CN101075433A - Artificial intelligent controlling method for discriminating robot speech - Google Patents
Artificial intelligent controlling method for discriminating robot speech Download PDFInfo
- Publication number
- CN101075433A CN101075433A CNA2007100395928A CN200710039592A CN101075433A CN 101075433 A CN101075433 A CN 101075433A CN A2007100395928 A CNA2007100395928 A CN A2007100395928A CN 200710039592 A CN200710039592 A CN 200710039592A CN 101075433 A CN101075433 A CN 101075433A
- Authority
- CN
- China
- Prior art keywords
- detects
- result
- yes
- phonetic entry
- described detection
- 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.)
- Pending
Links
Images
Landscapes
- Manipulator (AREA)
Abstract
A method for controlling voice identification of robot includes entering self-learning mode and setting step value to be step=o, detecting whether there is voice input or not and redetecting whether there is voice input or not if there is not or otherwise carrying out voice identification treatment, detecting whether voice is ineffective or not and returning back to step of detecting whether there is voice input or not if it is or otherwise carrying out special statement command identification, detecting whether statement is identified or not if it is not and setting reply of not enabling to identify by robot and record current statement if it is not or returning back to step of firs detecting after resetting.
Description
Technical field
The present invention relates to the control method of robotic artificial intelligence, relate in particular to a kind of control method of robot voice identification artificial intelligence.
Background technology
Existing speech recognition is based on the basis of individual character identification, because the phonetically similar word of Chinese character is a lot, just can't accomplish accurately so just pronounce to identify individual character.A lot of speech recognitions also all need to determine according to the front and back content, and accuracy rate neither be very desirable.It is a lot of that the robot voice that has has in addition been identified statement predefine, and a lot of statements can not used in the residing environment of this robot at all, and the statement of robot identification is more many, and the accuracy rate of its identification can be affected to some extent.With regard in all parts of the country, voice also differ widely, and in this case, the recognition capability of robot can be different because of the difference in zone.
Summary of the invention
Purpose of the present invention is exactly the control method that a kind of robot voice identification artificial intelligence is provided for the defective that overcomes above-mentioned prior art existence.
Purpose of the present invention can be achieved through the following technical solutions: a kind of control method of robot voice identification artificial intelligence, this control method comprises the following steps:
(1) sets the self-study pattern that enters;
(2) set step=0;
(3) detect whether phonetic entry is arranged, if testing result is no, then detect again whether phonetic entry is arranged;
(4) if the result who detects in the step (3) is yes, then carry out voice recognition processing;
Whether invalid, if testing result is for being then to return step (3) if (5) detecting voice;
(6) if the result who detects in the step (5) is no, then carry out special sentence instruction identification;
(7) if the result who detects in the step (6) is no, then whether inspect statement is identified;
(8) if the result who detects in the step (7) is no, the answer that robot carries out None-identified is set then, records current statement, set step=1, overtime zero clearing, and return step (3);
(9) if the result who detects in the step (7) is yes, robot then is set according to mood or external environment, makes corresponding voice answering, and return step (3);
(10) if the result who detects in the step (6) is for being then to enter speech recognition learning language intelligence control system; Perhaps enter speech recognition learning action intelligence control system; Perhaps enter speech recognition learning image recognition intelligence control system.
