JP2018194849A - Information processing device - Google Patents

Abstract

To provide an information processing device by which an appropriate recognition result can be obtained.SOLUTION: A CPU 13 in a car navigation system 10 obtains a recognition result of a voice recognition engine 12 that performs voice recognition of voice made by a user and parameters made up of sound pressure information, a score, and algorithm determination. The CPU 13 further obtains a recognition result of a voice recognition engine 22 in a smart phone 20 that has performed voice recognition of the same voice, and parameters made up of sound pressure information, a score, and algorithm determination via a short distance wireless communication unit 15. The CPU 13 selects either one of the recognition result of the voice recognition engine 12 and the recognition result of the voice recognition engine 22 on the basis of the parameters of the voice recognition engine 12 and the parameters of the voice recognition engine 22, and causes the one to be executed as a command.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an information processing apparatus that performs information processing based on a voice recognition processing result.

  2. Description of the Related Art Conventionally, in various electronic devices, there are devices that recognize a voice spoken by a user and perform an operation according to the recognition result. Since the algorithms, dictionaries, and the like of the voice recognition processing unit are different for each device, the recognition rate is different for each device even for the same voice.

  In recent years, cloud-type speech recognition systems have been proposed. In this method, a server is provided with a voice recognition engine and a dictionary, and a plurality of terminals each connect to the server via a network to request a voice recognition process and obtain a processing result. Such a cloud-type speech recognition system has an advantage that it has a dictionary in the server, so that the vocabulary can be greatly increased and it can be processed by an advanced algorithm.

  Patent Document 1 discloses sharing the result of speech recognition with other electronic devices. Specifically, when inputting to the external device 20 by voice, a recognition module is transmitted from the portable information processor 10 to the external device 20, and the external device 20 performs processing using the received recognition module.

JP 2003-140690 A

  The cloud type speech recognition system is basically recognized on the premise of conversation. However, for example, a car navigation system can use a unique phrase such as detour search or reroute as a command for voice operation, but a cloud-type speech recognition system can use a phrase used in such a unique environment. It is difficult to recognize properly.

  In the method described in Patent Document 1, although recognition results can be shared by a plurality of electronic devices, for example, when a recognition module of a car navigation system is moved to another device, the recognition module is unique to the car navigation system. In order to perform recognition suitable for the environment, for example, when a normal conversation is recognized, an appropriate recognition result may not be obtained.

  In view of the above-described problems, an object of the present invention is to provide an information processing apparatus capable of obtaining an appropriate recognition result, for example.

  In order to solve the above problems, a first acquisition unit that acquires first speech recognition result information and first speech recognition processing information from a first speech recognition unit that recognizes speech, and a second speech recognition unit that recognizes the speech A second acquisition unit for acquiring second voice recognition result information and second voice recognition processing information from the first voice recognition result information or the second voice recognition processing information based on the first voice recognition processing information and the second voice recognition processing information. A control unit that selects any one of the two speech recognition result information and causes the processing unit to execute a process related to the selected first speech recognition result information or the second speech recognition result information. .

  The invention according to claim 12 is a control method of an information processing apparatus that causes a processing unit to execute processing based on recognized speech, wherein the first speech recognition result information from the first speech recognition unit that recognizes the speech, and A first acquisition step of acquiring first speech recognition processing information; a second acquisition step of acquiring second speech recognition result information and second speech recognition processing information from a second speech recognition unit that recognizes the speech; One of the first voice recognition result information and the second voice recognition result information is selected based on one voice recognition processing information and the second voice recognition processing information, and the selected first voice recognition result information or the first voice recognition result information is selected. And a control step for causing the processing unit to execute processing related to the two speech recognition result information.

  The invention described in claim 13 is characterized in that the information processing method according to claim 12 is executed by a computer.

  The invention described in claim 14 is characterized in that the information processing program described in claim 13 is stored.

1 is an external perspective view of a car navigation system according to an embodiment of the present invention. It is a block block diagram of the car navigation system and smart phone which were shown by FIG. It is a flowchart of the speech recognition operation | movement of the car navigation system shown by FIG. 4 is a table for explaining a specific example of the flowchart shown in FIG. 3. 4 is a table for explaining a specific example of the flowchart shown in FIG. 3.

