CN1387663A - System and method of increasing recognition rate of speech-input instructions in remote communication terminals - Google Patents

System and method of increasing recognition rate of speech-input instructions in remote communication terminals Download PDF

Info

Publication number
CN1387663A
CN1387663A CN00815370A CN00815370A CN1387663A CN 1387663 A CN1387663 A CN 1387663A CN 00815370 A CN00815370 A CN 00815370A CN 00815370 A CN00815370 A CN 00815370A CN 1387663 A CN1387663 A CN 1387663A
Authority
CN
China
Prior art keywords
character
signal
character string
module
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.)
Granted
Application number
CN00815370A
Other languages
Chinese (zh)
Other versions
CN1191566C (en
Inventor
A·D·希门尼斯·费尔特斯特伦
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.)
Telefonaktiebolaget LM Ericsson AB
Original Assignee
Telefonaktiebolaget LM Ericsson AB
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 Telefonaktiebolaget LM Ericsson AB filed Critical Telefonaktiebolaget LM Ericsson AB
Publication of CN1387663A publication Critical patent/CN1387663A/en
Application granted granted Critical
Publication of CN1191566C publication Critical patent/CN1191566C/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/26Devices for calling a subscriber
    • H04M1/27Devices whereby a plurality of signals may be stored simultaneously
    • H04M1/271Devices whereby a plurality of signals may be stored simultaneously controlled by voice recognition
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/72Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724User interfaces specially adapted for cordless or mobile telephones

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Signal Processing (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Telephone Function (AREA)
  • Telephonic Communication Services (AREA)
  • Monitoring And Testing Of Exchanges (AREA)

Abstract

A method for enhancing the accuracy of speech-based dialing of remote communication terminals, and terminals incorporating the method, are disclosed. Analog speech input representative of a desired phone number is converted to a digital signal. An automatic speech recognition module identifies the digits and produces an output signal representative of the digits. A determining module applies a test to determine whether one or more digits in the phone number were not recognized by the conversion module. If the phone number includes unrecognized digits, a search module searches an associated memory module for phone numbers having digits that match the recognized digits of the phone number input by the user. Phone numbers from the memory that match may be presented to the user, either visually or audibly. If desired, the remote terminal may establish a connection with the phone number selected from the memory module.