Described speech recognition learning language intelligence control system may further comprise the steps:
(1) detects whether learn question and answer, if testing result is no, then go to other processing modes;
(2) whether if the result who detects in the step (1) is yes, it is non-zero then to detect step;
(3) if the result who detects in the step (2) is no, then turn back to the step whether described detection has phonetic entry;
(4) whether if the result who detects in the step (3) is yes, then detecting is " you should say ";
(5) if the result who detects in the step (4) is no, then go to other processing modes;
(6) whether if the result who detects in the step (4) is yes, then detecting step is 1;
(7) if the result who detects in the step (6) is no, step=0 then is set, and turns back to the step whether described detection has phonetic entry;
(8) if the result who detects in the step (6) is yes, then detect whether also have statement in the special sentence back;
(9) if the result who detects in the step (8) is yes, then set up the question and answer relation, step=0 is set, and turns back to the step whether described detection has phonetic entry;
(10) if the result who detects in the step (8) is no, then wait statement input;
(11) whether detection is overtime, if testing result is yes, step=0 is set then, and turns back to the step whether described detection has phonetic entry;
(12) if the result who detects in the step (11) is no, then detect whether carry out input by sentence;
(13) if the result who detects in the step (12) is no, then return step (10);
(14) if the result who detects in the step (12) is yes, then set up the question and answer relation, step=0 is set, and turns back to the step whether described detection has phonetic entry.
Described speech recognition learning action intelligence control system may further comprise the steps:
(1) detects whether learn action, if testing result is no, then go to other processing modes;
(2) whether if the result who detects in the step (1) is yes, it is non-zero then to detect step;
(3) if the result who detects in the step (2) is no, then turn back to the step whether described detection has phonetic entry;
(4) whether if the result who detects in the step (3) is yes, then detecting is " you should do like this ";
(5) if the result who detects in the step (4) is no, then go to other processing modes;
(6) whether if the result who detects in the step (4) is yes, then detecting step is 1;
(7) if the result who detects in the step (6) is no, step=0 then is set, and turns back to the step whether described detection has phonetic entry;
(8) if the result who detects in the step (6) is yes, then detects and whether move in addition in the special sentence back;
(9) if the result who detects in the step (8) is yes, then set up the question and answer action relationships, step=0 is set, and turns back to the step whether described detection has phonetic entry;
(10) if the result who detects in the step (8) is no, then wait for the action input;
(11) whether detection is overtime, if testing result is yes, step=0 is set then, and turns back to the step whether described detection has phonetic entry;
(12) if the result who detects in the step (11) be no, then whether detection moves input;
(13) if the result who detects in the step (12) is no, then return step (10);
(14) if the result who detects in the step (12) is yes, then set up the question and answer action relationships, step=0 is set, and turns back to the step whether described detection has phonetic entry.
Described speech recognition learning image recognition intelligence control system may further comprise the steps:
(1) detects whether learn image recognition, if testing result is no, then go to other processing modes;
(2) whether if the result who detects in the step (1) is yes, it is non-zero then to detect step;
(3) if the result who detects in the step (2) is no, then turn back to the step whether described detection has phonetic entry;
(4) whether if the result who detects in the step (3) is yes, then detecting is " I am ";
(5) if the result who detects in the step (4) is no, then go to other processing modes;
(6) whether if the result who detects in the step (4) is yes, then detecting step is 1;
(7) if the result who detects in the step (6) is no, step=0 then is set, and turns back to the step whether described detection has phonetic entry;
(8) if the result who detects in the step (6) is yes, then detect whether also have statement in the special sentence back;
(9) if the result who detects in the step (8) is yes, then set up image recognition question and answer relation, step=0 is set, and turns back to the step whether described detection has phonetic entry;
(10) if the result who detects in the step (8) is no, then wait statement input;
(11) whether detection is overtime, if testing result is yes, step=0 is set then, and turns back to the step whether described detection has phonetic entry;
(12) if the result who detects in the step (11) is no, then detect whether carry out input by sentence;
(13) if the result who detects in the step (12) is no, then return step (10);
(14) if the result who detects in the step (12) is yes, then set up image recognition question and answer relation, step=0 is set, and turns back to the step whether described detection has phonetic entry.
Compared with prior art, the speech recognition statement of robot is according to the residing varying environment of robot, and the oneself is progressively perfect.The data volume less, the recognition accuracy height.Can do as the Romans do while in Rome, intelligent degree is very high.
Description of drawings
Fig. 1 is the process flow diagram of the control method of a kind of robot voice identification of the present invention artificial intelligence.
Fig. 2 is a speech recognition artificial intelligent control system's of the present invention primary structure synoptic diagram.
