JP6287754B2 - Response generation apparatus, response generation method, and response generation program - Google Patents

Description

  The present invention relates to a response generation apparatus that performs a response to a user, a response generation method, and a response generation program.

  A voice recognition means for recognizing the user's voice, a structure analysis means for analyzing the structure of the voice recognized by the voice recognition means, and a response sentence to the user's voice based on the structure of the voice analyzed by the structure analysis means. There is known a response generation device including a response output unit that generates and outputs the generated response sentence (see, for example, Patent Document 1).

JP 2010-157081 A

The response generation apparatus as described above takes time for the structure analysis of voice and the generation of the response sentence, and waiting for a response occurs. For this reason, there is a possibility that a sense of incongruity occurs in the dialogue. Thus, for example, it is conceivable to simply respond by using the user's voice recognized by the voice recognition means while waiting for the response as a repeated response sentence. In this case, the waiting time for the response is shortened, and the uncomfortable feeling of the dialogue is alleviated, but the response pattern becomes uniform and unnaturalness as the dialogue remains.

  The present invention has been made to solve such problems, and provides a response generation device, a response generation method, and a response generation program that can alleviate the uncomfortable feeling of dialogue due to a uniform response pattern. The main purpose.

In order to achieve the above object, one aspect of the present invention includes a speech recognition unit that recognizes a user's voice, a structure analysis unit that analyzes a structure of a speech recognized by the speech recognition unit, and a recognition by the speech recognition unit. Noun extraction means for extracting a noun from the generated voice, repeat generation means for generating a repetitive response sentence for repeating the user's voice based on the noun extracted by the noun extraction means, and the structure analysis means Based on the structure of the voice analyzed by the above, an arbitrary response sentence to the user's voice is generated, the repeated response sentence generated by the repetition generation means is output, and then the generated arbitrary response sentence is output And a response output means for responding to the information by associating a plurality of keywords with the magnitude of the impression degree of each keyword, and attaching the magnitude of the impression degree. Storage means for storing a word and information in which an output mode is associated, and the repetition generation means selects a keyword of the storage means that matches the noun extracted by the noun extraction means, and selects the selected An additional word corresponding to the magnitude of the impression level of the keyword is added to the noun to generate the repeated response sentence, and the response output means stores in the storage means that matches the noun extracted by the noun extraction means In the response generation device, the selected keyword is selected, and the repeated response sentence generated by the repeated generation unit is output in an output mode corresponding to the impression level of the selected keyword. is there.
In this aspect, the storage means may store information in which at least one of the output forms of volume, frequency, and intonation is associated with a numerical value representing the impression level of each keyword.
In this one aspect, the output aspect may be set so that at least one of volume, frequency, and intonation increases as the impression level of each keyword increases.
In this aspect, the phoneme analysis unit that analyzes the phoneme of the user's voice, and the conflict generation unit that generates a response to the user's voice based on the analysis result of the phoneme analyzed by the phoneme analysis unit And before outputting the repeated response sentence generated by the repetition generation means, the response of the interaction generated by the interaction generation means may be output.
One aspect of the present invention for achieving the above object includes a step of recognizing a user's voice, a step of analyzing a structure of the recognized voice, a step of extracting a noun from the recognized voice, Generating a repetitive response sentence for repeating the user's voice based on the extracted noun; generating an optional response sentence for the user's voice based on the analyzed voice structure; After outputting the generated repeated response sentence, the step of outputting the generated arbitrary response sentence, information in which the magnitude of the impression level of each keyword is associated with a plurality of keywords, and the magnitude of the impression level Storing the information in which the additional word and the output mode are associated with each other, and selecting the keyword that matches the extracted noun, An additional word corresponding to the impression level of the selected keyword is added to the noun to generate the repeated response sentence, each keyword that matches the extracted noun is selected, and the impression of the selected keyword The response generation method may output the generated repeated response sentence in an output mode corresponding to the magnitude of the degree.
One aspect of the present invention for achieving the above object includes a process for recognizing a user's voice, a process for analyzing the structure of the recognized voice, a process for extracting a noun from the recognized voice, Based on the extracted noun, a process of generating a repeated response sentence for repeating the user's voice, and an optional response sentence to the user's voice based on the analyzed voice structure, A response generation program for causing a computer to execute a process of outputting the generated arbitrary response sentence after outputting the generated repeated response sentence, wherein the degree of impression of each keyword is set to a plurality of keywords. Information associated with each other and information in which an additional word and an output mode are associated with the magnitude of the impression degree are stored, and the keyword that matches the extracted noun is selected, A process of generating an iterative response sentence by adding an additional word corresponding to the magnitude of impression of the selected keyword to the noun, selecting each keyword that matches the extracted noun, and selecting the selected keyword A response generation program that causes a computer to execute the process of outputting the generated repeated response sentence in an output manner corresponding to the magnitude of the impression degree.