Description

The system and method for increase discrimination of speech-input instructions in telecommunication terminal
The present invention relates to the phonetic entry identification in communication facilities, more specifically, relate to the system and method that is used for strengthening in telecommunication terminal voice dialing system degree of accuracy.
The telecommunication terminal that is written into mobile phone is very general in many modern industrializations country.Most of telecommunication terminals use keypad as input equipment.Yet there is some shortcoming in keypad.At first, the use of keypad may require the user that notice is turned to this communication facilities, as long as one section is carved in short-term.In some cases, such as when driving, this does not expect.In addition, market is constantly ordered about manufacturer and is produced littler remote telephone terminal equipment, and this equipment is also referred to as mobile phone.The reducing to make of this terminal device size more may produce the mistake of keypad, thereby reduced the degree of accuracy as the keypad of input equipment.
Manufacturer has realized being suitable for receiving a phonetic entry, discerns this input, and carries out a voice-based input equipment based on the action of this input.For instance, authorize the U.S. patent No.4 of Kuniyoshi, 959,850 disclose a radio telephone device, and it comprises the speech identifying function based on phonetic dialing that is used for phone.Similarly, authorize the U.S. patent No.5 of Sakanishi, 042,063 and authorize people's such as Gerson U.S. patent No.4,870,686 disclose a use can carry out telephone device based on the speech identifying function of phonetic dialing.Speech identifying function also is disclosed in the following reference paper: authorize the U.S. patent No.5 of Will, 917,891; Authorize people's such as Maekawa U.S. patent No.5,884,257; Authorize people's such as Eting U.S. patent No.5,651,056; Authorize the U.S. patent No.5 of Meador, 638,425; Authorize the U.S. patent No.5 of Peterson, 509,049; Authorize the U.S. patent No.5 of Jakatdar, 495,533; With the U.S. patent No.5 that authorizes people such as Hunt, 303,299.
Yet speech recognition is a very difficult task, especially when voice signal with from the fuzzy noise of surrounding environment, when for example automobile noise and street noise combine.Inappropriate pronunciation and/or interference from fuzzy noise can make user's voice not discerned by equipment.In voice-based dialing application, this can cause telephone plant to transfer to an incorrect number.Alternatively, this telephone plant can impel the user to repeat unrecognized numerical digit, or whole Serial No..The precision that depends on speech recognition system, the user may be required the time duplicate numbers of significant proportion, this makes voice-based dialing characteristic become inconvenient for the user.
Therefore, in the art, exist improved needs based on voice dialing system and method.
The present invention is devoted to by providing a kind of apparatus and method based on phonetic dialing that are used to improve the telecommunication terminal that comprises mobile phone to solve these and other problems.According to the present invention, a remote terminal is applicable to and uses the information that is kept in the storer to strengthen speech recognition routine precision.Preferably, this information comprises the information about the telephone number before dialled by this remote terminal, this information can with the precision that is complementary by the telephone number of importing based on voice dial-up method with the enhancing speech recognition system.
An aspect the invention provides a system based on phonetic dialing that is used to promote communication facilities.This system comprises that a phonetic entry that is used for receiving an input character sequence represents and be created in the modular converter of signal indication of each character of this input character sequence, one is used for determining whether this input character sequence comprises the judge module of unknown character, memory module that comprises a plurality of character strings in response to the network disciple and one are used for having corresponding to the search module of the character string of the character of identification character in input character sequence one of memory module search.In the use, if modular converter can not be with one and a plurality of character conversion in this input character sequence, this search module can in memory module, search for have with input character sequence in one or more character strings of the character that is complementary of identification character.
On the other hand, the invention provides promotion method based on audio call in communication facilities.This method may further comprise the steps: the phonetic entry that receives desired character string is represented, produce a signal indication of each character in this character string, determine whether this input character sequence comprises unknown character, with if unknown character is arranged, then search for one and have, and produce the signal indication of a coupling character string corresponding to the coupling character string of the character of identification character in input character sequence.
These and other purposes of the present invention, feature and advantage will also become clearer in conjunction with the accompanying drawings by the description of this instructions.
Fig. 1 is a block diagram that is suitable for realizing exemplary gsm communication of the present invention;
Fig. 2 shows according to an embodiment of the invention, is used for improving the method flow diagram in the voice-based calling of a communication facilities; With
Fig. 3 is the schematic diagram of telecommunication terminal according to an embodiment of the invention.
Today, employed many digital radio system used time slot formula connecting system.User's information (for example voice) is by segmentation, compression, grouping and transmitting in preallocated time slot.Time slot can be assigned to different users, is commonly called time-division multiple access (TDMA) (TDMA) mechanism.Time-division multiple access (TDMA) (TDMA) communication system, such as global system for mobile communications (GSM) in Europe, digital advanced mobile phone system (D-AMPS) in the North America, or in personal digital honeycomb (PDC) system of Japan, how far permission shares the single radio frequency channels between the journey terminal, thereby has increased capability of communication system.