  Hereinafter, an information processing apparatus according to an embodiment of the present invention will be described. In the information processing apparatus according to an embodiment of the present invention, the first acquisition unit includes first speech recognition result information that is a speech recognition result of a first speech recognition unit that recognizes speech uttered by a user, and first information. First speech recognition processing information that is information obtained together with the first speech recognition result information from the speech recognition unit, and the second acquisition unit recognizes the speech recognized by the first speech recognition unit. Second speech recognition result information that is a speech recognition result of the recognition unit and second speech recognition processing information that is information obtained together with the second speech recognition result information from the second speech recognition unit are acquired. Then, based on the first voice recognition processing information acquired by the first acquisition unit and the second voice recognition processing information acquired by the second acquisition unit, the control unit performs the first voice recognition result information or the second voice recognition result information. Is selected, and the processing unit is caused to execute information processing based on the selected first voice recognition result information or second voice recognition result information. By doing in this way, since it can select from the result of the two speech recognition parts which recognized the same speech, speech recognition can be performed with the accuracy more than performing speech recognition independently. For example, if two speech recognition units have different algorithms and dictionaries, recognition results suitable for various environments can be obtained. Therefore, an appropriate recognition result can be obtained.

  In addition, when the first voice recognition processing information is equal to or greater than a predetermined first threshold, the control unit selects the first voice recognition result information and processes information processing based on the first voice recognition result information. May be executed by the part. By doing in this way, various information processings, such as a route search of a navigation system, a search of a store using the Internet, etc., can be performed using the recognition result of the 1st voice recognition part.

  Further, the control unit selects the second speech recognition result information when the first speech recognition processing information is less than the first threshold and the second speech recognition processing information is greater than or equal to a predetermined second threshold, Information processing based on the second speech recognition result information may be executed by the processing unit. By doing so, when the reliability of the recognition result of the first voice recognition unit is low and the possibility that it is not appropriate is high, the result of the second voice recognition unit is used, for example, the route search of the navigation system or the Internet is used. It is possible to perform various information processing such as searching for a shop or the like.

  The second acquisition unit further acquires processing result information that is a result processed based on the second speech recognition result information. Then, when the first voice recognition processing information is less than the predetermined first threshold and the second voice recognition processing information is equal to or greater than the predetermined second threshold, the second voice recognition result information is predetermined. It is determined whether or not it is included in the command group. If it is included, the processing unit executes information processing based on the second speech recognition result information, and if it is not included, the second acquisition unit acquires it. Information processing based on the processed result information may be executed by the processing unit. By doing in this way, when the possibility that the recognition result of the first speech recognition unit is not appropriate is high, the result of the second speech recognition unit can be used. Further, when the result of the second voice recognition unit is included in a predetermined command group such as a command for operating the device, for example, the operation according to the command can be performed. If the result is not included in the predetermined command group, information processing can be performed using the result processed by the device having the second speech recognition unit.

  In addition, when the first voice recognition process information is less than the first threshold value and the second voice recognition process information is less than the second threshold value, the control unit determines each of the first voice recognition process information and the second voice recognition process information. A predetermined calculation with weighting may be performed, and the first voice recognition result information or the second voice recognition result information may be selected based on the calculation result. By doing in this way, when the recognition result cannot be selected with the first threshold value and the second threshold value, the first voice recognition result is obtained by performing a calculation based on weighting based on the use environment for each result. Either the information or the second speech recognition result information can be selected.

  In addition, when the first voice recognition process information is less than the first threshold value and the second voice recognition process information is less than the second threshold value, the control unit determines whether the first voice recognition result information or the first voice recognition result information is based on the past use history. 2 Voice recognition result information may be selected. In this way, when the recognition result cannot be selected with the first threshold value and the second threshold value, the first voice recognition result information is based on the past use history such as whether it has been used for past voice recognition, search, or operation. Alternatively, either one of the second speech recognition result information can be selected.

  In addition, when the first voice recognition processing information is less than the first threshold and the second voice recognition processing information is less than the second threshold, the control unit determines whether the first voice recognition result information or the first voice recognition result information is based on the past usage situation. 2 Voice recognition result information may be selected. By doing in this way, when a recognition result cannot be selected with the first threshold value and the second threshold value, the first voice recognition result information or the second voice recognition result information is based on the past use situation such as time zone, season, and weather. Either of these can be selected.

  The first voice recognition process information and the second voice recognition process information include a degree of association that is information on the degree of association between the voice spoken by the user and the first voice recognition result information or the second voice recognition result information. Information may be included. By doing so, the first speech recognition result information or the second speech recognition result information is based on the degree of association with the recognition result based on the uttered speech, that is, the score indicating the similarity between the uttered speech and the dictionary. Either one can be selected.

  Moreover, the 1st audio | voice recognition part, the 1st acquisition part, the 2nd acquisition part, and the control part may be provided integrally. By doing so, it is possible to obtain an appropriate recognition result in the information processing apparatus by cooperating with an external device or the like having the second voice recognition unit.

