WO2007138944A1 - 情報付与システム、情報付与方法、情報付与プログラム及び情報付与プログラム記録媒体 - Google Patents
情報付与システム、情報付与方法、情報付与プログラム及び情報付与プログラム記録媒体 Download PDFInfo
- Publication number
- WO2007138944A1 WO2007138944A1 PCT/JP2007/060490 JP2007060490W WO2007138944A1 WO 2007138944 A1 WO2007138944 A1 WO 2007138944A1 JP 2007060490 W JP2007060490 W JP 2007060490W WO 2007138944 A1 WO2007138944 A1 WO 2007138944A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- attribute information
- language
- information
- language unit
- unit
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 31
- 230000014509 gene expression Effects 0.000 claims abstract description 63
- 230000015572 biosynthetic process Effects 0.000 claims description 38
- 238000003786 synthesis reaction Methods 0.000 claims description 38
- 230000008451 emotion Effects 0.000 claims description 34
- 230000008859 change Effects 0.000 claims description 18
- 239000000284 extract Substances 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 34
- 238000010586 diagram Methods 0.000 description 15
- 230000002194 synthesizing effect Effects 0.000 description 7
- 239000002131 composite material Substances 0.000 description 4
- 239000000203 mixture Substances 0.000 description 3
- 230000000877 morphologic effect Effects 0.000 description 3
- 230000002996 emotional effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 235000006481 Colocasia esculenta Nutrition 0.000 description 1
- 240000004270 Colocasia esculenta var. antiquorum Species 0.000 description 1
- 241000287462 Phalacrocorax carbo Species 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
- G10L13/10—Prosody rules derived from text; Stress or intonation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
Definitions
- Information grant system information grant method, information grant program, and information grant program recording medium
- the present invention relates to an information providing system (including an application system), an information providing method, an information providing program, and a recording medium on which an information providing program is recorded, and in particular, attribute information indicating a sentence emotion, an utterance style, and the like.
- the present invention relates to an information grant system, an information grant method, an information grant program, and a recording medium on which the information grant program is recorded.
- attribute information is information that is different from the original meaning of characters that can be used to improve the expressiveness at the time of text output, such as emotions of speakers such as emotions and readings.
- Information indicating the speaker's utterance style such as DJ (disc jockey) tone.
- methods for expressing sentences using this attribute information methods that appeal to the ear with voice, music, etc., and methods that appeal to the eyes with text color, pictures, light, etc. are considered.
- voice synthesis systems that read texts with emotion and mobile phones that display the contents of received emails with a single icon have already been realized.
- Patent Document 1 describes an example of a speech synthesis system that can read a text with emotion.
- This conventional speech synthesis system includes an utterance mode designating unit, a speech control parameter storage unit, a speech control level setting unit, and a synthesized speech unit.
- the speech synthesis system of Patent Document 1 is a system that reads out the entire sentence according to attribute information given to a user. In other words, upon receiving an arbitrary utterance mode designation from the user, the speech synthesis system of Patent Document 1 uses a combination of levels such as the generation speed and the amount of inflection corresponding to the designated utterance mode as a voice control parameter. Read memory power The In the speech synthesis system, the speech control level setting unit collectively sets the combination of the read levels, and the synthesized speech unit generates synthesized speech representing emotion.
- Patent Document 2 discloses a speech synthesis system capable of smoothly expressing emotional transitions by giving attribute information in detail.
- the speech synthesis system disclosed in Patent Document 2 includes a text analysis unit, an emotion information adding unit, and an emotion information interpolation unit.
- an input sentence is divided into segments by a text analysis unit, and emotion information is defined by referring to an emotion provision rule that defines emotion information for a character string expression representing emotion. Emotion information is added to the segment containing the character string.
- emotion information is defined by referring to an emotion provision rule that defines emotion information for a character string expression representing emotion.
- Emotion information is added to the segment containing the character string.
