CN100346625C - Telephone voice interactive system and its realizing method - Google Patents
Telephone voice interactive system and its realizing method Download PDFInfo
- Publication number
- CN100346625C CN100346625C CNB021592446A CN02159244A CN100346625C CN 100346625 C CN100346625 C CN 100346625C CN B021592446 A CNB021592446 A CN B021592446A CN 02159244 A CN02159244 A CN 02159244A CN 100346625 C CN100346625 C CN 100346625C
- Authority
- CN
- China
- Prior art keywords
- user
- voice
- navigation elements
- processing unit
- audio processing
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The present invention discloses a telephone voice interaction system which comprises a main control unit and at least one working unit, wherein the main control unit is used for creating more than one working unit and a functional unit inside each working unit, and is used for controlling the data exchange and the data storage of the coming and going messages in the system; the working unit is used for realizing the voice interaction process of the whole system. Each working unit further comprises a situation navigation unit used for realizing logic processing, systematic dynamic configuration and information provision in the process of voice interaction and a voice processing unit used for realizing various kinds of processing of telephone voice, wherein the situation navigation unit is connected with external information providing equipment, and the voice processing unit is connected with a telephone voice board card. The present invention also discloses a method for realizing the telephone voice interaction at the same time; the system and the method can accurately recognize the currently input voice of a user, and support the system to carry out processing by different kinds of guiding logic so as to ensure the normal operation of the system. The present invention not only enhances the processing capability and the processing efficiency of the system, but also facilitates the user.
Description
Technical field
The present invention relates to the treatment technology of call voice, refer to a kind of especially based on interactive telephone phonetic system natural language, that be used for mail management and its implementation.
Background technology
Along with the continuous maturation with the voice application technology be on the increase to various automations, intellectualizing system demand, variously finish the specific feature navigator interactive system of system based on voice suggestion guiding user and day by day increase, use and relate to telephone number, stock and other various information service fields.Therefore voice-based IAS becomes a very active field, and the mail with extensive use demand then to be of this field use focus.
At present, read-write for Email, can only by computer with and on the specific software system finish, like this, to the unskilled user of those computer operations, just have certain restriction, this class user might be because technical reason can not in time read or replied mail, not only can be for the user bring a lot of troubles, and may delay urgent incident.If adopt the mode of interactive voice, more simple and convenient concerning the user, but be subjected to the limitation of existing voice recognition technology, existing system often only can provide touch-tone one-way voice mutual or fixedly phonetic order simple mutual, follow the tree of conventional I VR system and weighed function, the light characteristics of experiencing, can not carry out follow-up interactive operation at the user instruction of current identification, can not resolve currently identified user instruction and realize correct guiding, can't embody the advantage that the interactive voice process is flexible, convenient, discrete, jump.
Summary of the invention
In view of this, main purpose of the present invention is to provide a kind of interactive telephone phonetic system, can the current input voice of accurate recognition user, and back-up system is handled with different guiding logics, not only improved the disposal ability and the efficient of system, and the user that is more convenient for uses.
Main purpose of the present invention is to provide a kind of implementation method of call voice processing, can carry out accurate recognition to the current input voice of user, and according to the legal operation of the further automated induction systems of the current state of living in of recognition result and system, to guarantee the normal operation of system, can be simultaneously that the user provides flexibly, simple, convenient, the operation that is easy to realize, for the user provides better service.
For achieving the above object, technical scheme of the present invention is achieved in that
A kind of interactive telephone phonetic system, this system comprises:
Main control unit is used to create the functional unit of an above working cell and each inside, working cell, and the exchanges data and the storage of the message of coming and going in the control system;
At least one working cell, be used to realize the interactive voice process of whole system, each working cell comprises that further sight navigation elements and being used to realizes the Audio Processing Unit to the various processing of call voice, the target operation state that the sight navigation elements semanteme that input is judged according to user speech and system's present located state are determined system is returned the corresponding user of being prompted to;
Wherein, the sight navigation elements provides equipment to link to each other with external information, and Audio Processing Unit links to each other with the call voice integrated circuit board.
