[go: up one dir, main page]

DE10116142A1 - Method of speaker voice recognition by telephone signals, involves picking off the voice signal via a microphone forming part of the telephone - Google Patents

Method of speaker voice recognition by telephone signals, involves picking off the voice signal via a microphone forming part of the telephone

Info

Publication number
DE10116142A1
DE10116142A1 DE10116142A DE10116142A DE10116142A1 DE 10116142 A1 DE10116142 A1 DE 10116142A1 DE 10116142 A DE10116142 A DE 10116142A DE 10116142 A DE10116142 A DE 10116142A DE 10116142 A1 DE10116142 A1 DE 10116142A1
Authority
DE
Germany
Prior art keywords
telephone
voice recognition
signal via
forming part
voice signal
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Withdrawn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
DE10116142A
Other languages
German (de)
Inventor
Werner Zuehlke
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.)
Technische Universitaet Ilmenau
Original Assignee
Technische Universitaet Ilmenau
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 Technische Universitaet Ilmenau filed Critical Technische Universitaet Ilmenau
Priority to DE10116142A priority Critical patent/DE10116142A1/en
Publication of DE10116142A1 publication Critical patent/DE10116142A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/247—Telephone sets including user guidance or feature selection means facilitating their use
    • 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
    • G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
    • G10L19/0018—Speech coding using phonetic or linguistical decoding of the source; Reconstruction using text-to-speech synthesis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/60—Substation equipment, e.g. for use by subscribers including speech amplifiers
    • H04M1/6008—Substation equipment, e.g. for use by subscribers including speech amplifiers in the transmitter circuit
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2250/00—Details of telephonic subscriber devices
    • H04M2250/74—Details of telephonic subscriber devices with voice recognition means

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Telephonic Communication Services (AREA)

Abstract

A voice recognition method during which voice recognition is undertaken as a subscriber is speaking and the phonetic- or the alphabetic-sequence is transmitted as a text accompanying the voice signal to the receiver. Transmission of the text specifically takes place in the voice pauses.

Description

Die Erfindung betrifft ein Verfahren zur Spracherkennung von Telefonsignalen und kommt bei der telefonischen Sprachsteuerung und beim Protokollieren von Telefongesprächen zur Anwendung.The invention relates to a method for speech recognition of telephone signals and comes in voice control and logging Telephone calls for use.

Die Spracherkennung hat neben den Schwierigkeiten durch unterschiedliche Sprechweise, Aussprachevariationen und Störungen auch mit der durch Bandbe­ grenzung und schwankenden Übertragungsverhältnissen entstehenden Beeinträch­ tigungen bei der Übertragung über den Telefonkanal zu kämpfen.In addition to the difficulties caused by different speech recognition Speech, pronunciation variations and disturbances also with that by Bandbe limitation and fluctuating transmission conditions to struggle with transmission over the telephone channel.

Der Erfindung liegt die Aufgabe zugrunde, die Spracherkennung von Telefonsi­ gnalen so zu gestalten, daß die Beeinträchtigung durch die Übertragungsstrecke entfällt.The invention is based, the speech recognition of Telefonsi the task gnalen so that the impairment caused by the transmission link not applicable.

Die Aufgabe wird nach Anspruch 1 erfindungsgemäß dadurch gelöst, daß die Spracherkennung schon beim sprechenden Teilnehmer vorgenommen wird und der Text begleitend zum Sprechsignal zum Empfänger übertragen wird.The object is achieved according to claim 1 in that the Speech recognition is already carried out at the speaking participant and the Text accompanying the speech signal is transmitted to the receiver.

Nach Anspruch 2 erfolgt die Übertragung des Textes in den Sprachpausen. According to claim 2, the transmission of the text takes place in the language breaks.  

Die Erfindung wird nachstehend an Ausführungsbeispielen erläutert. Zur Spracherkennung beim Sprecher wird das Sprachsignal über ein Mikrofon, das Teil des Telefons sein kann, abgegriffen und über eine Spracherkennung geleitet. Die ermittelte Laut- oder Buchstabenfolge wird in den digitalen Bitfluß eingespeist und zusätzlich zum Sprachsignal übertragen.The invention is explained below using exemplary embodiments. For Speech recognition at the speaker is the speech signal via a microphone that Can be part of the phone, tapped and routed via voice recognition. The determined sequence of sounds or letters is fed into the digital bit flow and transmitted in addition to the voice signal.

Dazu kann das achte Bit einer PCM-Folge verwendet werden oder Datenbits bei Verfahren, die zusätzliche Datenübertragung vorgesehen haben, wie ADPCM- Verfahren nach G.722 oder beim Mobilfunk.The eighth bit of a PCM sequence can be used for this, or data bits can be used Procedures that have provided additional data transmission, such as ADPCM Procedure according to G.722 or for mobile radio.

Wenn die Verzögerung unkritisch ist, kann die Übertragung der Textbits nach Umschaltung des Übertragungsmodems auch in den Sprachpausen erfolgen.If the delay is not critical, the transmission of the text bits can be postponed Switching of the transmission modem also takes place during the speech pauses.

Dieses Verfahren hat den Vorteil, daß die Übertragungsstrecke keinen negativen Einfluß auf die Erkennungsgenauigkeit hat und der Sprecher notfalls sofort Korrekturen einleiten kann. Außerdem können der Sender und der Empfänger ein einheitliches Protokoll über das Gespräch ableiten. Bis auf Übertragungsfehler der Datenbits sind die Protokolle identisch.This method has the advantage that the transmission path is not negative The speaker has an influence on the recognition accuracy and, if necessary, immediately Can initiate corrections. In addition, the transmitter and the receiver can be one derive a uniform protocol for the conversation. Except for transmission errors of the Data bits, the protocols are identical.