  Further, the control unit may cause the first speech recognition unit and the second speech recognition unit to learn the recognition result based on the first speech recognition result information or the second speech recognition result information selected by the control unit. By doing in this way, each voice recognition part can share a recognition result, and the precision of subsequent voice recognition can be improved.

  Moreover, the input part into which the audio | voice which the user uttered is each input may be provided corresponding to each of a 1st audio | voice recognition part and a 2nd audio | voice recognition part. In this way, for example, microphones can be provided as input units corresponding to the voice recognition units, respectively, and the sound pressure of the voice input from the microphones as the first voice recognition processing information and the second voice recognition processing information And can get volume.

  Also, in the control method of the information processing apparatus according to the embodiment of the present invention, the first voice recognition result that is the voice recognition result of the first voice recognition unit that recognizes the voice uttered by the user in the first acquisition step. Information and first voice recognition processing information which is information obtained together with the first voice recognition result information from the first voice recognition unit, and the voice recognized by the first voice recognition unit in the second acquisition step is voiced. The second voice recognition result information that is the voice recognition result of the second voice recognition unit to be recognized and the second voice recognition processing information that is information obtained together with the second voice recognition result information from the second voice recognition unit are acquired. . Then, in the control process, based on the first voice recognition process information acquired in the first acquisition process and the second voice recognition process information acquired in the second acquisition process, the first voice recognition result information or the second voice recognition result information Is selected, and the processing unit is caused to execute information processing based on the selected first voice recognition result information or second voice recognition result information. By doing in this way, since it can select from the result of the two speech recognition parts which recognized the same speech, speech recognition can be performed with the accuracy more than performing speech recognition independently. For example, if two speech recognition units have different algorithms and dictionaries, recognition results suitable for various environments can be obtained. Therefore, an appropriate recognition result can be obtained.

  Moreover, it is good also as a control program of the information processing apparatus which performs the control method of the information processing apparatus mentioned above with a computer. By doing in this way, an appropriate recognition result can be obtained using a computer.

  The control program for the information processing apparatus described above may be stored in a computer-readable recording medium. In this way, the program can be distributed as a single unit in addition to being incorporated in the device, and version upgrades can be easily performed.

  A car navigation system 10 as an information processing apparatus according to an embodiment of the present invention will be described with reference to FIGS. The car navigation system 10 is mounted on an instrument panel 100 of a vehicle as shown in FIG. The car navigation system 10 can communicate with a smartphone 20 (described later) placed on the passenger seat 101 by wireless or wired connection.

  As shown in FIG. 2, the car navigation system 10 shown in FIG. 1 includes a microphone 11, a speech recognition engine 12, a CPU 13, a storage device 14, a short-range wireless communication unit 15, a GPS 16, and a display unit. 17.

  The microphone 11 serving as an input unit receives voice uttered by the user, converts the voice into an audio signal that is an electrical signal, and outputs the voice signal to the voice recognition engine 12. Note that the microphone 11 may not be provided integrally with the car navigation system 10, and may be provided near the user, for example, a steering column in the case of a vehicle and connected by a cable or wirelessly.

  The voice recognition engine 12 as the first voice recognition unit performs voice recognition based on the voice signal input from the microphone 11, and the recognition result information includes a phrase based on a word or a combination of words, a voice signal, and itself. An algorithm determination indicating the degree of determination by an algorithm such as a score indicating the degree of approximation with a vocabulary in the dictionary possessed, a matching degree with a dictionary possessed by itself or a candidate estimated from previous and subsequent contexts, and input from the microphone 11 Parameters such as sound pressure information of the sound signal are output to the CPU 13. Note that there may be a plurality of result information as candidates, in which case the score, algorithm determination, and sound pressure information are output for each candidate. Also, volume information may be used instead of the sound pressure information. Further, the parameter may be one or more of the three parameters described above, but preferably includes a score. That is, the phrase corresponds to the first voice recognition result information, and the parameter corresponds to the first voice recognition processing information. Further, since the score is a degree of approximation between the voice signal and the dictionary, the score is relevance information that is information relating to the degree of association between the voice signal and the phrase searched from the dictionary.

  Note that the recognition algorithm and the score calculation method used for the speech recognition engine 12 may be well-known and are not particularly limited. However, since the speech recognition engine 12 is provided in the car navigation system 10, What is adjusted so that the recognition probability of phrases such as “reroute” and “detour search” used for voice input commands (operation commands) is increased is preferable. The voice recognition engine 12 may not be included in the car navigation system 10, and may use, for example, a cloud type voice recognition system described in the related art. In other words, the voice signal input from the microphone 11 may be transmitted to a server or the like, the voice recognition process may be performed by the server, and the car navigation system 10 may receive the phrases and parameters.