In the said system, described main control unit further comprises the message buffer, is used for being the give information information space of storage and exchange of sight navigation elements and Audio Processing Unit.Described sight navigation elements further comprises sight navigation module, external interface module and database, and external interface module provides equipment to link to each other with external information.It is mail server that this external information provides equipment, and then external interface module is the mail interface module.Described Audio Processing Unit further comprises identification module, synthesis module and call processing module, and identification module, synthesis module and call processing module link to each other with the call voice integrated circuit board by the voice plate card application programming interfaces respectively.Described identification module and synthesis module are realized by the identification synthesis server.
A kind of implementation method of interactive telephone phonetic, this method may further comprise the steps:
A. main control unit is pre-created at least one working cell, and is each working cell establishment Audio Processing Unit wherein;
B. when new user inserted, main control unit distributed the working cell of a free time for the active user, and was the sight navigation elements in this current user's building work unit;
C. by Audio Processing Unit play cuing voice and discern the current input voice of user, the sight navigation elements is determined the target operation state of system according to the current state of living in of semanteme and system of the current input voice of the user who is discerned;
D. judge whether target operation state is active user's need state, if judge that then whether target operation state is for logging off, if then log off process ends; Otherwise play the information of user's request, return step c; If target operation state is not active user's a need state, then determine the suggestion voice that dbjective state will be play, return step c.
This method further comprises: be pre-created and store a semantic file that is used to discern the current input voice of user semanteme.
This method further comprises: set a logic state transition diagram according to user's normal or abnormal operation logic in advance, the sight navigation elements is determined the target operation state of system according to this logic state transition diagram.The described logic state transition diagram of real-time update in the interactive voice process.
This method further comprises: new user sets up and calls out when inserting, and Audio Processing Unit distributes the user ID Caller ID of unique binding for each user.
This method further comprises: when Audio Processing Unit can't accurately be discerned the current input voice of user, the sight navigation elements was initiatively play control system the indication that can accurately distinguish the current input voice of user semanteme.
Therefore, interactive telephone phonetic system provided by the present invention and its implementation, create corresponding grammar file and language parsing template according to user's use habit in advance, can discern automatically and the semanteme of definite user input voice, then according to the current state of living in of user input voice and system, further determine the direction and the state of next step operation,, improve the efficient and the success rate of system to satisfy user's business demand.In addition, the present invention adopts the self-navigation logic, be pre-created the logic state transfer organization of guidance system true(-)running, make no matter which kind of state is system be in, the self-navigation logic all can continue operation according to the logically true guidance system of predefined state transitions, thereby make system provide better service, and operation is more flexible, simple, convenient for the user, is easy to realize for the user.
Description of drawings
Fig. 1 forms schematic diagram for system applies of the present invention in the structure of telephone voice mail interactive system;
Fig. 2 is the concrete application example structure chart based on telephone voice mail interactive system of the present invention;
The process chart of Fig. 3 for the user being landed based on telephone voice mail interactive system of the present invention;
The process chart of Fig. 4 for the user being withdrawed from based on telephone voice mail interactive system of the present invention;
Fig. 5 is the guiding logical topology structure chart based on telephone voice mail interactive system of the present invention;
Fig. 6 is the embodiment process chart based on telephone voice mail interactive system of the present invention;
Fig. 7 is the process chart that improves embodiment illustrated in fig. 6.
Embodiment
Being applied to the telephone voice mail interactive system below in conjunction with accompanying drawing with the present invention is example, and the present invention is further described in more detail, that is: voice interactive system is the voice mail interactive system.
Fig. 1 forms schematic diagram based on the structure of telephone voice mail interactive system of the present invention, and as shown in Figure 1, this system mainly comprises two parts: main control unit 10 and working cell 11.Wherein, working cell 11 can be further divided into sight navigation elements 110 and Audio Processing Unit 111 again; Main control unit 10 also comprises a message buffer, is mainly used to provide for the message data of sight navigation elements 110 and Audio Processing Unit 111 information space of storage and exchange.Audio Processing Unit 111 links to each other with the call voice integrated circuit board; Sight navigation elements 110 provides equipment to link to each other with external information, and in the present embodiment, it is mail service equipment that external information provides equipment, as: the Notes of enterprise mail server.Main control unit 10 will be according to call voice integrated circuit board port case, create a plurality of working cells 11, create Audio Processing Unit 111 and sight navigation elements 110 respectively for each working cell 11 again, and the space of exchanges data is provided for the message of contact between Audio Processing Unit 111 and the sight navigation elements 110 by the message buffer module in the main control unit 10.