Exemplary embodiment subsequently is provided in the environment of time-division multiple access (TDMA) (TDMA) radio communications system.Yet, those skilled in the art will recognize that TDMA methodology only is to be described for exemplary purpose, and the present invention is easy to be applicable to and comprises frequency division multiple access (FDMA) that TDMA is in all types of access techniques of Code Division Multiple Access (CDMA) and their mixing.
At the file ETS of ETSI (ETSI) 300 573, the operation according to the cellular communication system of GSM standard has been described among ETS 300 574 and the ETS 300 578, these files are referred to herein as a reference.Therefore, the running of an exemplary gsm system is only briefly described once more.Though real name is described with the exemplary embodiment in gsm system, those skilled in the art should recognize that the present invention also can be used in other the communication system.
With reference to Fig. 1, described one and wherein can implement communication system 10 of the present invention.This system 10 is a hierarchical network with the multilayer that is used for administer calls.Use the wireless frequency of one group of up-link and downlink, the telecommunication terminal 12 of working in system 10 uses the time slot of distributing to them on these frequencies to participate in calling.In the layering on a top, one group of mobile switching centre (MSCs) 14 will send to the destination from the call routing of originator.Particularly, the setting that these entities are responsible for calling out, control and termination.A MSCs14 is commonly referred to a gateway MSC, with public switched telephone network (PSTN) 18, comes together to handle with other public and private network and communicates by letter.
Among the MSCs14 each is connected to one and a plurality of base station controllers (BSCs) 16.According to GSM standard, BSC16 comes to communicate with a MSC14 by the standard interface that is called as the A-interface, and this interface is based on the MAP of CCITT signaling system No.7.
Each one of control and a plurality of basic transmitting-receiving stations (BTSs) 20 among the BSCs16.Each BTS20 comprises that one or more use uplink and downlink link radio frequencies (RF frequency) think a particular geographic area, and transceiver (TRXs) (not shown) of service is provided such as one and a plurality of communication cells 21.BTSs20 mainly is provided for launching data burst (burst) at they remote stations 12 in the sub-district and receive RF link from the data burst of these remote stations separately.In one exemplary embodiment, a plurality of BTSs20 are included in the radio base station (RBS) 22.RBS 22, for example, can construct according to RBS200 product family of gang, and these products are by Telefonaktiebolaget LM Ericsson company, and assignee of the present invention provides.For with the more details of the realization of exemplary distal end station 12 and RBS22, interesting reader can be referring to the U.S. patent No.5 that authorizes people such as Frodigh, 909,469, disclosing of this document is referred to herein as a reference.
Fig. 2 has represented a synoptic diagram that is suitable for according to the remote terminal in the use of the present invention 200.Remote terminal 200 preferably one be used for digital TDMA cellular communications system, such as gsm system, PDC system, or the mobile phone in the D-AMPS system.Yet aforesaid, the present invention can be applied in all types of connecting systems, and can easily be applied to TDMA or cdma system, or in their commingled system.Remote terminal is known and is can obtain on the market.Therefore, only describe those aspects relevant of remote terminal 200 below in detail with the present invention.For other information that relate to remote terminal, interesting reader can be referring to the U.S. patent No.5 that authorizes people such as Dent, and 745,523, this document is referred to herein as a reference.
With reference to Fig. 2, remote terminal 200 comprises, in relevant portion, and a microphone 210 that is used to receive from phone user's voice.Microphone 210 is connected to modular converter 220.Modular converter 220 can comprise modulus (A/D) converter 224 that is used for the analog voice input is converted to digital signal.Modular converter 220 can also comprise automatic speech recognition (ASR) module 228 that is used to discern user's voice.Remote terminal 200 comprises that also one is used for determining whether ASR module 228 identifies a judge module 230 by the said character of user with desired precision.Remote terminal 200 also comprises the memory module 250 and the search module 240 that is used for searching storage module 250 that are used to preserve the character string of representing effective telephone-number.Remote terminal 200 comprises that also one is used to set up and the link block that communicates to connect 260 such as the communication network of as shown in Figure 1 GSM network.Remote terminal 200 also comprises a display 270 that is fit to (for example, a LED and LCD display) that is used for information is shown to the user.Terminal with suitable sound identification module is for by obtainable T28 on the market that Ericsson provided.
What we wished is that the some or all of modules among the module 220-260 are embedded a suitable special IC (ASIC) or a programmable digital signal processor (DSP), or is one group of chipset that comprises a plurality of ASIC.Between the miscellaneous part of each module 200-260 and remote terminal, be formed with electrical connection.For example, judge module 230 and search module 240 are electrically connected to display 270, to loudspeaker 280 with to link block 260.
In addition, in a preferred embodiment, the relevant telephone number of connection that the electrical connection between memory module 250 and link block 260 makes memory module 250 to preserve to be set up with remote terminal 200.For example, each user is with in the telephone number input remote terminal 200, and this number can be stored in the memory module 250.In this way, memory module 250 can keep the phone number list of a previous dialing, and these telephone numbers can be used as the previous information of enhancing based on the precision of phonetic dialing, and are as described below.