  The CPU 13 as a control unit, a first acquisition unit, and a processing unit is configured as a microcomputer including a RAM, a ROM, and the like, and governs overall control of the car navigation system 10. And CPU13 performs various processes, such as destination setting, route search, guidance, and map display, which car navigation system 10 generally has. Further, the CPU 13 acquires the phrases and parameters output from the voice recognition engine 12. Based on the parameters output by the speech recognition engine 12 and the parameters output by the speech recognition engine 22 acquired by the short-range wireless communication unit 15 from the smartphone 20 described later, the phrases output by the speech recognition engine 12 and the smartphone 20 One of the phrases output by the speech recognition engine 22 acquired by the distance wireless communication unit 15 is selected, and processing based on the selected phrase is executed.

  The storage device 14 is configured by a nonvolatile read / write storage medium such as a hard disk or a semiconductor memory. The storage device 14 stores information such as a map used for guidance in the car navigation system 10, for example.

  The short-range wireless communication unit 15 as a second acquisition unit is connected to a smartphone 20 described later by short-range wireless communication such as Bluetooth (registered trademark) or infrared communication, and performs data communication with each other. In addition, the short-range wireless communication unit 15 acquires phrases and parameters output from the smartphone 20 described later by a voice recognition engine 22. Note that the short-range wireless communication unit 15 is not limited to short-range wireless communication, and may be other wireless communication such as a wireless LAN (Local Area Network) or wired communication such as USB (Universal Serial Bus).

  As is well known, the GPS 16 receives radio waves transmitted from a plurality of GPS (Global Positioning System) satellites, obtains current position information (current position information), and outputs it to the CPU 13. In this embodiment, an example in which the GPS 16 is provided integrally with the car navigation system 10 is shown, but the GPS 16 may be configured as a separate body and detachable from the car navigation system 10.

  The display unit 17 is configured by a display device such as a liquid crystal display or an EL (Electro Luminescence) display. The display unit 17 may have a touch panel superimposed on the display surface. The display unit 17 displays a map, guidance information such as the position of the vehicle, destination and route, various operation menus, buttons for touch panel operation, and the like.

  In the car navigation system 10 having the above-described configuration, data communication is performed between the smartphone 20 and the short-range wireless communication unit 15 illustrated in FIG. In addition, as described above, the car navigation system 10 performs navigation functions such as route search by itself with map information. However, the car navigation system 10 causes the server to execute the navigation function with map information in an external server or the like. May be configured to receive and display the result.

  The smartphone 20 includes a microphone 21, a voice recognition engine 22, a CPU 23, a storage device 24, a short-range wireless communication unit 25, and a line communication unit 26.

  The microphone 21 serving as an input unit receives voice spoken by the user, converts the voice into an audio signal that is an electric signal, and outputs the voice signal to the voice recognition engine 22.

  The voice recognition engine 22 as the second voice recognition unit performs voice recognition based on the voice signal input from the microphone 21, and the recognition result information includes a phrase based on a word or a combination of words, a voice signal, and itself. The CPU 23 outputs to the CPU 23 a score indicating a degree of approximation with a vocabulary in the dictionary, an algorithm determination indicating a matching degree with the dictionary held by the dictionary, and sound pressure information of an audio signal input from the microphone 21. Note that there may be a plurality of result information as candidates, in which case the score, algorithm determination, and sound pressure information are output for each candidate. That is, the phrase corresponds to the second voice recognition result information, and the parameter corresponds to the second voice recognition processing information.

  The recognition algorithm used for the speech recognition engine 22 and the score calculation method may be well-known ones and are not particularly limited. However, the speech recognition engine 22 preferably has a recognition algorithm or dictionary different from the speech recognition engine 12. . In this case, the possibility of recognizing a phrase that cannot be recognized correctly by the speech recognition engine 12 increases, and the speech recognition engine 12 can be supplemented.

  The voice recognition engine 22 may not be included in the smartphone 20, and may use, for example, a cloud type voice recognition system described in the related art. That is, the speech signal input from the microphone 21 may be transmitted to a server or the like, the speech recognition process may be performed by the server, and the smartphone 20 may receive the phrases and parameters.

  The CPU 23 is configured as a microcomputer including a RAM, a ROM, and the like, and governs overall control of the smartphone 20. And CPU23 performs the function which the smart phone 20 generally has, for example, functions, such as a telephone call, mail, and an internet connection, or execution of an application. Further, the CPU 23 acquires a phrase and parameters from the voice recognition engine 22 and transmits them to the car navigation system 10 via the short-range wireless communication unit 25. Further, processing such as Internet search is performed based on the recognition result of the voice recognition engine 22.