  According to the present invention, it is possible to provide a response generation device, a response generation method, and a response generation program that can alleviate the uncomfortable feeling of dialogue due to a uniform response pattern.

It is a block diagram which shows the schematic system configuration | structure of the response generation apparatus which concerns on Embodiment 1 of this invention. It is a block diagram which shows the schematic hardware constitutions of the response generation apparatus which concerns on Embodiment 1 of this invention. It is a flowchart which shows the processing flow of the response generation method which concerns on Embodiment 1 of this invention. It is a block diagram which shows the schematic system configuration | structure of the response generation apparatus which concerns on Embodiment 2 of this invention.

Embodiment 1
Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing a schematic system configuration of a response generation apparatus according to Embodiment 1 of the present invention. The response generation apparatus 1 according to the first embodiment includes a voice recognition unit 2 that recognizes a user's voice, a structure analysis unit 3 that analyzes a voice structure, and a response output that generates and outputs a response sentence to the user's voice. A unit 4, a repeat generation unit 5 that generates a repeated response sentence, and a noun extraction unit 9 are provided.

  The response generation device 1 includes, for example, a CPU (Central Processing Unit) 1a that performs arithmetic processing and the like, a ROM (Read Only Memory) and a RAM (Random Access Memory) that store arithmetic programs executed by the CPU 1a, control programs, and the like. 2) and a microcomputer including an interface unit (I / F) 1c for inputting / outputting signals to / from the outside, and the like (FIG. 2). The CPU 1a, the memory 1b, and the interface unit 1c are connected to each other via a data bus 1d.

  The voice recognition unit 2 performs voice recognition processing based on the user's voice information acquired by the microphone 6, converts the user's voice information into text, and recognizes it as character string information. The speech recognition unit 2 is a specific example of speech recognition means. The voice recognition unit 2 detects a speech section from the user's voice information output from the microphone 6, and performs voice matching by performing pattern matching on the detected voice information of the speech section with reference to, for example, a statistical language model. Recognize. Here, the statistical language model is a probability model for calculating the appearance probability of a language expression, such as the distribution of the appearance of a word or the distribution of a word that appears after a certain word, and learned the connection probability in units of morphemes. Is. The statistical language model is stored in advance in the memory 1b or the like. Note that the speech recognition unit 2 generates morpheme information with part-of-speech information by adding the part-of-speech type (noun, adjective, verb, adverb, etc.) to each morpheme of the user's speech information. The voice recognition unit 2 outputs the recognized voice information of the user to the structure analysis unit 3 and the noun extraction unit 9.

  The structure analysis unit 3 analyzes the structure of the voice information recognized by the voice recognition unit 2. The structure analysis unit 3 is a specific example of structure analysis means. For example, the structure analysis unit 3 performs morphological analysis on character string information indicating the voice information of the user that has been voice-recognized using a general morphological analyzer, and interprets the meaning of the character string information. The structure analysis unit 3 outputs the analysis result of the character string information to the response output unit 4.