Claims (2)

1. Verfahren zur Spracherkennung von Telefonsignalen, dadurch gekennzeichnet, daß beim sprechenden Teilnehmer eine Spracherkennung vorgenommen wird und die Laut- oder die Buchstabenfolge als Text begleitend zum Sprachsignal zum Empfänger übertragen wird.1. A method for speech recognition of telephone signals, characterized in that speech recognition is carried out at the speaking subscriber and the sequence of letters or letters is transmitted as text accompanying the speech signal to the receiver. 2. Verfahren nach Anspruch 1, dadurch gekennzeichnet, daß die Übertragung des Textes in den Sprachpausen vorgenommen wird.2. The method according to claim 1, characterized in that the transmission of Text is made in the language breaks.
DE10116142A 2000-04-05 2001-03-27 Method of speaker voice recognition by telephone signals, involves picking off the voice signal via a microphone forming part of the telephone Withdrawn DE10116142A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
DE10116142A DE10116142A1 (en) 2000-04-05 2001-03-27 Method of speaker voice recognition by telephone signals, involves picking off the voice signal via a microphone forming part of the telephone

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE10016808 2000-04-05
DE10116142A DE10116142A1 (en) 2000-04-05 2001-03-27 Method of speaker voice recognition by telephone signals, involves picking off the voice signal via a microphone forming part of the telephone

Publications (1)

Publication Number Publication Date
DE10116142A1 true DE10116142A1 (en) 2001-12-20

Family

ID=7637601

Family Applications (1)

Application Number Title Priority Date Filing Date
DE10116142A Withdrawn DE10116142A1 (en) 2000-04-05 2001-03-27 Method of speaker voice recognition by telephone signals, involves picking off the voice signal via a microphone forming part of the telephone

Country Status (1)

Country Link
DE (1) DE10116142A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8096579B2 (en) 2003-10-17 2012-01-17 Volkswagen Ag Motor vehicle having an occupant protection system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4473904A (en) * 1978-12-11 1984-09-25 Hitachi, Ltd. Speech information transmission method and system
DE3719490C2 (en) * 1986-03-19 1994-09-15 Baymak Faruk Arrangement for the wireless transmission of information
DE19806927A1 (en) * 1998-02-19 1999-08-26 Abb Research Ltd Method of communicating natural speech
US6035273A (en) * 1996-06-26 2000-03-07 Lucent Technologies, Inc. Speaker-specific speech-to-text/text-to-speech communication system with hypertext-indicated speech parameter changes

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4473904A (en) * 1978-12-11 1984-09-25 Hitachi, Ltd. Speech information transmission method and system
DE3719490C2 (en) * 1986-03-19 1994-09-15 Baymak Faruk Arrangement for the wireless transmission of information
US6035273A (en) * 1996-06-26 2000-03-07 Lucent Technologies, Inc. Speaker-specific speech-to-text/text-to-speech communication system with hypertext-indicated speech parameter changes
DE19806927A1 (en) * 1998-02-19 1999-08-26 Abb Research Ltd Method of communicating natural speech

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8096579B2 (en) 2003-10-17 2012-01-17 Volkswagen Ag Motor vehicle having an occupant protection system

Similar Documents

Publication Publication Date Title
DE60034551T2 (en) Communication protocol between a communication device and an external attachment
DE69839260T2 (en) METHOD AND DEVICE FOR USING CONDITIONAL STATEMENT FOR CONTROLLING FUNCTIONAL PARTS IN DIGITAL TELEPHONE SYSTEMS
DE69734668D1 (en) CONFERENCE CALLING SYSTEM AND METHOD FOR A WIRELESS COMMUNICATION CHANNEL
CN104539816A (en) Intelligent voice mixing method and device for multi-party voice communication
EP0120325A1 (en) Circuit arrangement for a hands free telephone
NO960979D0 (en) Method and apparatus for voice transmission in a mobile communication system
US20030120489A1 (en) Speech transfer over packet networks using very low digital data bandwidths
DE102009035796A1 (en) Notification of audio failure in a teleconference connection
DE10116142A1 (en) Method of speaker voice recognition by telephone signals, involves picking off the voice signal via a microphone forming part of the telephone
DE2820096A1 (en) Telephone instrument with remote listening unit - uses earphones with radio receiver and transmitter in instrument modulated by speech signal
CH634702A5 (en) Information transmission system
US7230955B1 (en) System and method for improved use of voice activity detection
DE59905927D1 (en) MICROPHONE ARRANGEMENT FOR VOICE RECOGNITION UNDER VARIABLE SPACIAL CONDITIONS
EP0156826A1 (en) Telephone transmission installation.
DE3034569C2 (en) Voice operated speakerphone
DE4426226A1 (en) Circuit arrangement for transmitting coded speech signals
DE19530678C2 (en) Subscriber terminal
DE102005015083B4 (en) Method and device for preventing interference from speaking sounds when making a call
EP0848561A2 (en) Method of transmitting digital payload and signalling data over a single channel
SU1674226A1 (en) Method and apparatus for detecting speech signals and their boundaries
EP1531570A3 (en) Method for improving the reproduction quality in a packet based transmission of audio/video data
DE102004044387B4 (en) communication system
EP4375990A3 (en) Method for training a speaker recognition unit of a hearing aid and combination of such a hearing aid and a communication device
DE3219953C2 (en) Transfer arrangement for the transfer of calls from a two-wire line to an intercom
DE19806927A1 (en) Method of communicating natural speech

Legal Events

Date Code Title Description
OM8 Search report available as to paragraph 43 lit. 1 sentence 1 patent law
8139 Disposal/non-payment of the annual fee