  The storage device 24 is composed of a nonvolatile read / write storage medium such as a semiconductor memory. A removable storage medium such as a memory card may be used. The storage device 24 stores, for example, phone books and application data used in the smartphone 20.

  The short-range wireless communication unit 25 is connected to a car navigation system 10 described later by short-range wireless communication such as Bluetooth (registered trademark) or infrared communication, and performs data communication with each other. In addition, the short-range wireless communication unit 25 transmits the phrase and parameters output by the voice recognition engine 22 to the car navigation system 10.

  The line communication unit 26 connects to the mobile phone network and performs various communications. The line communication unit 26 is connected to a base station or the like by a communication method such as W-CDMA (Wideband Code Division Multiple Access) or LTE (Long Term Evolution), and is connected to the mobile phone line network.

  The car navigation system 10 having the above-described configuration selects a more appropriate recognition result (phrase) using both the voice recognition engine 12 that the car navigation system 10 has and the voice recognition engine 22 that the smartphone 20 has. Then, various processes based on the selected phrase are executed. The detailed operation will be described with reference to the flowchart shown in FIG. The CPU 13 executes the flowchart shown in FIG. In addition, the car navigation system 10 and the smartphone 20 can perform data communication with each other by short-range wireless communication in advance before executing this flowchart.

  First, in step S1 as the first acquisition step, the speech uttered by the user is recognized by the speech recognition engine 12 (car navigation system 10) via the microphone 11, and the phrase and parameter (score, algorithm determination, sound pressure) are recognized. Information) is acquired, and the process proceeds to step S3.

  On the other hand, in step S2 as the second acquisition step, the phrases and parameters that the voice recognition engine 22 (smart phone 20) recognizes the same voice as in step S1 are acquired via the short-range wireless communication unit 15 and the process proceeds to step S3. move on.

  Next, in step S3, the parameters of the speech recognition engine 12 acquired in step S1 are compared with the parameters of the speech recognition engine 22 acquired in step S2, and the process proceeds to step S4.

  Next, in step S4, it is determined whether or not the score and the sound pressure information are equal to or greater than a predetermined threshold among the parameters output by the speech recognition engine 12, and if they are equal to or greater than the threshold (YES), the process proceeds to step S5. If it is less than the threshold (in the case of NO), the process proceeds to step S6. For example, the threshold value is 85 or more when the maximum value of sound pressure information (sound pressure) is 100, and the score is 92 or more. In the present embodiment, not only the score but also a threshold value is set for the sound pressure information because there is a high possibility that accurate speech recognition is possible when the sound pressure is higher. That is, when these conditions are satisfied, it is determined that the threshold value is exceeded. That is, the threshold used for the determination in this step corresponds to the first threshold.

  Next, in step S5, since it is determined in step S4 that the threshold is greater than or equal to the threshold value, the phrase that is the recognition result of the speech recognition engine 12 is determined (selected) as a determination word, that is, an operation command to be executed in a later step. Proceed to S19.

  In step S6, it is determined whether or not the score and the sound pressure information are equal to or greater than a predetermined threshold among the parameters acquired from the smartphone 20. If (NO), the process proceeds to step S11. For example, the threshold value is set to 82 or more when the maximum value of sound pressure information (sound pressure) is 100, and the score is set to 96 or more. That is, when these conditions are satisfied, it is determined that the threshold value is exceeded. The threshold value determined in this step and the threshold value determined in step S4 may be the same value. These threshold values may be set as appropriate based on the installation position, the algorithm of each voice recognition engine, and the like. That is, the threshold value used for the determination in this step corresponds to the second threshold value.

  Next, in step S7, since it was judged that it was more than a threshold value by step S6, the phrase which is the recognition result acquired from the smart phone 20 is determined (selected) as a judgment word, and it progresses to step S8.

  Next, in step S8, it is determined whether or not the determination word determined in step S7 is in the navigation command. If there is (in the case of YES), the phrase is determined (selected) as a determination word and the process proceeds to step S19. If not (NO), the process proceeds to step S9. The navigation command indicates a predetermined command group used for the operation of the car navigation system 10. That is, in this step, it is determined whether or not the determined determination word is a navigation command.

  Next, in step S9, since it was determined in step S8 that the determination word is not included in the navigation command, the smartphone 20 is caused to perform a cooperative operation, and the process proceeds to step S10. For example, when an Internet search or navigation application is installed using a phrase (determination word) output from the speech recognition engine 22 on the smartphone 20, point information related to the search result (store name or location) Or latitude / longitude information). For this cooperative operation, a command for instructing execution from the car navigation system 10 (CPU 13) to the smartphone 20 may be transmitted, or the smart phone 20 may perform the cooperative operation in advance following the voice recognition operation.