  The response output unit 4 generates a response sentence (hereinafter referred to as an optional response sentence) to the user's voice information based on the structure of the voice information analyzed by the structure analysis unit 3, and outputs the generated optional response sentence To do. The response output unit 4 is a specific example of response output means. For example, the response output unit 4 generates an arbitrary response sentence for the user's voice information based on the analysis result of the character string information output from the structure analysis unit 3. Then, the response output unit 4 outputs the generated response sentence using the speaker 7.

  More specifically, the structure analysis unit 3 extracts the predicate term structure in the character string information “eating tonkatsu” and specifies the predicate “eat” and the case particle “wo”. Then, the response output unit 4 extracts the type of case particles that can be related to the predicate “eat” specified by the structure analysis unit 3 from the deficiency dictionary database 8 in which the correspondence between the predicate and the case particle is stored. To do. The deficiency dictionary database 8 is constructed in the memory 1b, for example.

  The response output unit 4 generates, for example, predicate term structures such as “what to eat”, “where to eat”, “when to eat”, and “who to eat” as an optional response sentence. Further, the response output unit 4 randomly selects from other predicate term structures except the surface case "" that does not match the user's voice in the generated predicate term structure, and selects the selected predicate term. The structure is an arbitrary response sentence. The response output unit 4 selects, for example, a predicate term structure “who did you eat?” And outputs it as an optional response sentence. In addition, the generation method of the arbitrary response sentence mentioned above is an example, It is not limited to this, Arbitrary generation methods can be used.

  The noun extraction unit 9 extracts only the noun from the recognized user's voice information based on the morpheme information with part of speech information of the voice information output from the voice recognition unit 2. The noun extraction unit 9 is a specific example of noun extraction means. The noun extraction unit 9, for example, from the morphological information with part-of-speech information “tonkatsu (noun) (participant) ate (verb) yo (particle)” of the speech information output from the speech recognition unit 2, “tonkatsu (noun)” "Only. In addition, the noun extraction unit 9 includes, for example, tonkatsu (general noun), toba Yaba (proprietary noun), voting => voting (sa variable noun) (however, excluding some nouns such as numerals), etc. To extract. The noun extraction unit 9 outputs the extracted noun to the repetition generation unit 5.

  By the way, the structure analysis of voice information and the generation of a response sentence as described above require time (for example, about 3 seconds), and the processing cost is high. For this reason, there is a possibility that waiting for a response may occur, and the conversation may feel uncomfortable.

  On the other hand, in the response generation device 1 according to the first embodiment, the repeat generation unit 5 repeats a response sentence (hereinafter referred to as a repeat response sentence) from the user's voice recognized by the voice recognition unit 2. ) Is generated easily. And the response output part 4 outputs the voluntary response sentence based on the structure of an audio | voice after making the repeated response sentence produced | generated by the repetition production | generation part 5. FIG.

  Thereby, since the repeated response sentence only repeats the recognized user's voice by returning a parrot, it does not require generation time (for example, about 1 second), and the processing cost is low. Therefore, it is possible to output a repetitive response sentence with a low processing cost while waiting for a response until the optional response sentence with a high processing cost is output. Therefore, it is possible to alleviate the uncomfortable feeling of the dialogue due to the large duration of the dialogue caused by waiting for a response.

  As described above, the repeat generation unit 5 generates the speech information recognized by the speech recognition unit 2 as a repeat response sentence for performing a parrot return. Here, rather than returning the parrot as it is without changing the user's voice at all, the naturalness of the conversation is improved by adding a specific additional word to the noun of the user's voice information and returning the parrot. For example, in response to the user's utterance “I went to the ocean”, the response generation device 1 responds “Umi ka” or “Oh, ka ka” rather than simply responding “I went to the ocean”. The naturalness of dialogue is further improved.

  Therefore, the repeat generation unit 5 according to the first embodiment generates a repeat response sentence by adding a specific additional word to the noun extracted by the noun extraction unit 9. For example, the repetition generation unit 5 selects each keyword in the memory 1b that matches the noun extracted by the noun extraction unit 9, and adds an additional word corresponding to the numerical value of the selected keyword to the noun. Generate a response sentence. As a result, since the vocabulary of the repeated response sentence can be varied, it is not a uniform response pattern, and the discomfort of the dialogue can be further alleviated.