When new calling inserts, obtain the voice plate card port information that the user dials in by the Audio Processing Unit monitoring, and distribute to the sign Caller ID of the unique binding of each user, main control unit is realized sight navigation elements and Audio Processing Unit message from different user are handled by this Caller ID.
Fig. 2 is the concrete application example structure chart based on telephone voice mail interactive system of the present invention, should be with among the embodiment, the function of telephone voice mail system is mainly realized by the telephone voice mail server, the call voice integrated circuit board also can be placed in this telephone voice mail server, but identification, the complex functionality of identification module and synthesis module realized by independently discerning synthesis server in the Audio Processing Unit.Notes mail server among Fig. 2 is as the remote mail server, and telephone voice mail server, identification synthesis server link to each other with local area network (LAN) respectively with the Notes mail server, and communicate by local area network (LAN).
Based on said structure, system of the present invention operation principle in actual applications is such:
A. behind the telephone voice mail startup of server, main control unit wherein at first will be created several working cells, and is each working cell establishment Audio Processing Unit wherein.
B. when dialing, the user moves or landline telephone, after telephone network incoming voice call mailing system:
1〉main control unit in the telephone voice mail server distributes the working cell of a free time to give the active user earlier, and creates sight navigation elements wherein.
2〉then, main control unit indication identification synthesis server is discerned, is analyzed the voice of user's input and be synthetic, obtains the voice flow of user's input; System judges user's correct semanteme according to resulting voice flow, by the sight navigation elements according to next step state transitions direction of determined semantic decision.That is to say that the sight navigation elements can be determined next step direction of operating according to the semanteme of current state of living in of voice system and user input voice, or determine next step channeling direction how correctly to guide the user to import, this method promptly can be described as Voice Navigation.
Give an example, system's present located state is: " you have two envelope new mails from Zhang San to system plays, and an envelope new mail is from Li Si, which envelope you need listen? " after, wait for the user's voice input.At this moment, if the user is input as " mail of reading Zhang San " or similar voice such as " reading Zhang San's the first envelope mail ", its logic meets normal sequential logic, and then the sight navigation elements is through judging, confirm that next step should turn to and read mail action that the targeted mails of being read is the mail of user's appointment.But this moment, if the user is input as voice messagings such as " mails of replying Zhang San ", then this logic is the logic that does not meet normal sequence, judge the logic state that whether can be transferred to user's specified services from current system mode earlier by the sight navigation elements, if of course, then the sight navigation elements determines that the shift direction of next step operation is the logic state that contains user's specified services; If cannot, then the sight navigation elements determines which state next step should enter the user is imported channeling conduct.
In this process, described semanteme judgement to user input voice is meant and is pre-created and stores a semantic file in system of the present invention, when new user speech input is arranged, the voice of input newly and every kind of semanteme in the semantic file are compared, determine the correct semanteme of current input voice, so that system determines the operation that next step will be carried out.Wherein, the establishment of semantic file is through obtaining numerous user's practical application regular testings.In addition; for can being imported according to system's current state and user, the sight navigation elements semanticly determines that next step wants the state of redirect; system sets a logic state transition diagram according to user's normal or abnormal operation logic in advance; per step navigation operation of sight navigation elements, redirect judge that whole logic-based state transition diagrams finish, and the annexation in this logic state transition diagram between the state point can also increase in real time, delete or upgrade according to the practical application operation.
3〉after the sight navigation elements is determined next step direction of operating, determine the current voice that will play and next step system handles state by Audio Processing Unit according to this direction of operating, then, play corresponding voice to the user, and wait for replying of user by Audio Processing Unit.
4〉after the user imports new voice, receive by Audio Processing Unit, the identification synthesis server is discerned, is analyzed, and determines the semanteme of the current input voice of user; Semanteme is determined shift direction by the sight navigation elements after determining again, returns step 3 afterwards 〉.