  Next, in step S10, the cooperative operation result performed by the smartphone 20 in step S9 is acquired via the short-range wireless communication unit 15, and the process proceeds to step S19. That is, the cooperation operation result corresponds to the processing result information.

In step S11, since both steps S4 and S6 were less than the threshold value, that is, less than the first threshold value and less than the second threshold value, evaluation was performed using the following formulas (1) and (2). Then, the process proceeds to step S12.
(Sound pressure × a) × ((score + determination) × b) (1)
(Sound pressure × c) × ((score + determination) × d) (2)

  The expression (1) is an expression that is calculated by substituting the parameters acquired from the smartphone 20, and the expression (2) is an expression that is calculated by substituting the parameters output by the speech recognition engine 12. The determination is a numerical value for algorithm determination, and a, b, c, and d are coefficients for weighting the terms to be multiplied. That is, a predetermined calculation is performed by weighting each of the first voice recognition process information and the second voice recognition process information.

  Next, in step S12, it is determined whether or not the result of the evaluation performed in step S11 has been confirmed to one. If it can be confirmed (in the case of YES), the process proceeds to step S13 and cannot be confirmed. If yes (NO), go to step S14. In this step, for example, when the difference between the calculation results of the above formulas (1) and (2) is 8 or more, a phrase having a large calculation result is selected and fixed to one.

  Next, in step S13, the phrase determined in step S12 or later-described steps S15 and S17 is selected as a determination word, and the process proceeds to step S19.

  In step S14, evaluation is performed based on the past use history of the phrase acquired as the recognition result, and the process proceeds to step S15. The past use history is not limited to the speech recognition history, but is the operation of the car navigation system 10 such as Internet search or destination search, history information used by the smartphone 20, and the like. The usage history information of the smartphone 20 may be acquired by specifying a phrase via the short-range wireless communication unit 15 at the time of executing this step, for example.

  Next, in step S15, as a result of the evaluation performed in step S14, it is determined whether or not one can be confirmed. If it can be confirmed (YES), the process proceeds to step S13 and cannot be confirmed. In the case (NO), the process proceeds to step S16. In this step, for example, as a result of step S14, a frequently used phrase is selected and fixed to one.

  Next, in step S16, it evaluates based on the past use condition of the phrase acquired as a recognition result, and progresses to step S15. The past use situation is a scene in which the phrase has been used in the past, for example, an external environment such as a time zone such as AM / PM, season, weather, or the like.

  Next, in step S17, it is determined whether or not the result of the evaluation performed in step S16 has been confirmed to one, and if it can be confirmed (in the case of YES), the process proceeds to step S13 and cannot be confirmed. In the case (NO), the process proceeds to step S18. In this step, for example, as a result of step S16, phrases used in the same scene are selected and confirmed as one.

  Next, in step S18, the phrase having the highest score is determined as a determination word since it cannot be determined as one in steps S12 to S17, and the process proceeds to step S19.

  Next, in step S19, the speech recognition engines 12 and 22 learn the determination words determined in steps S5, S7, S13, and S18, and the process proceeds to step S20. Since this learning is performed not only by the voice recognition engine 12 but also by the voice recognition engine 22, the determination word information is also transmitted to the smartphone 20 via the short-range wireless communication unit 15.

  Next, in step S20, a command is executed based on the determination word. That is, the determination word is interpreted as an operation command of the car navigation system 10 and the process is executed. In addition, when the short-range wireless communication unit 15 acquires the cooperation result from the smartphone 20 by executing Step S10, a point search may be performed based on the result, or the content may be displayed as it is. . Further, when the determination word cannot be interpreted as an operation command, an error message may be displayed on the display unit 17 or the flowchart may be restarted from the beginning by prompting for another input.

  As is clear from the above description, steps S4 to S20 are performed based on the parameter acquired in step S1 and the parameter acquired in step S2, or the phrase output by the speech recognition engine 12 or the phrase output by the speech recognition engine 22. It functions as a control step of selecting either one and causing the processing unit to execute information processing based on the selected phrase.

  The operations shown in steps S11, S14, and S16 are not limited to this order. Alternatively, not all three operations may be performed, but only one or two may be performed.

  Here, a specific example will be described along the flowchart shown in FIG. For example, when the user pronounces “I like soba (buckwheat noodle)”, the speech recognition engine 12 of the car navigation system 10 determines that the sound pressure information is 87 and “Soma City”, and “Mobara City” as another candidate. The speech recognition engine 22 of the smartphone 20 determines that the sound pressure information is 78 and “is on the sofa”, and other candidates are “Soba-like” and “Soma City”. And the score and algorithm determination including each other candidate are as shown in FIG. As shown in FIG. 4, the flowchart shown in FIG. 2 is not limited to comparing one phrase for each of the car navigation system 10 and the smartphone 20, but may be compared using a plurality of candidates.