- Patent Document 1 JP-A-5-100692
- Patent Document 2 JP 2005-181840
- the speech synthesis system of Patent Document 2 can give more attribute information than the speech synthesis system of Patent Document 1, but it does not provide attribute information (emotion information). Only segments that contain vocabulary registered in the dictionary (emotion rules) are granted.
- the present invention has been made in view of the above circumstances, and the object of the present invention is not only a language unit including a specific character string expression but also a language unit to which attribute information is added. In view of the relationship, it is an object of the present invention to provide an information providing system, an information providing method, an information providing program, and a recording medium on which the information providing program is recorded.
- analysis means for dividing a linguistic expression into a predetermined language unit using a dictionary, and extracting a predetermined vocabulary from the language unit using the dictionary and obtaining attribute information.
- a first attribute information determination means for determining, and an attribute assignment system for assigning attribute information to a language expression at a language unit level, wherein the connection relation between each language unit and the first attribute information determination means
- a second attribute information determination means for determining attribute information for each language unit, wherein the attribute information is assigned based on the attribute information already assigned by An information processing system that performs speech synthesis and text output using attribute information assigned by the information assignment system is provided.
- an analysis unit that divides a language expression into predetermined language units using a dictionary, and a predetermined vocabulary is extracted from the language units using the dictionary to determine attribute information.
- a first attribute information determination means for executing an information grant system for assigning attribute information to a language expression at a language unit level, wherein the information grant system is connected to each language unit. And the attribute information already assigned by the first attribute information determination means, the attribute information is added and functions as the second attribute information determination means for determining the attribute information for each language unit.
- a recording medium on which the program is recorded are provided.
- an analysis unit that divides a language expression into predetermined language units using a dictionary, and a predetermined vocabulary is extracted from the language units using the dictionary to determine attribute information.
- An information providing method implemented using an information providing system that assigns attribute information to a language expression at a language unit level, wherein the information providing system includes the first attribute information determining means. Determining attribute information in language units included in the language expression by one attribute information determining means, and the information providing system assigning the connection relation of each language unit and the first attribute information determining means.
- an information providing method characterized by including: a step of determining attribute information for each language unit, wherein the attribute information is assigned based on the attribute information already completed.
- FIG. 1 is a block diagram showing a configuration of a speech synthesis system according to a first embodiment of the present invention.
- FIG. 2 is a flowchart showing the operation of the speech synthesis system according to the first embodiment of the present invention.
- FIG. 3 is a block diagram showing a configuration of a text display system according to a second embodiment of the present invention.
- FIG. 4 is a flowchart showing the operation of the text display system according to the second exemplary embodiment of the present invention.
- FIG. 5 is a diagram for explaining the correspondence between vocabulary defined in a dictionary and attribute information.
- FIG.6 A diagram for explaining the concept of analyzing the connection relationship between sentences (language units)
- FIG. 7 is a sample sentence used in the explanation of the embodiment of the present invention.
- FIG. 8 is a diagram showing an example of the analysis result of the input sentence in FIG.
- FIG. 9 State power of FIG. 8 is a diagram showing a state in which attribute information is given based on the vocabulary included in each sentence.
- FIG. 10 is a diagram showing the result of assigning attribute information based on the connection relation of the state sentence in FIG.
- FIG. 11 is a diagram showing the result of assigning attribute information using the prior art (Patent Document 2).
- FIG. 12 is a diagram for explaining the correspondence between attribute information defined in the expression dictionary and expression information.
- FIG. 13 is a diagram showing an output example by the text display system according to the second embodiment of the present invention.
- FIG. 14 is a diagram showing an output example by the text display system according to the second embodiment of the present invention.
- FIG. 15 is a diagram showing an output example by the text display system according to the second embodiment of the present invention. Explanation of symbols
- FIG. 1 is a block diagram showing the configuration of a speech synthesis system according to the first embodiment of the present invention.
- the speech synthesis system includes an input means 10 such as a keyboard and a microphone, a data processing unit 20 that operates by program control, a storage unit 30 that stores information, a display device, and a speaker. And first-class output means 40.
- the input means 10 is for inputting a sentence or inputting an instruction when selection by an operator is necessary.