Like this circulation execution in step 3 〉, 4, until arriving the current desired business of user, play out the information of user expectation, get back to initial condition then and begin new business, or transfer to the state of user's appointment; Or carrying out cycling normally or unusually logs off up to the user.Wherein, the desired information of user is according to the collection of Notes mail server, adds up and be stored in the sight navigation elements e-mail messages in the database and play.
The handling process of the user being landed based on telephone voice mail interactive system of the present invention is as shown in Figure 3:
Step 301～303: before user's phonetic entry is arranged, main control unit in the voice-mail system of the present invention carries out initialization to the message buffer of self earlier, and create a plurality of working cells and inner Audio Processing Unit thereof simultaneously, wait for new user's access then.
Step 304～306: when new user inserts, the Audio Processing Unit of main control unit indication current working unit is created the sight navigation elements, and Audio Processing Unit is sent out the updating message buffering area and is instructed to main control unit, and new user's relevant information is stored in the message buffer.
Step 307～309: after the sight navigation elements was created successfully, Audio Processing Unit sent new user's login message to the sight navigation elements; After the sight navigation elements is received, in the message buffer of main control unit, read the content of message buffer, and determine the initial environment of mailing system navigation according to the content of being obtained.
Step 310～311: the sight navigation elements is according to determined initial environment updating message buffer contents, and the transmission navigation message is to Audio Processing Unit.
Step 312～313: after Audio Processing Unit is received navigation message, read the current content of message buffer in the message buffer of main control unit, determine next step suggestion voice and set next step interaction mode according to the information of being obtained.
Step 314～316: after suggestion voice was determined, Audio Processing Unit was indicated next step the voice messaging scope that need import of user to the indication language of user side Play System; After the user receives, import corresponding audio response message, this voice messaging is received from the call voice integrated circuit board by voice API by Audio Processing Unit, and finishes further speech recognition and handle with synthetic in the identification of Audio Processing Unit, synthesis module.
Step 317: after the current input speech processes of Audio Processing Unit to new user, process information is delivered to the message buffer, the content of updating message buffering area.
Step 318: Audio Processing Unit sends identification message to the sight navigation elements, shows that the voice that the user imports dispose, and the sight navigation elements can be carried out next step navigation.
Step 319～321: after the sight navigation elements is received identification message, in the message buffer, read new content, determine the navigation step that next step will carry out according to the content of being obtained again, then the content of updating message buffering area.
Step 322: the sight navigation elements sends navigation message to Audio Processing Unit, and the suggestion voice processing unit reads the fresh content in the message buffer.
Step 323～324: Audio Processing Unit reads the fresh content in the message buffer, and determines next step suggestion voice and set next step interaction mode according to the content of being obtained.
Step 325～326: after suggestion voice was determined, Audio Processing Unit was indicated next step the voice messaging scope that need import of user to the indication language of user side Play System; After the user receives, import corresponding audio response message.This voice messaging is received from the call voice integrated circuit board by voice API by Audio Processing Unit, and in the identification of Audio Processing Unit, synthesis module, finish further speech recognition and handle with synthetic, that is: Audio Processing Unit receive the user reply voice after, return step 316, and so forth, up to finishing the current desired business of user, come back to the state that initial condition begins new business or forwards user's appointment to again; Or normally or unusually log off up to the user.
The handling process that the user is withdrawed from based on telephone voice mail interactive system of the present invention is as shown in Figure 4:
Step 401～402: when the user will withdraw from the telephone voice mail system, the user can import the voice messaging that will withdraw from, and Audio Processing Unit is received new voice messaging, the indication that logs off when finding through the identification back, then should indicate storage, updating message buffering area.
Step 403: Audio Processing Unit sends identification message to the sight navigation elements, and prompting sight navigation elements reads the fresh content in the message buffer.
Step 404～406: the sight navigation elements reads the fresh content in the message buffer, and enters according to the content of being obtained and to withdraw from processing procedure, and the content of updating message buffering area.
Step 407～408: the sight navigation elements sends navigation message to Audio Processing Unit, and the notice Audio Processing Unit will finish the sight flow of navigation, and the sight navigation elements withdraws from the sight flow of navigation.
Step 409～410: Audio Processing Unit reads the content in the message buffer, according to the definite access that discharges active user's mutual resource and wait for other new user of the content of obtaining.