Embodiment
The invention will be further described below in conjunction with drawings and the specific embodiments.
As shown in Figure 1, step 1 is initial actuating in speech recognition learning language intelligence control system, sets the self-study pattern that enters; In step 2, set step=0; Whether in step 3, detecting has phonetic entry; If NO, then return step 3; If be yes in the step 3, then in step 4, carry out voice recognition processing; Whether in step 5, it is invalid to detect voice; If yes, then return step 3; If be no in the step 5, then in step 6, carry out special sentence instruction identification; If be no in the step 6, then in step 7, whether inspect statement is identified; If be no in the step 7, then in step 8, robot is set says: " I do not understand.", record current statement, set step=1, overtime zero clearing, and return step 3; If be yes in the step 7, then in step 9, robot is set according to mood or external environment, make corresponding voice answering, and return step 3; If be yes in the step 6, then in step 10, detect and whether learn question and answer; If be no in the step 10, then in step 11, go to other processing modes; If be yes in the step 10, then whether in step 12, detecting step is non-NULL; If be no in the step 12, then return step 3; If be yes in the step 12, then whether in step 13, detecting is " you should say "; If be no in the step 13, then in step 14, go to other processing modes; If be yes in the step 13, then in step 15, detect whether step is 1; If be no in the step 15, step=0 then be set in step 16, and return step 3; If be yes in the step 15, then in step 17, detect whether also have statement in the special sentence back; If be yes in the step 17, then in step 18, set up the question and answer relation, step=0 is set, and returns step 3; If be no in the step 17, then in step 19, wait statement is imported; In step 20, whether overtimely detect; If yes, step=0 is set then, and returns step 3; If be no in the step 20, then in step 21, detect and whether carry out input by sentence; If be no in the step 21, then return step 19; If be yes in the step 21, then in step 18, set up the question and answer relation, step=0 is set, and returns step 3.
With reference to shown in Figure 1, step 1 is initial actuating in speech recognition learning action intelligence control system, sets the self-study pattern that enters; In step 2, set step=0; Whether in step 3, detecting has phonetic entry; If NO, then return step 3; If be yes in the step 3, then in step 4, carry out voice recognition processing; Whether in step 5, it is invalid to detect voice; If yes, then return step 3; If be no in the step 5, then in step 6, carry out special sentence instruction identification; If be no in the step 6, then in step 7, whether inspect statement is identified; If be no in the step 7, then in step 8, robot is set says: " I do not understand.", record current statement, set step=1, overtime zero clearing, and return step 3; If be yes in the step 7, then in step 9, robot is set according to mood or external environment, make corresponding action and answer, and return step 3; If be yes in the step 6, then in step 10, detect and whether learn action; If be no in the step 10, then in step 11, go to other processing modes; If be yes in the step 10, then whether in step 12, detecting step is non-NULL; If be no in the step 12, then return step 3; If be yes in the step 12, then whether in step 13, detecting is " you should do like this "; If be no in the step 13, then in step 14, go to other processing modes; If be yes in the step 13, then in step 15, detect whether step is 1; If be no in the step 15, step=0 then be set in step 16, and return step 3; If be yes in the step 15, then in step 17, detect and whether move in addition in the special sentence back; If be yes in the step 17, then in step 18, set up action question and answer relation, step=0 is set, and returns step 3; If be no in the step 17, then in step 19, wait for the action input; In step 20, whether overtimely detect; If yes, step=0 is set then, and returns step 3; If be no in the step 20, then in step 21, detect and whether move input; If be no in the step 21, then return step 19; If be yes in the step 21, then in step 18, set up the question and answer relation, step=0 is set, and returns step 3.