  At this time, in step S4, “Soma City” determined by the speech recognition engine 12 and “Mobara City” as another candidate cannot satisfy the threshold values of the sound pressure information 85 or more and the score 92 or more. Therefore, although step S6 is executed, “to the sofa” determined by the speech recognition engine 22 and “Soba-like” and “Soma-shi” as other candidates also satisfy the threshold values of the sound pressure information 82 or more and the score 96 or more. I can't.

  Therefore, the equations (1) and (2) are calculated and evaluated in step S11, and the determination is made in step S12. At this time, algorithm determination is performed by appropriately converting ◎ and ○ into points. As a result of the calculation, for example, “Sofa” is 78, “Soba-like” is 76, “Soma City” is 73, and “Mobara City” is 41. Then, “to the sofa”, “soba noodles”, and “Soma City” are extracted as candidates with the highest score and up to 8 candidates from that candidate, but cannot be determined as one. “Soma City” is listed as a candidate for both the car navigation system 10 and the smartphone 20, but the subsequent judgment is based on the result of the above calculation formula, for example, the result of the car navigation system 10. Judgment shall be made based on this. Or it is good also considering the voice recognition engine 12 with which CPU13 which performs this flowchart is provided as priority.

  In step S14, the car navigation system 10 and the smartphone 20 are evaluated based on past usage histories, and the determination is made in step S15. The usage history (number of times of use) of “on the sofa”, “soba noodles”, and “Soma City” is as shown in FIG. Here, what has a history in both the car navigation system 10 and the smartphone 20 (the number of times is 1 or more) is extracted. In this case, “Soba noodles” and “Soma City” are extracted but cannot be determined as one. It should be noted that the number of times may be narrowed by the number of times or more, or the difference from the maximum number, or the like, without having a history in both. If all candidates are 0, the following calculation (step S16) is performed for all candidates (“sofa”, “soba noodles”, “Soma city”).

  In step S16, evaluation is performed based on the situation in which the phrase has been used in the past, and determination is made in step S17. As described above, the most appropriate one is selected based on the situation (status) such as time zone, season, and weather. That is, a situation similar to the situation used in the past and the situation this time is selected. The similarity determination may be, for example, that two or more of the three statuses are coincident and similar.

  As a result of step S17, if the situation of “soba noodles” used in the past is similar to this time, “soba noodles” is selected, and the determination word is determined in step S13. If neither “Soba noodle lover” nor “Soma City” corresponds to the similarity, step S18 is executed, and “Soba noodle lover” having the highest score is selected.

  Next, the case where “Soba noodles” satisfy the threshold in step S6 will be described. In this case, “Soba noodle” is determined as a determination word in step S7, and it is determined whether or not the navigation command is in step S8. “Soba noodles” is not included in the command for operating the car navigation system 10, so the cooperative operation of the smartphone 20 is performed in step S 9. On the smartphone 20, a search related to “soba noodles” is performed using the Internet or the like. For example, if information on the name and location of a restaurant, a famous store, a soba noodle-making event is obtained, the information is used as a linkage result. The car navigation system 10 acquires by the smart phone 20 transmitting (step S10).

  The information obtained in step S10 is used in step S20 after learning of the determination word (“noodles like”) in step S19. For example, it is registered as point information based on information such as the name and location of the restaurant and soba experience event hall obtained in step S10, whether to set as a destination, or displayed on a map. In other words, the command execution in step S20 in this case does not interpret the determination word as an operation command, but selects and executes an arbitrary command based on the obtained information.

  According to the present embodiment, the CPU 13 of the car navigation system 10 acquires a phrase recognized by the voice recognition engine 12 that recognizes voice spoken by the user, and parameters including sound pressure information, score, and algorithm determination. In addition, the speech recognition engine 22 of the smartphone 20 that recognizes the same speech recognizes the phrase and the parameters including the sound pressure information, the score, and the algorithm determination via the short-range wireless communication unit 15. Based on the parameters of the speech recognition engine 12 and the parameters of the speech recognition engine 22, either the recognition result of the speech recognition engine 12 or the recognition result of the speech recognition engine 22 is selected and executed as a command. By doing so, it is possible to select from the results of the two speech recognition engines, so that speech recognition can be performed with higher accuracy than performing speech recognition alone. In addition, since the car navigation system 10 and the smartphone 20 have different algorithms and dictionaries, recognition results suitable for various environments can be obtained. Therefore, an appropriate recognition result can be obtained.