  The memory 1b stores impression degree information (table information or the like) in which a plurality of keywords and an impression value indicating the magnitude of the impression degree of each keyword are associated with each other as follows. The memory 1b is a specific example of storage means.

Keyword “tonkatsu” Impression value “0.7”,
Keyword “steak” impression value “−0.3”,
Keyword “baseball” impression value “0.7”,
Keyword “soccer” Impression value “−0.47”

The impression value is set to a value between (uncomfortable) -1.0 to +1.0 (comfortable), but is not limited thereto. The response generation device 1 has a conversation function with a user accumulated in advance, and a determination function that increases the impression value of a part of speech when the frequency of appearance of a positive part of speech (such as “I like tonkatsu”) increases, for example. (M = Log (n + 1) etc.) and the impression value of each keyword may be set. Thus, the impression value of each keyword is set so that the impression value increases as the keyword has a better user impression.
In addition, although the numerical value is set to the said impression value, it is not limited to this. The impression value may be, for example, large, medium, or small, and an arbitrary value representing the magnitude of the impression level of the keyword can be set.

The repeat generation unit 5 sets an impression value for the noun from the noun extraction unit 9 based on the noun output from the noun extraction unit 9 and the impression degree information in the memory 1b.
Further, for example, three levels of excitement are set in advance for the impression value x as follows, but the present invention is not limited to this, and the excitement can be arbitrarily set.
x <0.3 Excitability = 0
0.3 ≦ x ≦ 0.7 Excitability = 1
0.7 ≦ x Excitability = 2

The memory 1b stores excitement level information (table information) in which the excitement level and additional words (beginning, ending, etc.) are associated with each other.
The repeat generation unit 5 sets the excitement level for the noun based on the set impression value of the noun and the excitement level information in the memory 1b. The repetition generation unit 5 outputs the set excitement level of the noun to the response output unit 4. The repeat generation unit 5 selects an additional word corresponding to the noun based on the set excitement level of the noun and the excitement level information in the memory 1b. The repeat generation unit 5 generates a repeat response sentence by adding an additional word to the set noun.

More specifically, the noun extraction unit 9 extracts only the noun “tonkatsu” from the character string information “I ate a tongue cutlet” recognized by the voice recognition unit 2, and outputs it to the repetition generation unit 5. .
The repeat generation unit 5 sets an impression value = 0.7 for the noun “tonkatsu” based on the noun “tonkatsu” output from the noun extraction unit 9 and the impression degree information in the memory 1b. . The repetition generation unit 5 sets the excitement level = 1 corresponding to the impression value = 0.7 to the noun “tonkatsu”.

  Based on the excitement level = 1 of the set noun “tonkatsu” and the excitement level information in the memory 1b, the repetition generation unit 5 adds an additional word corresponding to the noun “tonkatsu” (beginning “o,”, Select the ending "ka"). The repeat generation unit 5 generates a repeat response sentence “O, Tonkatsu Ka” by adding an additional word (beginning “O,”, ending “Ka”) to the set noun “Tonkatsu”.

  The memory 1b may store, for example, information that associates impression values with additional words. In this case, the repetition generation unit 5 selects an additional word corresponding to the impression value based on the set impression value of the noun and the information in the memory 1b. The repeat generation unit 5 generates a repeat response sentence by adding an additional word to the set noun.

  Furthermore, in the first embodiment, in order to improve a uniform response pattern and improve the naturalness of dialogue, not only a specific additional word is added to the noun, but also the output mode is changed. That is, the response output unit 4 according to the first embodiment is generated by the repeated generation unit 5 in an output mode corresponding to the impression value of each keyword in the memory 1b that matches the noun extracted by the noun extraction unit 9. Output repeated response text. As a result, since the vocabulary of the repeated response sentence can be varied, it is not a uniform response pattern, and the discomfort of the dialogue can be further alleviated.