With reference to shown in Figure 1, step 1 is initial actuating in speech recognition learning image recognition intelligence control system, sets the self-study pattern that enters; In step 2, set step=0; Whether in step 3, detecting has phonetic entry; If NO, then return step 3; If be yes in the step 3, then in step 4, carry out voice recognition processing; Whether in step 5, it is invalid to detect voice; If yes, then return step 3; If be no in the step 5, then in step 6, carry out special sentence instruction identification; If be no in the step 6, then in step 7, whether inspect statement is identified; If be no in the step 7, then in step 8, robot is set says: " I do not understand.", record current statement, set step=1, overtime zero clearing, and return step 3; If be yes in the step 7, then in step 9, robot is set according to mood or external environment, make corresponding voice answering, and return step 3; If be yes in the step 6, then in step 10, detect and whether learn image recognition; If be no in the step 10, then in step 11, go to other processing modes; If be yes in the step 10, then whether in step 12, detecting step is non-NULL; If be no in the step 12, then return step 3; If be yes in the step 12, then whether in step 13, detecting is " I am "; If be no in the step 13, then in step 14, go to other processing modes; If be yes in the step 13, then in step 15, detect whether step is 1; If be no in the step 15, step=0 then be set in step 16, and return step 3; If be yes in the step 15, then in step 17, detect whether also have statement in the special sentence back; If be yes in the step 17, then in step 18, set up image recognition question and answer relation, step=0 is set, and returns step 3; If be no in the step 17, then in step 19, wait statement is imported; In step 20, whether overtimely detect; If yes, step=0 is set then, and returns step 3; If be no in the step 20, then in step 21, detect and whether carry out input by sentence; If be no in the step 21, then return step 19; If be yes in the step 21, then in step 18, set up image recognition question and answer relation, step=0 is set, and returns step 3.
As shown in Figure 2, this Fig. 2 is a speech recognition artificial intelligent control system's of the present invention primary structure synoptic diagram, and its structure comprises acoustic receiver 22, wave filter 23, AD conversion 24, digital filtering 25, voice recognition processing 26, phonetic study processing 27, storer 28, phonetic synthesis 29, DA conversion 30, amplifier 31, electrical loudspeaker 32, central processing unit 33.At first enter the self study pattern, after acoustic receiver 22 receives acoustic signals, through behind the wave filter 23, to import voice analog signal by AD conversion 24 and convert digital signal to, pass to central processing unit 33, the digital filtering 25 of the software module of process central processing unit 33 inside is handled, the reference data that then enters voice recognition processing 26 identifications obtains from storer 28, voice recognition processing 26 is judged phonetic code, the code that will pronounce is again passed to phonetic study and is handled 27, processing 27 is determined according to the data in the storer 28 through phonetic study, if discernible non-special sentence code, then phonetic study is handled 27 and directly call known answer-back code from storer 28, pass to phonetic synthesis 29, phonetic synthesis 29 is called relevant speech data according to answer-back code and is exported to DA conversion 30 from storer 28, by DA conversion 30 digital signal is become simulating signal, passes to amplifier 31 again the voice signal of output is amplified rear drive electrical loudspeaker 32.Phonetic study processing 27 is determined according to the data in the storer 28, then directly calls the answer of " I do not understand " statement if can not discern statement from storer 28, then enters circulation next time; Receive acoustic signals by acoustic receiver 22 once more, through behind the wave filter 23, to import voice analog signal by AD conversion 24 and convert digital signal to, pass to central processing unit 33, the digital filtering 25 of the software module of process central processing unit 33 inside is handled, the reference data that then enters voice recognition processing 26 identifications obtains from storer 28, enter phonetic study again and handle 27, after " you should " determined in language phonetic study processing 27, show that the question statement of front is answered with the statement of back.Once more from receiving acoustic signals by acoustic receiver 22, through behind the wave filter 23, to import voice analog signal by AD conversion 24 and convert digital signal to, pass to central processing unit 33, the digital filtering 25 of the software module of process central processing unit 33 inside is handled, the reference data that then enters voice recognition processing 26 identifications obtains from storer 28, enter phonetic study again and handle 27, phonetic study is handled 27 the question of the front answer with the back is associated, and respectively question statement, answer statement, condition association is saved in respectively in the storer 28.And so forth, robot can carry out the speech recognition manual intelligent.In like manner, be replaced with action learning module or image recognition study module if the phonetic study of this system is processed 27, then this system can have the function of action learning or image recognition study.