  If the parameter of the speech recognition engine 12 is equal to or greater than the threshold value, the phrase recognized by the car navigation system 10 (speech recognition engine 12) is selected as a determination word, so the result recognized by the car navigation system 10 is given priority. Can be used.

  When the parameter of the speech recognition engine 12 is less than the threshold and the parameter of the smartphone 20 (speech recognition engine 22) is greater than or equal to the threshold, the phrase recognized by the smartphone 20 is selected as a determination word, so the car navigation system The result recognized by the smartphone 20 can be used when the reliability of the recognized result of 10 is low and the possibility of being unsuitable for use is high.

  When the parameter of the voice recognition engine 12 is less than the threshold and the parameter of the smartphone 20 (voice recognition engine 22) is greater than or equal to the threshold, and the recognition result of the smartphone 20 is not included in the navigation command, the smartphone 20 performs a cooperative operation. The result is acquired, and the processing is performed in the CPU 13. By doing in this way, although the reliability of the result recognized by the smartphone 20 is high, when the phrase is not a command for operating the car navigation system 10, information related to the phrase is obtained and operated. Can do.

  Moreover, since the determination word determined by the car navigation system 10 and the smartphone 20 is learned after the determination word is determined, both voice recognition engines can share the recognition result to improve the accuracy of subsequent voice recognition. Can do. In this case, the car navigation system 10 can learn results that could not be known so far, and can be expected to improve the score accuracy and increase the dictionary vocabulary from the next time. For example, new words and buzzwords can be learned in a timely manner. Further, since the smartphone 20 can learn the navigation command, the speech recognition accuracy can be further improved.

  When the parameters of the speech recognition engine 12 are less than the threshold and the parameters of the speech recognition engine 22 are less than the threshold, the evaluation based on the expressions (1) and (2), the evaluation based on the past use history, the past use information Since the determination word is determined by evaluation or the like, the determination word can be determined even when the determination word cannot be determined based on the sound pressure information, the score, and the algorithm determination result.

  In addition, since the voice recognition engine 12, the CPU 13, and the short-range wireless communication unit 15 are integrally provided, appropriate recognition is performed in the car navigation system 10 by linking with the smartphone 20 having the voice recognition engine 22. The result can be obtained.

  In the flowchart shown in FIG. 3, it is determined whether or not the navigation command is a navigation command in step S8 after the recognition result of the smartphone 20 is used as a determination word in step S7. If it is determined as a determination word, step S19 may be executed as it is.

  In the configuration shown in FIGS. 1 and 2, the car navigation system 10 and the smartphone 20 have voices input to the microphones 11 and 21, respectively. For example, the voice input to the microphone 11 of the car navigation system 10 is voiced. After converting into a signal, it transmits to the smart phone 20, and the smart phone 20 may perform voice recognition based on the audio | voice signal. In this case, the sound pressure information cannot be used as a parameter, but since the score and algorithm determination are often different, it is possible to determine only with such information. That is, there may be one input unit.

  Further, by configuring the flowchart of FIG. 3 as a program executable by a computer, it can be configured as a control program of the information control apparatus.

  In the above-described embodiment, the car navigation system 10 is mainly operated, but the smartphone 20 may be mainly used. Moreover, you may apply not only to the car navigation system 10 or the smart phone 20, but to other information processing apparatuses, such as a personal computer and the household appliances which can be operate | moved with an audio | voice.

  Further, the present invention is not limited to the above embodiment. That is, those skilled in the art can implement various modifications in accordance with conventionally known knowledge without departing from the scope of the present invention. Of course, such modifications are included in the scope of the present invention as long as the configuration of the information processing apparatus of the present invention is provided.

10 Car navigation system (information processing equipment)
11 Microphone (input unit)
12 Speech recognition engine (first speech recognition unit)
13 CPU (control unit, first acquisition unit, processing unit)
15 Short-range wireless communication unit (second acquisition unit)
20 Smartphone 21 Microphone (input unit)
22 Voice recognition engine (second voice recognition unit)
S1 Voice recognition on the navigation side (first acquisition process)
S2 Voice recognition on the smartphone side (second acquisition process)
S4 ~ S20 Select either Navi or Smartphone and execute command (control process)

Claims (1)

A first acquisition unit that acquires first speech recognition result information and first speech recognition processing information from a first speech recognition unit that recognizes speech;
A second acquisition unit that acquires second voice recognition result information and second voice recognition processing information from a second voice recognition unit that recognizes the voice;
Based on the first speech recognition processing information and the second speech recognition processing information, either the first speech recognition result information or the second speech recognition result information is selected, and the selected first speech recognition result information or A control unit that causes the processing unit to execute processing related to the second speech recognition result information;
An information processing apparatus comprising:

Images