Fig. 2 shows a kind of method based on phonetic dialing according to an embodiment of the invention.In brief, with reference to Fig. 3, this method comprises that one of reception is one with this character conversion and is stoped signal by the said character of user, and determines whether this character string is complete.If this character string is imperfect, then this system repeatedly receives other character and is digital signal with these character conversion.After receiving a complete character string, system judges whether this character string comprises one and a plurality of Unidentified characters.If this character string does not comprise Unidentified character, then being sent to of this character string is used to make phone to transfer in response to the module of the number of identification character sequence (for example link block).If this character string comprises one and a plurality of unknown characters, then call a search module.Numerical digit corresponding in identification character and the character string in relational storage that this search module will be in this character string is compared to determine whether that a character string in storer may be matched with the character string of user's input.When detecting a possible coupling, this character string can be sent to one and be used to make this phone to transfer in response to the module of the corresponding number of identification character sequence.Alternatively, the user that character string can be shown and acoustically phone is given in performance, this user can indicate this character string in fact whether to be matched with desired character string.To explain this process in more detail below.
In one exemplary embodiment, the process among Fig. 3 is implemented in a telecommunication terminal that has based on the phonetic dialing characteristic, for example in the mobile phone.With reference to figure 3, in step 310, voice-based dialing characteristic is activated and remote terminal is received in the phonetic entry of first character in the character string represents.In the U.S., known ten dialing formats (for example, in xxx-xxx-xxxx) preferably represented in this character.Yet we expect that this character string can be the form that is applicable to the dial system of different geographic regions, or can represent the network address (for example, a URL or an IP address) in a data network in a kind of digital application.Alternatively, this character string can represent to point to the instruction of a remote terminal, or comprises a storage address that is used for the number of speed dialling.
In step 320, the character that has received is converted into the digital signal of an expression by the said character of this user.This conversion can use the suitable ASR module of an analog to digital (A/D) converter incorporates to realize.Many ASR modules realize being used to being reported as the statistics routine of the measure of reliability of the judgement that a specific character does.Desired reliability can be been programmed in the logical circuit of ASR module, or can be by user-selected and be input in the system as a parameter.The ASR module is known in the field, and the detail of ASR module and the present invention are irrelevant.
In step 330, carry out a test and whether finish with the input of determining this character string.For example, in US telephone system, it uses the form of ten characters, just thinks that the input of this character string finishes when the tenth character of input.In another embodiment, determining step can use overtime routine, and is promptly depleted after a specific character input when a schedule time, supposes that then this character string is done.In another optional embodiment, a user can be by indicating this character string to finish by a specified button or by saying a special code on one's own initiative.Person of skill in the art will appreciate that many kinds can detect other modes of the termination of an input character sequence.If this character string is not finished, then step 310 to 330 can repeat to finish until this character string, or the user indicates this phonetic entry process of hope cancellation.
After definite this character string is finished,, carry out a test to determine whether this character string comprises one or more unknown characters in step 340.At this, term " unknown character " should refer in this character string the character do not confirmed by the ASR module.In one embodiment, this system can test to determine that the measure of reliability relevant with the one or more characters in the character string is whether less than a predetermined threshold (for example 95%, or 90%), if then this character string can be confirmed as having unknown character.Also can adopt other test.For example, if the measure of reliability relevant with two characters less than a predetermined threshold, then this character string can be confirmed as having unknown character.
If this character string does not comprise unknown character, then in step 380, this character string by dialing and remote terminal 200 attempt to set up one with being connected of network.
If this character string comprises unknown character, then in step 350, memory module relevant with remote terminal is searched to determine whether that a character string in this memory module is matched with the identification character in the character string of user's input.If in step 360, find a coupling, then show alternatively and give the user by this character string of search in this storer and in step 370.At an embodiment, this character string for example visually shows to the user by a LCD display or other suitable displays.In another embodiment, give user with this character string in performance acoustically with a voice operation demonstrator.After the indication that receives from user's agreement, group be this character string in step 380.
With what recognize is that some or all of steps among the step 310-380 can be by a proper A SIC, DSP, or a chipset, or operate by the logical order on a general processor and to implement.
Though the present invention describes in detail with reference to several exemplary embodiment, those skilled in the art will be appreciated that and can do various remodeling and do not deviate from the present invention.Therefore, the present invention is only limited by subsequently claim, and this claim is intended to comprise all equivalents of the present invention.