From the aforesaid operations process as can be seen, navigation is the most key step among the present invention, and navigation relates to the traffic direction of whole system.From system of the present invention and user's voice alternately, the actual two parts that are divided into navigate: a part is based on system's indication and guiding logic, can be described as navigational logic; Another part is based on the recognition result to user input voice, determines the logic of system mode trend, can be described as semantic logic, and it is lead-in wire to say that these two parts are equivalent to one, and one is lead-in wire to listen.
Fig. 5 is the guiding logical topology structure chart based on telephone voice mail interactive system of the present invention, as shown in Figure 5, from the guiding logic angle as can be seen, the present invention includes semantic logic and navigational logic two parts.Wherein, navigational logic realizes that according to current system and interaction mode the navigation elements of different business function form by a series of, each navigation elements according to system and user's reciprocal process all can unique definite current needs to the suggestion voice of user's channeling conduct and support the navigation grammer of current indication.
When navigation elements generates the indication language, generally can according to user interaction process in the voice of the current input of user catch the current most probable operation of user automatically and be intended to, and clear and definite indication is carried out in the realization of customer service demand.In addition, according to current system and interaction mode, shift the inside that also needs between the navigation elements to carry out navigation elements, i.e. redirect between each business function state is to realize personalized and intelligentized navigation procedure.
Adopt telephone voice mail interactive system of the present invention to realize that the program request mail is an example with the user, Fig. 6 has provided a navigation elements boot flow schematic diagram.As shown in Figure 6, comprised four independently navigation elements in this flow chart, respectively with
Symbolic representation.When the user imports program request and meets the phonetic order of certain condition mail, system judges whether a plurality of similar recognition results earlier, so that the accuracy channeling conduct to identifying information confirms that this process realizes that by a navigation elements that provides guiding to determine recognition result promptly navigation elements 601.The recognition result channeling conduct of a plurality of similar pronunciations that 601 pairs of systems of navigation elements obtain is distinguished, just virtual operator is owing to can't determine the particular content of user speech, and the inquiry process that proposes, such as: the voice that the current input of user can't be distinguished by system still are " Zhang Shan " for " Zhang San ", then navigation elements 601 can play " may I ask you and want to listen a Zhang San, the still mail of Zhang Shan; be the first if the former please say, and and the like." voice suggestion so that obtain the identification of correct semanteme in another way.The so not only clear and definite operation of user expectation, and solved the deficiency that the identification engine is difficult to distinguish to similar sound.
After voice identification result was clear and definite, navigation elements also needed the mail that satisfies same voice condition is further guided, and this process realizes by the navigational logic unit of refinement program request voice condition, promptly finished by navigation elements 602.Only provided expectation such as: active user and read Zhang San's mail, and be more than of Zhang San, at this moment, system can provide " 5 people that are named as Zhang San are arranged; respectively from the A of department, the B of department, the C of department, if you say is that the Zhang San of the A of department please say the first, and and the like." voice suggestion so that accurately finish active user's demand business, this bootup process has effectively solved because the problem that homonymous phenomena of the same name causes system to be given an irrelevant answer.
When system according to reciprocal process can clear and definite user the program request demand time, whether exist according to the mail that satisfies condition, need to determine whether further mutual, help the user to carry out program request again or play-over the user and want the mail listened, herein, the guiding user flow process of program request is again finished by navigation elements 603, play-overs the flow process of customer objective mail and is finished by navigation elements 604.
The realization of above-mentioned logic all is according to realizing that the normal process order that mail is play progressively realizes.But in actual applications, user's input voice are the indication of complete compliance with system not necessarily, when user input voice does not meet system's guiding, predetermined navigation elements can't be handled these voice, in order to guarantee the normal operation of system, system can handle current input voice in conjunction with semantic logic.Semantic logic also needs the current various discrete logics relevant with systemic-function of user are replied and discerns and handle except the continuous logic voice answering directly related with signal language being discerned and supported.
Be example with user shown in Figure 6 program request mail in the voice mail interactive system still, as shown in Figure 7, this system still comprises four navigation elements 601～604, has just increased additional flow process, supplies the flow process after the semantic logical process that is:.That is to say that when when each navigation elements can't be handled current input voice, system can guide from the initial condition of current navigation elements redirect reuse family program request, wait for re-entering or navigation system again of user.