The memory 1b stores, for example, output information (table information or the like) in which the output mode is associated with the degree of excitement as follows. Note that the output information, impression degree information, and excitement degree information in the memory 1b can be set and changed via an arbitrary input device such as a touch panel, a keyboard, or a voice recognition device.
Exciting degree = 0 Output mode Speaker volume = 1 times Exciting degree = 1 Output mode Speaker volume = 1.5 times Exciting degree = 2 Output mode Speaker volume = 2 times

  The response output unit 4 selects the output mode of the repeated response sentence based on the excitement level of the noun output from the repeated generation unit 5 and the output information of the memory 1b. The response output unit 4 outputs the repeated response text output from the repeated generation unit 5 in the selected output mode.

  For example, based on the excitement level = 1 of the noun “tonkatsu” output from the repeat generation unit 5 and the output information of the memory 1b, the response output unit 4 outputs an output form “speaker volume = Select “1.5 times”. The response output unit 4 outputs the output response “speaker volume = 1.5 times” in which the repeated response sentence “O, Tonkatsuka” output from the repeated generation unit 5 is selected. As a result, the louder speaker volume increases as the degree of user excitement (impression value) for the noun increases. Therefore, diversity can be given to the repeated response sentence, and the uncomfortable feeling of dialogue can be further alleviated.

  The memory 1b may store, for example, output information in which impression values are associated with output modes. In this case, the repeat generation unit 5 selects an output mode corresponding to the impression value based on the set impression value of the noun and the output information of the memory 1b. The response output unit 4 outputs the repeated response text output from the repeated generation unit 5 in the selected output mode.

Furthermore, although the said speaker volume is mentioned as an example of an output mode, it is not limited to this. The output mode may be the setting of the fundamental frequency (magnification, increase, etc.) or intonation (magnification, increase, etc.) of the speaker sound. For example, the response output unit 4 outputs the repeated response sentence output from the repeated generation unit 5 in the selected output mode “basic frequency = 1.2 times”. As a result, the higher the user excitement level (impression value) with respect to the noun, the higher the fundamental frequency (the higher the voice becomes). Therefore, diversity can be given to the repeated response sentence, and the uncomfortable feeling of dialogue can be further alleviated.
In addition, the process which produces | generates the repeated response sentence mentioned above is a simple process which extracts a noun from audio | voice information, adds a corresponding additional word with respect to the extracted noun, and outputs it in a corresponding output mode. is there. Therefore, the processing cost for generating the repeated response text is lower than the processing cost for generating the voluntary response text by analyzing the structure of the voice information.

FIG. 3 is a flowchart showing a processing flow of the response generation method according to the first embodiment.
The voice recognition unit 2 performs voice recognition of the user's voice information acquired by the microphone 6 (step S101), and outputs the recognized user's voice information to the structure analysis unit 3, the repeat generation unit 5, and the noun extraction unit 9. To do.

  The noun extraction unit 9 extracts only the noun from the recognized user's speech information based on the morpheme information with part of speech information of the speech information output from the speech recognition unit 2 (step S102). The noun extraction unit 9 outputs the extracted noun to the repetition generation unit 5.

  The repeat generation unit 5 sets an impression value for the noun from the noun extraction unit 9 based on the noun output from the noun extraction unit 9 and the impression degree information in the memory 1b (step S103). . The repeat generation unit 5 sets the excitement level for the noun based on the set impression value of the noun and the excitement level information in the memory 1b (step S104). The repetition generation unit 5 outputs the set excitement level of the noun to the response output unit 4.

  The repeat generation unit 5 selects an additional word corresponding to the noun based on the set excitement level of the noun and the excitement level information in the memory 1b (step S105). The repeat generation unit 5 generates a repeat response sentence by adding an additional word to the set noun (step S106). The repeat generation unit 5 outputs the generated repeat response sentence to the response output unit 4.