Claims (4)
1. the control method of robot voice identification artificial intelligence, this control method comprises the following steps:
(1) sets the self-study pattern that enters;
(2) set step=0;
(3) detect whether phonetic entry is arranged, if testing result is no, then detect again whether phonetic entry is arranged;
(4) if the result who detects in the step (3) is yes, then carry out voice recognition processing;
Whether invalid, if testing result is for being then to return step (3) if (5) detecting voice;
(6) if the result who detects in the step (5) is no, then carry out special sentence instruction identification;
(7) if the result who detects in the step (6) is no, then whether inspect statement is identified;
(8) if the result who detects in the step (7) is no, the answer that robot carries out None-identified is set then, records current statement, set step=1, overtime zero clearing, and return step (3);
(9) if the result who detects in the step (7) is yes, robot then is set according to mood or external environment, makes corresponding voice answering, and return step (3);
(10) if the result who detects in the step (6) is for being then to enter speech recognition learning language intelligence control system; Perhaps enter speech recognition learning action intelligence control system; Perhaps enter speech recognition learning image recognition intelligence control system.
2. the control method of a kind of robot voice identification artificial intelligence according to claim 1 is characterized in that described speech recognition learning language intelligence control system may further comprise the steps:
(1) detects whether learn question and answer, if testing result is no, then go to other processing modes;
(2) whether if the result who detects in the step (1) is yes, it is non-zero then to detect step;
(3) if the result who detects in the step (2) is no, then turn back to the step whether described detection has phonetic entry;
(4) whether if the result who detects in the step (3) is yes, then detecting is " you should say ";
(5) if the result who detects in the step (4) is no, then go to other processing modes;
(6) whether if the result who detects in the step (4) is yes, then detecting step is 1;
(7) if the result who detects in the step (6) is no, step=0 then is set, and turns back to the step whether described detection has phonetic entry;
(8) if the result who detects in the step (6) is yes, then detect whether also have statement in the special sentence back;
(9) if the result who detects in the step (8) is yes, then set up the question and answer relation, step=0 is set, and turns back to the step whether described detection has phonetic entry;
(10) if the result who detects in the step (8) is no, then wait statement input;
(11) whether detection is overtime, if testing result is yes, step=0 is set then, and turns back to the step whether described detection has phonetic entry;
(12) if the result who detects in the step (11) is no, then detect whether carry out input by sentence;
(13) if the result who detects in the step (12) is no, then return step (10);
(14) if the result who detects in the step (12) is yes, then set up the question and answer relation, step=0 is set, and turns back to the step whether described detection has phonetic entry.
3. the control method of a kind of robot voice identification artificial intelligence according to claim 1 is characterized in that, described speech recognition learning action intelligence control system may further comprise the steps:
(1) detects whether learn action, if testing result is no, then go to other processing modes;
(2) whether if the result who detects in the step (1) is yes, it is non-zero then to detect step;
(3) if the result who detects in the step (2) is no, then turn back to the step whether described detection has phonetic entry;
(4) whether if the result who detects in the step (3) is yes, then detecting is " you should do like this ";
(5) if the result who detects in the step (4) is no, then go to other processing modes;
(6) whether if the result who detects in the step (4) is yes, then detecting step is 1;
(7) if the result who detects in the step (6) is no, step=0 then is set, and turns back to the step whether described detection has phonetic entry;
(8) if the result who detects in the step (6) is yes, then detects and whether move in addition in the special sentence back;
(9) if the result who detects in the step (8) is yes, then set up the question and answer action relationships, step=0 is set, and turns back to the step whether described detection has phonetic entry;
(10) if the result who detects in the step (8) is no, then wait for the action input;
(11) whether detection is overtime, if testing result is yes, step=0 is set then, and turns back to the step whether described detection has phonetic entry;
(12) if the result who detects in the step (11) be no, then whether detection moves input;
(13) if the result who detects in the step (12) is no, then return step (10);
(14) if the result who detects in the step (12) is yes, then set up the question and answer action relationships, step=0 is set, and turns back to the step whether described detection has phonetic entry.