Process shown in Figure 7 shows in any one bootup process, the user may answer according to indication, also can say the discrete answer of some and indication, therefore need realize the response of various user's requests is handled by complete processing to semantic logic without any relation.
In a word, the above is preferred embodiment of the present invention only, is not to be used to limit protection scope of the present invention.
Claims (12)
1, a kind of interactive telephone phonetic system is characterized in that this system comprises:
Main control unit is used to create the functional unit of an above working cell and each inside, working cell, and the exchanges data and the storage of the message of coming and going in the control system;
At least one working cell, be used to realize the interactive voice process of whole system, each working cell comprises that further sight navigation elements and being used to realizes the Audio Processing Unit to the various processing of call voice, the target operation state that the sight navigation elements semanteme that input is judged according to user speech and system's present located state are determined system is returned the corresponding user of being prompted to;
Wherein, the sight navigation elements provides equipment to link to each other with external information, and Audio Processing Unit links to each other with the call voice integrated circuit board.
2, interactive telephone phonetic according to claim 1 system, it is characterized in that: described main control unit further comprises the message buffer, is used for being the give information information space of storage and exchange of sight navigation elements and Audio Processing Unit.
3, interactive telephone phonetic according to claim 1 system, it is characterized in that: described sight navigation elements further comprises sight navigation module, external interface module and database, external interface module provides equipment to link to each other with external information.
4, interactive telephone phonetic according to claim 3 system, it is characterized in that: it is mail server that described external information provides equipment, and described external interface module is the mail interface module.
5, interactive telephone phonetic according to claim 1 system, it is characterized in that: described Audio Processing Unit further comprises identification module, synthesis module and call processing module, and identification module, synthesis module and call processing module link to each other with the call voice integrated circuit board by the voice plate card application programming interfaces respectively.
6, interactive telephone phonetic according to claim 5 system is characterized in that: described identification module and synthesis module are realized by the identification synthesis server.
7, a kind of implementation method of interactive telephone phonetic is characterized in that, this method may further comprise the steps:
A. main control unit is pre-created at least one working cell, and is each working cell establishment Audio Processing Unit wherein;
B. when new user inserted, main control unit distributed the working cell of a free time for the active user, and was the sight navigation elements in this current user's building work unit;
C. by Audio Processing Unit play cuing voice and discern the current input voice of user, the sight navigation elements is determined the target operation state of system according to the current state of living in of semanteme and system of the current input voice of the user who is discerned;
D. judge whether target operation state is active user's need state, if judge that then whether target operation state is for logging off, if then log off process ends; Otherwise play the information of user's request, return step c; If target operation state is not active user's a need state, then determine the suggestion voice that dbjective state will be play, return step c.
8, method according to claim 7 is characterized in that this method further comprises: be pre-created and store a semantic file that is used to discern the current input voice of user semanteme.
9, method according to claim 7; it is characterized in that this method further comprises: set a logic state transition diagram according to user's normal or abnormal operation logic in advance, the sight navigation elements is determined the target operation state of system according to this logic state transition diagram.
10, require 9 described methods according to power, it is characterized in that this method further comprises: the described logic state transition diagram of real-time update in the interactive voice process.
11, method according to claim 7 is characterized in that this method further comprises: new user sets up and calls out when inserting, and Audio Processing Unit distributes the user ID Caller ID of unique binding for each user.