Claims (16)

1. be used to improve the system of the phonetic dialing of communication facilities, comprise:
The modular converter of signal indication of each character of this input character sequence is represented and is created in phonetic entry that is used for receiving an input character sequence,
One is used for determining whether this input character sequence comprises the judge module of unknown character,
A memory module that comprises a plurality of character strings in response to the network disciple,
With one be used for having corresponding to the search module of the character string of the character of identification character in input character sequence one of memory module search;
Like this, if modular converter can not be with one and a plurality of character conversion in this input character sequence, this search module can in memory module, search for have with input character sequence in one or more character strings of the character that is complementary of identification character.
2. the system of claim 1, wherein this modular converter comprises:
One is used for the digitized A/D converter of the voice input signal that is received.
3. the system of claim 1, wherein this modular converter comprises:
One is used to analyze this digital signal and produce the sound identification module of being indicated by the signal of the represented character string of this digital signal.
4. the system of claim 1, wherein:
This modular converter produces the signal that is used to represent the level of trust relevant with conversion accuracy; With
This judge module produces the signal whether this level of trust of expression is higher than a predetermined threshold.
5. the system of claim 1, wherein:
This modular converter and judge module are embedded in the digital signal processor.
6. the system of claim 1 also comprises:
A signal that is used for producing a character string that is illustrated in storer.
7. the system of claim 6 also comprises:
Be used to show the display apparatus module of the character string that the signal that produced by this output module is represented.
8. the system of claim 6 also comprises:
Be used for the module of sound announcement by the represented character string of the signal that output module produced.
9. the system of claim 1 also comprises:
One is used to set up and the link block that is connected by the character string of the signal indication that output module produced.
Promotion in communication facilities based on the method for audio call
May further comprise the steps:
The phonetic entry that receives desired character string represents,
Produce a signal indication of each character in this character string,
Whether comprise unknown character and unknown character arranged if determine this input character sequence, then search for one have corresponding in input character sequence the coupling character string of the character of identification character and
Produce the signal indication of a coupling character string.
11. the method for claim 10, the step that wherein is used for producing a signal indication of this each character of character string comprises the voice input signal digitizing that will be received.
Analyze this digital signal and produce signal indication 12. the method for claim 11, the step that wherein is used for producing a signal indication of this each character of character string comprise by the represented character string of this digital signal.
13. the method for claim 10, the step that wherein is used for producing a signal indication of this each character of character string produces first signal that is used to represent the level of trust relevant with conversion accuracy.
14. the method for claim 13 is used for wherein determining whether this input character sequence comprises that unknown character comprises relatively this level of trust and a predetermined threshold and produces one and represent whether this level of trust is higher than the secondary signal of a predetermined threshold.
15. the method for claim 10 also comprises the character string of demonstration by the signal indication that output module produced.
16. the method for claim 10 also comprises with the sound announcement by the represented character string of the signal that output module produced.
CNB008153701A 1999-11-04 2000-10-31 System and method of increasing recognition rate of speech-input instructions in remote communication terminals Expired - Fee Related CN1191566C (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US43414199A 1999-11-04 1999-11-04
US09/434,141 1999-11-04

Publications (2)

Publication Number Publication Date
CN1387663A true CN1387663A (en) 2002-12-25
CN1191566C CN1191566C (en) 2005-03-02

Family

ID=23722981

Family Applications (1)

Application Number Title Priority Date Filing Date
CNB008153701A Expired - Fee Related CN1191566C (en) 1999-11-04 2000-10-31 System and method of increasing recognition rate of speech-input instructions in remote communication terminals

Country Status (5)

Country Link
EP (1) EP1226576A2 (en)
JP (1) JP2003513341A (en)
CN (1) CN1191566C (en)
AU (1) AU1390501A (en)
WO (1) WO2001033553A2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105830151A (en) * 2014-01-15 2016-08-03 宝马股份公司 Method and system for generating a control command