4. the control method of a kind of robot voice identification artificial intelligence according to claim 1 is characterized in that described speech recognition learning image recognition intelligence control system may further comprise the steps:
(1) detects whether learn image recognition, if testing result is no, then go to other processing modes;
(2) whether if the result who detects in the step (1) is yes, it is non-zero then to detect step;
(3) if the result who detects in the step (2) is no, then turn back to the step whether described detection has phonetic entry;
(4) whether if the result who detects in the step (3) is yes, then detecting is " I am ";
(5) if the result who detects in the step (4) is no, then go to other processing modes;
(6) whether if the result who detects in the step (4) is yes, then detecting step is 1;
(7) if the result who detects in the step (6) is no, step=0 then is set, and turns back to the step whether described detection has phonetic entry;
(8) if the result who detects in the step (6) is yes, then detect whether also have statement in the special sentence back;
(9) if the result who detects in the step (8) is yes, then set up image recognition question and answer relation, step=0 is set, and turns back to the step whether described detection has phonetic entry;
(10) if the result who detects in the step (8) is no, then wait statement input;
(11) whether detection is overtime, if testing result is yes, step=0 is set then, and turns back to the step whether described detection has phonetic entry;
(12) if the result who detects in the step (11) is no, then detect whether carry out input by sentence;
(13) if the result who detects in the step (12) is no, then return step (10);
(14) if the result who detects in the step (12) is yes, then set up image recognition question and answer relation, step=0 is set, and turns back to the step whether described detection has phonetic entry.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2007100395928A CN101075433A (en) | 2007-04-18 | 2007-04-18 | Artificial intelligent controlling method for discriminating robot speech |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2007100395928A CN101075433A (en) | 2007-04-18 | 2007-04-18 | Artificial intelligent controlling method for discriminating robot speech |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101075433A true CN101075433A (en) | 2007-11-21 |
Family
ID=38976430
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2007100395928A Pending CN101075433A (en) | 2007-04-18 | 2007-04-18 | Artificial intelligent controlling method for discriminating robot speech |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101075433A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102152312A (en) * | 2010-11-16 | 2011-08-17 | 深圳中科智酷机器人科技有限公司 | Robot system and task execution method of robot system |
CN102842306A (en) * | 2012-08-31 | 2012-12-26 | 深圳Tcl新技术有限公司 | Voice control method and device as well as voice response method and device |
CN103793536A (en) * | 2014-03-03 | 2014-05-14 | 陈念生 | Intelligent platform obtaining method and device |
CN106537493A (en) * | 2015-09-29 | 2017-03-22 | 深圳市全圣时代科技有限公司 | Speech recognition system and method, client device and cloud server |
CN109227536A (en) * | 2018-08-20 | 2019-01-18 | 南京邮电大学 | Intelligent greeting explains machine person speech interaction control system and control method |
CN110785776A (en) * | 2017-06-22 | 2020-02-11 | 卡西欧计算机株式会社 | Information processing apparatus, artificial intelligence recognition method, and program |
CN112975964A (en) * | 2021-02-23 | 2021-06-18 | 青岛海科虚拟现实研究院 | Robot automatic control method and system based on big data and robot |
CN117789713A (en) * | 2023-09-18 | 2024-03-29 | 江苏省疾病预防控制中心(江苏省公共卫生研究院) | Health literacy investigation quality control method and system based on voice recognition |
-
2007
- 2007-04-18 CN CNA2007100395928A patent/CN101075433A/en active Pending
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102152312A (en) * | 2010-11-16 | 2011-08-17 | 深圳中科智酷机器人科技有限公司 | Robot system and task execution method of robot system |