12, method according to claim 7, it is characterized in that this method further comprises: when Audio Processing Unit can't accurately be discerned the current input voice of user, the sight navigation elements was initiatively play control system the indication that can accurately distinguish the current input voice of user semanteme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB021592446A CN100346625C (en) | 2002-12-27 | 2002-12-27 | Telephone voice interactive system and its realizing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB021592446A CN100346625C (en) | 2002-12-27 | 2002-12-27 | Telephone voice interactive system and its realizing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1512747A CN1512747A (en) | 2004-07-14 |
| CN100346625C true CN100346625C (en) | 2007-10-31 |
Family
ID=34237384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB021592446A Expired - Fee Related CN100346625C (en) | 2002-12-27 | 2002-12-27 | Telephone voice interactive system and its realizing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100346625C (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101141526B (en) * | 2006-09-08 | 2011-08-10 | 中国电信股份有限公司 | Method of implementing voice navigation |
| CN101951553B (en) * | 2010-08-17 | 2012-10-10 | 深圳市车音网科技有限公司 | Navigation method and system based on speech command |
| CN108417215A (en) * | 2018-04-27 | 2018-08-17 | 三星电子（中国）研发中心 | A kind of playback equipment exchange method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1224203A (en) * | 1998-01-20 | 1999-07-28 | 白涛 | Intelligent instantaneous synchronous Chinese and English machine translation method for translating from each into other |
| CN1329739A (en) * | 1998-10-16 | 2002-01-02 | 艾利森电话股份有限公司 | Voice control of a user interface to service applications |
| CN1368719A (en) * | 2001-02-02 | 2002-09-11 | 国际商业机器公司 | Method and system for automatic generating speech XML file |
| WO2002073449A1 (en) * | 2001-03-14 | 2002-09-19 | At & T Corp. | Automated sentence planning in a task classification system |
| WO2002087201A1 (en) * | 2001-04-19 | 2002-10-31 | British Telecommunications Public Limited Company | Voice response system |
| WO2002097795A1 (en) * | 2001-05-30 | 2002-12-05 | Bellsouth Intellectual Property Corporation | Multi-context conversational environment system and method |
-
2002
- 2002-12-27 CN CNB021592446A patent/CN100346625C/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1224203A (en) * | 1998-01-20 | 1999-07-28 | 白涛 | Intelligent instantaneous synchronous Chinese and English machine translation method for translating from each into other |
| CN1329739A (en) * | 1998-10-16 | 2002-01-02 | 艾利森电话股份有限公司 | Voice control of a user interface to service applications |
| CN1368719A (en) * | 2001-02-02 | 2002-09-11 | 国际商业机器公司 | Method and system for automatic generating speech XML file |
| WO2002073449A1 (en) * | 2001-03-14 | 2002-09-19 | At & T Corp. | Automated sentence planning in a task classification system |
| WO2002087201A1 (en) * | 2001-04-19 | 2002-10-31 | British Telecommunications Public Limited Company | Voice response system |
| WO2002097795A1 (en) * | 2001-05-30 | 2002-12-05 | Bellsouth Intellectual Property Corporation | Multi-context conversational environment system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1512747A (en) | 2004-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1581294B (en) | Speech recognition enhanced caller identification | |
| US9088652B2 (en) | System and method for speech-enabled call routing | |
| EP0484070B1 (en) | Editing compressed voice information | |
| AU2005246437B2 (en) | Remote access system and method and intelligent agent therefor | |
| US7418086B2 (en) | Multimodal information services | |
| US5652789A (en) | Network based knowledgeable assistant | |
| US6510414B1 (en) | Speech recognition assisted data entry system and method | |
| US20030177009A1 (en) | System and method for providing a message-based communications infrastructure for automated call center operation | |
| US20030115289A1 (en) | Navigation in a voice recognition system | |
| WO2008137327A1 (en) | Automated attendant grammar tuning | |
| GB2376335A (en) | Address recognition using an automatic speech recogniser | |
| CN1658687A (en) | Command based group SMS with mobile message receiver and server | |
| CN1722230A (en) | Allocation of speech recognition tasks and combination of results thereof | |
| CN107680588A (en) | Intelligent sound air navigation aid, device and storage medium | |
| CN1239797A (en) | Voice processing system | |
| US20020001370A1 (en) | Voice portal platform | |
| CN101079792A (en) | Taxi dispatching system based on instant communication and its method | |
| CN1260932A (en) | Conversational prompting method for voice-controlled infromation and inquiry services involving computer telephone | |
| CN100346625C (en) | Telephone voice interactive system and its realizing method | |
| US7451086B2 (en) | Method and apparatus for voice recognition | |
| KR100977001B1 (en) | Automated response system for providing guidance classified by customer | |
| WO2000018100A9 (en) | Interactive voice dialog application platform and methods for using the same | |
| CN109410926A (en) | Voice method for recognizing semantics and system | |
| CN1216363C (en) | Method for realizing state conversion | |
| CN109451185A (en) | Incoming call recognition methods, device and storage medium based on enterprise directory |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20071031 Termination date: 20201227 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |