine Sprachausgabeeinheit ausgegeben. Der jeweilige Betriebszustand wird zusätzlich optisch signalisiert.The assignment of the user's own language pattern vocabulary to the respective user takes place According to the invention via an identification word to be spoken by the user at the beginning. The Identification words of all potential users are in a common one Speech pattern vocabulary, which is always the first to be active until a Identification word recognized and thus the corresponding user's own speech pattern vocabulary is activated. To inform the user of the change of vocabulary, According to the invention, a greeting text is output via a voice output unit. Of the the respective operating status is additionally signaled optically.

Die erfindungsgemäße Bildung der nutzereigenen Sprachmustervokabulare aus frei wählbaren Worten, welche ihrer Wortbedeutung entsprechend eigene Aktionen auslösen können, schafft auf einfache Weise ein leistungsfähiges Hilfsmittel zur Strukturierung und Verriegelung bei der sprachgesteuerten Bedienung von Maschinen und Einrichtungen. So ist es z. B. möglich, durch Strukturierung der nutzereigene Vokabulare unterschiedliche Bedien­ plattformen für Maschineneinrichter und Maschinenbediener zu schaffen.The creation of the user's own language pattern vocabularies according to the invention from free selectable words, which trigger their own actions according to their word meaning can easily create a powerful tool for structuring and Locking in the voice-operated operation of machines and equipment. So is it z. B. possible by structuring the user's own vocabularies different operating to create platforms for machine setters and machine operators.

BezugszeichenlisteReference list

1 sprecherabhängiger Spracherkenner
2 Sprachmustervokabular Identifikationsworte
3 Sprachmustervokabular einsatzspezifisch
4 Sprachausgabeeinheit
5 optische Anzeige 1 speaker-dependent speech recognizer
2 speech pattern vocabulary identification words
3 Language pattern vocabulary specific to use
4 voice output unit
5 optical display

Claims (4)

1. Mehrnutzersystem zur Spracheingabe dadurch gekennzeichnet, daß bei einem sprecherabhängigen Spracherkennungssystem (1) ein gesondertes, für alle Nutzer gemeinsam zur Verfügung stehendes Sprachmustervokabular (2) mit den Identifikationsworten der Nutzer vorhanden ist und für jeden Nutzer speziell ein weiteres Sprachmustervokabular (3) mit den einsatzspezifischen Worten zur Verfügung steht.1. Multi-user system for voice input, characterized in that in a speaker-dependent speech recognition system ( 1 ) there is a separate speech pattern vocabulary ( 2 ) available for all users together with the identification words of the users and for each user a further speech pattern vocabulary ( 3 ) with the mission-specific words is available. 2. Mehrnutzersystem zur Spracheingabe dadurch gekennzeichnet, daß die Zuordnung des einsatzspezifischen Sprachmustervokabulars (3) zum Nutzer durch Spracherkennung des nutzerspezifischen Identifikationswortes erfolgt.2. Multi-user system for voice input, characterized in that the assignment of the application-specific language pattern vocabulary ( 3 ) to the user is carried out by voice recognition of the user-specific identification word. 3. Mehrnutzersystem zur Spracheingabe dadurch gekennzeichnet, daß die Anzahl der Worte des einsatzspezifischen Sprachmustervokabulars (3) und deren Bedeutung für jeden Nutzer frei wählbar sind.3. Multi-user system for voice input, characterized in that the number of words of the mission-specific language pattern vocabulary ( 3 ) and their meaning are freely selectable for each user. 4. Mehrnutzersystem zur Spracheingabe dadurch gekennzeichnet, daß zur Erkennung des jeweils aktiven Sprachmustervokabulars (3) eine Sprachausgabeeinheit (4) und eine optische Anzeige (5) bzw. nur eines von beiden vorhanden ist.4. Multi-user system for voice input, characterized in that a voice output unit ( 4 ) and an optical display ( 5 ) or only one of the two is present for the recognition of the respectively active voice pattern vocabulary ( 3 ).
DE1996136452 1996-09-07 1996-09-07 Multiple user speech input system Withdrawn DE19636452A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
DE1996136452 DE19636452A1 (en) 1996-09-07 1996-09-07 Multiple user speech input system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE1996136452 DE19636452A1 (en) 1996-09-07 1996-09-07 Multiple user speech input system

Publications (1)

Publication Number Publication Date
DE19636452A1 true DE19636452A1 (en) 1998-03-12

Family

ID=7804970

Family Applications (1)

Application Number Title Priority Date Filing Date
DE1996136452 Withdrawn DE19636452A1 (en) 1996-09-07 1996-09-07 Multiple user speech input system

Country Status (1)