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10120513C1 (en) 2001-04-26 2003-01-09 Siemens Ag Method for determining a sequence of sound modules for synthesizing a speech signal of a tonal language
KR100412474B1 (en) * 2001-06-28 2003-12-31 유승혁 a Phone-book System and Management Method Of Telephone and Mobile-Phone used to Voice Recognition and Remote Phone-book Server
KR100869878B1 (en) * 2001-12-31 2008-11-24 주식회사 케이티 System for generating pronunciation dictionary in intelligent network services using voice recognition and method for using the same system
US8442331B2 (en) 2004-02-15 2013-05-14 Google Inc. Capturing text from rendered documents using supplemental information
US10635723B2 (en) 2004-02-15 2020-04-28 Google Llc Search engines and systems with handheld document data capture devices
US20080313172A1 (en) 2004-12-03 2008-12-18 King Martin T Determining actions involving captured information and electronic content associated with rendered documents
US20070300142A1 (en) 2005-04-01 2007-12-27 King Martin T Contextual dynamic advertising based upon captured rendered text
US9143638B2 (en) 2004-04-01 2015-09-22 Google Inc. Data capture from rendered documents using handheld device
US9116890B2 (en) 2004-04-01 2015-08-25 Google Inc. Triggering actions in response to optically or acoustically capturing keywords from a rendered document
US7990556B2 (en) 2004-12-03 2011-08-02 Google Inc. Association of a portable scanner with input/output and storage devices
US8874504B2 (en) 2004-12-03 2014-10-28 Google Inc. Processing techniques for visual capture data from a rendered document
US9460346B2 (en) 2004-04-19 2016-10-04 Google Inc. Handheld device for capturing text from both a document printed on paper and a document displayed on a dynamic display device
US8620083B2 (en) 2004-12-03 2013-12-31 Google Inc. Method and system for character recognition
US8346620B2 (en) 2004-07-19 2013-01-01 Google Inc. Automatic modification of web pages
WO2006023937A2 (en) * 2004-08-23 2006-03-02 Exbiblio B.V. A portable scanning device
US8447066B2 (en) 2009-03-12 2013-05-21 Google Inc. Performing actions based on capturing information from rendered documents, such as documents under copyright
WO2010105246A2 (en) 2009-03-12 2010-09-16 Exbiblio B.V. Accessing resources based on capturing information from a rendered document
US9081799B2 (en) 2009-12-04 2015-07-14 Google Inc. Using gestalt information to identify locations in printed information
US9323784B2 (en) 2009-12-09 2016-04-26 Google Inc. Image search using text-based elements within the contents of images

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH03144877A (en) * 1989-10-25 1991-06-20 Xerox Corp Method and system for recognizing contextual character or phoneme
DE19532114C2 (en) * 1995-08-31 2001-07-26 Deutsche Telekom Ag Speech dialog system for the automated output of information
JP3427692B2 (en) * 1996-11-20 2003-07-22 松下電器産業株式会社 Character recognition method and character recognition device
WO1999035806A1 (en) * 1998-01-09 1999-07-15 Alcatel Usa, Inc. Method and system for totally voice activated dialing

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105830151A (en) * 2014-01-15 2016-08-03 宝马股份公司 Method and system for generating a control command

Also Published As

Publication number Publication date
WO2001033553A2 (en) 2001-05-10
CN1191566C (en) 2005-03-02
WO2001033553A3 (en) 2001-11-29
AU1390501A (en) 2001-05-14
JP2003513341A (en) 2003-04-08
EP1226576A2 (en) 2002-07-31

Similar Documents

Publication Publication Date Title
CN1191566C (en) System and method of increasing recognition rate of speech-input instructions in remote communication terminals
FI116964B (en) Method and apparatus for extracting acoustic signals for mobile terminals
US5384825A (en) Method for memory dialing for cellular telephones
US6751481B2 (en) Dialing method for effecting international call in intelligent cellular phone
US5787159A (en) Use of caller ID information
RU98108604A (en) METHOD AND DEVICE FOR ENSURING THE IMPROVED INTERFACE OF THE CALLING SUBSCRIBER IN THE STATIONARY CELLULAR COMMUNICATION SYSTEM
GB2377856A (en) International calling method for mobile phone
JPH09200836A (en) System and method for locating position of radio terminal equipment
JPH09502333A (en) Cellular network based positioning system
CN1111081A (en) Virtual pager for general purpose data terminal
CA2328278A1 (en) Telephone number area code preprocessor
JPH11285039A (en) Method for preparing direct call selecting function in communication device
WO2000056047A3 (en) Method and facility for ascertaining subscriber call numbers by inputting the motor vehicle registration number in order to make it possible to contact an owner of a motor vehicle via a mobile radio telephone network
US20030007608A1 (en) System and method for making calls to vanity numbers using voice dialing
JPH06318976A (en) Telecommunication network
JPH10276257A (en) Telephone system
JP3118620B2 (en) Automatic dial telephone system with directory assistance
WO1992003882A1 (en) Dialing editing method and apparatus
US20050105713A1 (en) Intelligent telephone number dialer and method
JPH11298966A (en) Portable telephone communication system
EP0972396A1 (en) Operating a communications network
KR20000001057A (en) Method for providing telephone number in mobile radio communication system
CN1227451A (en) Terminal incoming indicator of personal handy phone system and indication method thereof
WO2002013547A2 (en) Method and apparatus for displaying a call notification message prior to a call acceptance
KR950013136A (en) Extension call device by voice guidance in key phone system and method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
C19 Lapse of patent right due to non-payment of the annual fee
CF01 Termination of patent right due to non-payment of annual fee