CN102842306A (en) * | 2012-08-31 | 2012-12-26 | 深圳Tcl新技术有限公司 | Voice control method and device as well as voice response method and device |
CN102842306B (en) * | 2012-08-31 | 2016-05-04 | 深圳Tcl新技术有限公司 | Sound control method and device, voice response method and device |
CN103793536A (en) * | 2014-03-03 | 2014-05-14 | 陈念生 | Intelligent platform obtaining method and device |
CN103793536B (en) * | 2014-03-03 | 2017-04-26 | 陈念生 | Intelligent platform obtaining method and device |
CN106537493A (en) * | 2015-09-29 | 2017-03-22 | 深圳市全圣时代科技有限公司 | Speech recognition system and method, client device and cloud server |
CN110785776A (en) * | 2017-06-22 | 2020-02-11 | 卡西欧计算机株式会社 | Information processing apparatus, artificial intelligence recognition method, and program |
CN110785776B (en) * | 2017-06-22 | 2023-11-28 | 卡西欧计算机株式会社 | Information processing apparatus, artificial intelligence recognition method, and program |
CN109227536A (en) * | 2018-08-20 | 2019-01-18 | 南京邮电大学 | Intelligent greeting explains machine person speech interaction control system and control method |
CN112975964A (en) * | 2021-02-23 | 2021-06-18 | 青岛海科虚拟现实研究院 | Robot automatic control method and system based on big data and robot |
CN112975964B (en) * | 2021-02-23 | 2022-04-01 | 青岛海科虚拟现实研究院 | Robot automatic control method and system based on big data and robot |
CN117789713A (en) * | 2023-09-18 | 2024-03-29 | 江苏省疾病预防控制中心(江苏省公共卫生研究院) | Health literacy investigation quality control method and system based on voice recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101075433A (en) | Artificial intelligent controlling method for discriminating robot speech | |
CN1188831C (en) | System and method for voice recognition with a plurality of voice recognition engines | |
CN1303582C (en) | Automatic speech sound classifying method | |
CN100338558C (en) | Systems and methods for inputting graphical data into a graphical input field | |
CN1238836C (en) | Combining DTW and HMM in speaker dependent and independent modes for speech recognition | |
RU2009102507A (en) | METHOD AND DEVICE FOR NATURALLY SPEECH RECOGNITION OF SPEECH SPEECH | |
CN1737902A (en) | Text-to-speech interchanging device | |
CN1750121A (en) | A kind of pronunciation evaluating method based on speech recognition and speech analysis | |
CN1950882A (en) | Detection of end of utterance in speech recognition system | |
CN108595406B (en) | User state reminding method and device, electronic equipment and storage medium | |
CN112581938B (en) | Speech breakpoint detection method, device and equipment based on artificial intelligence | |
CN111326178A (en) | Multi-mode speech emotion recognition system and method based on convolutional neural network | |
CN1831937A (en) | Method and device for voice identification and language comprehension analysing | |
CN1797542A (en) | Baseband modem for speech recognition and mobile communication terminal using the same | |
CN1787073A (en) | Speech recognition system for automatically controlling input level and speech recognition method using the same | |
Gupta et al. | Speech feature extraction and recognition using genetic algorithm | |
CN1458645A (en) | Voice identification equipment and voice identification program | |
CN1224954C (en) | Speech recognition device comprising language model having unchangeable and changeable syntactic block | |
CN1317134A (en) | Method and system for voice dialling | |
CN112863485A (en) | Accent voice recognition method, apparatus, device and storage medium | |
CN1560834A (en) | Method of grammar describing and identification analyse of colloquial identification understanding | |
CN1581293A (en) | Man-machine interacting method and device based on limited-set voice identification | |
CN1628337A (en) | Speech recognizing method and device thereof | |
CN1473323A (en) | System and method for improving voice recognition in noisy environments and frequency mismatch conditions | |
CN1666253A (en) | System and method for mandarin chinese speech recogniton using an optimized phone set |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20071121 |