Country Link
DE (1) DE19636452A1 (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000079515A3 (en) * 1999-06-21 2001-04-26 Palux Ag Device for controlling vending machines
WO2001067435A1 (en) * 2000-03-08 2001-09-13 Siemens Aktiengesellschaft Method for the voice-controlled initiation of actions by means of a limited circle of users, whereby said actions can be carried out in an appliance
DE10122087C1 (en) * 2001-05-07 2002-08-29 Siemens Ag Method for training and operating a voice/speech recognition device for recognizing a speaker's voice/speech independently of the speaker uses multiple voice/speech trial databases to form an overall operating model.
DE10129326B4 (en) * 2000-06-19 2007-02-22 Yamaha Corp., Hamamatsu Information processing system with a graphical user interface controllable by a voice recognition device and thus equipped musical instrument
US7343288B2 (en) 2002-05-08 2008-03-11 Sap Ag Method and system for the processing and storing of voice information and corresponding timeline information
US7406413B2 (en) 2002-05-08 2008-07-29 Sap Aktiengesellschaft Method and system for the processing of voice data and for the recognition of a language
DE102008024258A1 (en) * 2008-05-20 2009-11-26 Siemens Aktiengesellschaft A method for classifying and removing unwanted portions from a speech recognition utterance
DE102008024257A1 (en) * 2008-05-20 2009-11-26 Siemens Aktiengesellschaft Speaker identification method for use during speech recognition in infotainment system in car, involves assigning user model to associated entry, extracting characteristics from linguistic expression of user and selecting one entry
DE102007011039B4 (en) * 2007-03-07 2019-08-29 Man Truck & Bus Ag Hands-free device in a motor vehicle

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000079515A3 (en) * 1999-06-21 2001-04-26 Palux Ag Device for controlling vending machines
WO2001067435A1 (en) * 2000-03-08 2001-09-13 Siemens Aktiengesellschaft Method for the voice-controlled initiation of actions by means of a limited circle of users, whereby said actions can be carried out in an appliance
DE10129326B4 (en) * 2000-06-19 2007-02-22 Yamaha Corp., Hamamatsu Information processing system with a graphical user interface controllable by a voice recognition device and thus equipped musical instrument
DE10122087C1 (en) * 2001-05-07 2002-08-29 Siemens Ag Method for training and operating a voice/speech recognition device for recognizing a speaker's voice/speech independently of the speaker uses multiple voice/speech trial databases to form an overall operating model.
US7343288B2 (en) 2002-05-08 2008-03-11 Sap Ag Method and system for the processing and storing of voice information and corresponding timeline information
US7406413B2 (en) 2002-05-08 2008-07-29 Sap Aktiengesellschaft Method and system for the processing of voice data and for the recognition of a language
DE102007011039B4 (en) * 2007-03-07 2019-08-29 Man Truck & Bus Ag Hands-free device in a motor vehicle
DE102008024258A1 (en) * 2008-05-20 2009-11-26 Siemens Aktiengesellschaft A method for classifying and removing unwanted portions from a speech recognition utterance
DE102008024257A1 (en) * 2008-05-20 2009-11-26 Siemens Aktiengesellschaft Speaker identification method for use during speech recognition in infotainment system in car, involves assigning user model to associated entry, extracting characteristics from linguistic expression of user and selecting one entry

Similar Documents

Publication Publication Date Title
EP0852051B1 (en) Process for automatic control of one or more devices by voice commands or by real-time voice dialog and apparatus for carrying out this process
DE69923253T2 (en) Method and device for speech recognition
EP1927980B1 (en) Method for classifying spoken language in spoken dialogue systems
DE69922104T2 (en) Speech recognizer with vocabulary adaptable by spelled word input
DE69633883T2 (en) Method for automatic speech recognition of arbitrary spoken words
DE69514382T2 (en) VOICE RECOGNITION
DE10338512A1 (en) Support procedure for speech dialogues for the operation of motor vehicle functions
DE19636452A1 (en) Multiple user speech input system
DE60034772T2 (en) REJECTION PROCEDURE IN LANGUAGE IDENTIFICATION
EP1443494B1 (en) Method and device to limit the search scope in a speech recognition lexicon
EP1249016B1 (en) Method for the voice-operated identification of the user of a telecommunication line in a telecommunications network during an interactive communication using a voice-operated conversational system
DE60014583T2 (en) METHOD AND DEVICE FOR INTEGRITY TESTING OF USER INTERFACES OF VOICE CONTROLLED EQUIPMENT
WO2001067435A9 (en) Method for the voice-controlled initiation of actions by means of a limited circle of users, whereby said actions can be carried out in an appliance
DE60029456T2 (en) Method for online adjustment of pronunciation dictionaries
DE102018215293A1 (en) Multimodal communication with a vehicle
DE10327943B4 (en) Different number reading modes allowing speech recognition system
DE10111121B4 (en) Method for speaker recognition for the operation of devices
EP1083479A1 (en) Operation method for a voice controlled input device in an automotive vehicle
EP0983906A2 (en) Procedure and control device for operating vehicle technical devices
EP0676883A2 (en) Method for recognizing spelled names or terms for communication exchanges
DE10129005A1 (en) Speech recognition method and speech recognition system
DE10063796B4 (en) Speech recognition method for security systems in combination with speech recognition
EP1179818A2 (en) Automatic recognition of company names in speeches
DE102005030967A1 (en) Method and apparatus for interacting with a speech recognition system to select items from lists
DE19933323C2 (en) Speech recognition system and method for speech recognition of predefined speech patterns, in particular for the speech control of motor vehicle systems

Legal Events

Date Code Title Description
8127 New person/name/address of the applicant

Owner name: KOEHLER, DIETMAR, DIPL.-ING, 04600 ALTENBURG, DE K

8130 Withdrawal