  The response output unit 4 selects the output mode of the repeated response sentence based on the excitement level of the noun output from the repeated generation unit 5 and the output information of the memory 1b (step S107). The response output unit 4 outputs the repeated response sentence output from the repeated generation unit 5 from the speaker 7 in the selected output mode (step S108).

  In parallel with the above (Step 102) and (Step 108), the structure analysis unit 3 analyzes the structure of the speech information recognized by the speech recognition unit 2 (Step S109), and returns the analysis result of the character string information as a response. Output to the output unit 4.

  The response output unit 4 generates an arbitrary response sentence based on the analysis result of the character string information output from the structure analysis unit 3 (step S110), and outputs the generated arbitrary response sentence from the speaker 7 (step S111).

  As described above, in the first embodiment, the repeat generation unit 5 selects each keyword in the memory 1b that matches the noun extracted by the noun extraction unit 9, and adds an additional word corresponding to the selected keyword to the noun. To generate a repeated response sentence. Furthermore, the response output unit 4 outputs the repeated response sentence generated by the repeated generation unit 5 in an output mode corresponding to the impression value of each keyword in the memory 1b that matches the noun extracted by the noun extraction unit 9. To do. As a result, since the vocabulary of the repeated response sentence can be varied, it is not a uniform response pattern, and the discomfort of the dialogue can be further alleviated.

Embodiment 2. FIG.
FIG. 4 is a block diagram illustrating a schematic system configuration of the response generation apparatus according to the second embodiment of the present invention. In addition to the configuration of the response generation apparatus 1 according to the first embodiment, the response generation apparatus 20 according to the second embodiment includes a phoneme analysis unit 21 that analyzes the phoneme of the user's voice information, and a conflict of the user's voice information. It is characterized in that it further includes an interaction generation unit 22 that generates a response.

  The phoneme analysis unit 21 analyzes the phoneme of the user's voice information based on the user's voice information acquired by the microphone 6. The phoneme analysis unit 21 is a specific example of phoneme analysis means. For example, the phonological analysis unit 21 estimates a break in a user's voice by detecting a change in volume level or frequency (such as a fundamental frequency) of voice information. The phoneme analysis unit 21 outputs the phoneme analysis result to the conflict generation unit 22.

  Based on the phonological analysis result output from the phonological analysis unit 21, the harmonious generation unit 22 generates a response to the user's voice (hereinafter referred to as a “compatibility response”). The interaction generating unit 22 is a specific example of the interaction generating unit. For example, when the volume level of the voice information is equal to or lower than the threshold, the conflict generation unit 22 searches the standard response database 23 in which the conflict pattern is stored. Then, the conflict generation unit 22 randomly selects a conflict response from the standard response database 23. The standard response database 23 stores a plurality of patterns used for consideration such as “Yes. The fixed response database 23 is constructed in the memory 1b and the like. The interaction generating unit 22 outputs the generated interaction response to the response output unit 4.

  The response output unit 4 causes the speaker 7 to output the conflict response generated by the conflict generation unit 22 before the repeated response sentence generated by the repeat generation unit 5. Note that the phonological analysis unit 21 performs phonological analysis using feature quantities with low processing costs. For this reason, the generation time of the conflict response is shorter than the generation time of the repeated response sentence, and the processing cost is lower.

  Therefore, it is possible to output a conflict response with a lower processing cost before outputting the repeated response sentence. Thereby, the connection between dialogs becomes smoother, and the uncomfortable feeling of dialog can be eased more. Further, more responses and response sentences having different processing costs are generated in parallel and output in the order of generation. As a result, it is possible to maintain a smoother continuity of dialogue and realize a more natural dialogue that does not impair the sense of tempo.

  Note that the conflict generation unit 22 routinely generates a conflict response, and the repeat generation unit 5 generates a repeat response sentence by only performing surface interpretation of the speech recognition result. Therefore, it is assumed that the response output unit 4 generates an optional response candidate similar to the interaction response generated by the interaction generation unit 22 and the repetition response generated by the repetition generation unit 5.

  On the other hand, the response output unit 4 excludes from the voluntary response candidates the voluntary response candidates that overlap with the conflict response generated by the conflict generation unit 22 and the repeat response generated by the repeat generation unit 5. And the response output part 4 selects an optimal candidate from the excluded voluntary response candidates, and makes it an arbitrary response sentence. This eliminates redundant useless words and realizes a more natural dialogue.

  For example, in response to the user's utterance “Today is hot”, the conflict generation unit 22 generates a conflict response “Yes”. Subsequently, the repeat generation unit 5 generates a repeat response sentence “hot”. On the other hand, the response output unit 4 generates a voluntary response candidate “I don't like it”, “How long will it be hot?”, “It ’s hot”, “I think so”, and so on. The response output unit 4 eliminates “hot” overlapping with the repeated response sentence generated by the repeated generation unit 5 from the generated voluntary response candidates. Then, the response output unit 4 selects, for example, “How long will it be hot?” From the excluded optional response candidates, and uses it as an optional response sentence.

  Note that, in the response generation device 20 according to the second embodiment, the same parts as those in the response generation device 1 according to the first embodiment are denoted by the same reference numerals, and detailed description thereof is omitted.

Hereinafter, an example of the interaction between the response generation device 20 and the user will be shown. In the following example, M is a response sentence and a response of the response generation device 20, and U is a user's utterance.
M (topic provided): What did you eat at lunch?
U: I ate Tonkatsu.
M (conformity response): Yeah. Yup.
M (repeat response): Oh, tonkatsu. ("O" and "ka" are added, speaker volume = 1.5 times output)
M (optional response): Who did you eat?
U: I ate with my friends.
M (Aiso response): That's right.
M (repeat response): I'm a friend. (Add "Nandaa")
M (voluntary response): Where did you eat it?
U: I ate in Yaba.
M (conformity response): I see.
M (repeat response): Oh, Yaba. ("Oo" and "Dane" added, speaker volume = 1.5 times, fundamental frequency = 1.1 times)
M (optional response): I ate it.
U: It was delicious.
M (conformity response): Hmm.
M (repeat response): Was it delicious? (Add "noka")
M (voluntary response): That's good. Mr. ○○.

  As shown in the example of the above dialogue, when the user utters, the response response of the response generation device 20, the repeated response text, and the voluntary response text continue to the utterance at a fast pace, and the connection between the dialogs is smoother. I understand that In addition, it is understood that the naturalness of the dialogue is further improved by giving diversity to the additional words added to the repeated response sentence and the output mode.

  Note that the present invention is not limited to the above-described embodiment, and can be changed as appropriate without departing from the spirit of the present invention.

  In the above-described embodiment, the response output unit 4 outputs the conflict response generated by the conflict generation unit 22 from the speaker 7, but is not limited thereto. The response output unit 4 may perform an arbitrary response with a low processing load based on the conflict response generated by the conflict generation unit 22. For example, the response output unit 4 may perform vibrations of the vibration device, lighting / flashing of the light device, display of the display device, operation of each part such as a robot's limbs, head, and trunk, and any combination thereof. You may go.

  In the above embodiment, the response output unit 4 outputs the repeated response text generated by the repeated generation unit 5 from the speaker 7, but is not limited thereto. The response output unit 4 may output an arbitrary repeated response sentence with a low processing load based on the repeated response sentence generated by the repeated generation unit 5. For example, the response output unit 4 may output a repetitive response sentence using a display on the display device or the like, or may output it by arbitrarily combining means. In this case, for example, the output mode of the response output unit 4 may be settings such as character size, brightness, and shape.

In addition, the present invention can realize the processing shown in FIG. 3 by causing the CPU 1a to execute a computer program, for example.
The program may be stored using various types of non-transitory computer readable media and supplied to a computer. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (for example, flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (for example, magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / W and semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (random access memory)) are included.

  The program may also be supplied to the computer by various types of transitory computer readable media. Examples of transitory computer readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.

  DESCRIPTION OF SYMBOLS 1 Response production | generation apparatus, 2 Speech recognition part, 3 Structure analysis part, 4 Response output part, 5 Repeat production | generation part, 6 Microphone, 7 Speaker, 8 Insufficient dictionary database, 9 Noun extraction part, 21 Phonological analysis part, 22 Generation unit, 23 standard response database

Claims (6)

Voice recognition means for recognizing the user's voice;
Structure analysis means for analyzing the structure of the voice recognized by the voice recognition means;
Noun extraction means for extracting nouns from the speech recognized by the speech recognition means;
Based on the noun extracted by the noun extraction means, a repeat generation means for generating a repeated response sentence for repeating the user's voice;
Based on the structure of the voice analyzed by the structure analysis means, an optional response sentence for the user's voice is generated, and after the repetition response sentence generated by the repetition generation means is output, the generated optional answer sentence is generated. A response output means for outputting a response sentence;
A response generation device comprising:
Storage means for storing information in which the magnitude of the impression level of each keyword is associated with a plurality of keywords, and information in which an additional word and an output mode are associated with the magnitude of the impression level,
The repeat generation means selects a keyword of the storage means that matches the noun extracted by the noun extraction means, and adds an additional word corresponding to the impression level of the selected keyword to the noun. Generating the repeated response sentence;
The response output means selects each keyword of the storage means that matches the noun extracted by the noun extraction means, and outputs the repeat generation means in an output mode corresponding to the impression degree of the selected keyword. A response generation apparatus characterized by outputting a repetitive response sentence generated by. The response generation device according to claim 1,
The said memory | storage means has memorize | stored the information which matched at least 1 said output aspect among volume, a frequency, and intonation with the magnitude | size of the impression degree of each said keyword, The response generation apparatus characterized by the above-mentioned . The response generation device according to claim 2,
The response generation device is characterized in that the output mode is set so that at least one of volume, frequency, and intonation increases as the degree of impression of each keyword increases. . The response generation device according to any one of claims 1 to 3,
Phoneme analysis means for analyzing the phoneme of the user's voice;
A conflict generating means for generating a response to the user's voice based on the analysis result of the phoneme analyzed by the phoneme analyzing means;
Before outputting the repeated response sentence generated by the repetition generation means, the response response generated by the interaction generation means is output. Recognizing the user's voice;
Analyzing the structure of the recognized speech;
Extracting a noun from the recognized speech;
Generating a repetitive response sentence for repeating the user's voice based on the extracted noun;
Generating an arbitrary response sentence to the user's voice based on the analyzed voice structure, outputting the generated repeated response sentence, and then outputting the generated arbitrary response sentence;
Storing information in which the magnitude of the impression level of each keyword is associated with a plurality of keywords, and information in which an additional word and an output mode are associated with the magnitude of the impression level;
A response generation method including:
Selecting the keyword that matches the extracted noun, adding an additional word corresponding to the impression level of the selected keyword to the noun to generate the repeated response sentence;
Selecting each keyword that matches the extracted noun and outputting the generated repetitive response sentence in an output mode corresponding to the magnitude of the impression level of the selected keyword. Method. Processing to recognize the user's voice,
Processing to analyze the structure of the recognized speech;
A process of extracting nouns from the recognized speech;
Based on the extracted noun, a process of generating a repeated response sentence for repeating the user's voice;
A process of generating an arbitrary response sentence to the user's voice based on the analyzed voice structure, outputting the generated repeated response sentence, and outputting the generated arbitrary response sentence. A response generation program to be executed by a computer,
Information in which the magnitude of the impression level of each keyword is associated with a plurality of keywords, and information in which an additional word and an output mode are associated with the magnitude of the impression level are stored,
Selecting the keyword that matches the extracted noun, and adding the additional word corresponding to the impression level of the selected keyword to the noun to generate the repeated response sentence;
Selecting each keyword that matches the extracted noun, and causing the computer to execute a process of outputting the generated repeated response sentence in an output manner corresponding to the magnitude of the impression degree of the selected keyword A response generation program characterized by the above.

Images