- the data processing unit 20 includes an analysis unit 21 and an attribute information determination unit (first attribute information determination unit).
- the analysis unit 21 refers to the dictionary 31 and performs morphological analysis and syntax analysis on the sentence.
- Attribute information determining means (first attribute information determining means) 22 refers to the dictionary 31 and extracts the vocabulary for determining attribute information from the analysis result by the analyzing means 21, and determines attribute information to be given. Determine.
- Attribute information addition language unit selection means (second attribute information determination means) 23 analyzes the connection relation of the language units with reference to the analysis result by the analysis means 21 and the dictionary 31, and the attribute information determination means. (First attribute information determining means) Based on the attribute information determined by 22 and the connection relationship of the language units, a language unit to which attribute information is added is additionally determined.
- the synthesizing unit 24 refers to the output result of the attribute information determining unit (first attribute information determining unit) 22 and the attribute information addition language unit selecting unit (second attribute information determining unit) 23 and the synthesis dictionary 32. Then, information necessary for reading out the sentence with synthesized speech is output.
- the storage unit 30 includes a dictionary 31 and a synthesis dictionary 32 for speech synthesis processing by the synthesis means 24.
- the output means 40 is for displaying the input text on the screen or outputting it by voice using the result output by the data processing unit 20.
- the analysis means 21 refers to the dictionary 31 and performs morphological analysis and syntax analysis on the sentence (step S101 in FIG. 2).
- the attribute information determining means (first attribute information determining means) 22 refers to the dictionary 31 and searches whether there is a vocabulary for determining attribute information in the analysis result (FIG. 2). Step S102). If no vocabulary for determining attribute information is extracted (NO in step S103 in FIG. 2), the synthesizing means 24 refers to the synthesizing dictionary 32 and standard prosody for the entire sentence. And the synthesized speech is output to the output means 40 (step S108 in FIG. 2).
- attribute information determining means (first attribute information determining means) 22 determines attribute information to be given ( Step S104 in Figure 2).
- the attribute information addition language unit selection means (second attribute information determination means) 23 analyzes the connection relation of the language units with reference to the analysis result by the analysis means 21 and the dictionary 31, and also determines the attribute information determination means (first Based on the attribute information determined by the attribute information determining means) 22 and the connection relation of the language units, a language unit to which attribute information is added is additionally determined (step S 105 in FIG. 2).
- the synthesis means 24 refers to the synthesis dictionary 32 and refers to the prosody corresponding to the attribute information. Is added to the sentence (step S106 in Fig. 2).
- the output means 40 outputs the sentence to which the prosody is given as synthesized speech (step S107 in FIG. 2).
- the attribute information determination language unit selection is performed after the attribute information determination means (first attribute information determination means) 22 determines the attribute information in the sentence.
- Means (second attribute information determination means) 23 is configured to further determine the language unit to which each attribute information is assigned, so it reflects the emotional flow at the time of writing the sentence and the intended change in utterance style. Can do.
- FIG. 3 is a block diagram showing the configuration of the text display system according to the second embodiment of the present invention.
- the difference from the first embodiment is that an expression dictionary 33 and an expression providing means 25 are provided instead of the composition dictionary 32 and the composition means 24 in the first embodiment. Is a point.
- the expression assigning means 25 refers to the output results of the attribute information determining means (first attribute information determining means) 22 and the attribute information giving language unit selecting means (second attribute information determining means) 23 and the expression dictionary 33. Thus, the font information and the icons to be added are added.
- steps S111 to S115 in Fig. 4 are the same as the operations in steps S101 to S105 in Fig. 2 in the first embodiment, and thus the description thereof is omitted.
- step S113 in FIG. 4 if no vocabulary for determining attribute information is extracted in step S113 in FIG. 4 (NO in step S113 in FIG. 4), the entire sentence without attribute information is added. Output without attribute information (step S 118 in FIG. 4).
- the assigning means 25 refers to the expression dictionary 33 and assigns a font designation or icon corresponding to the attribute information to the sentence (step S 116 in FIG. 4).
- the output means 40 displays the text with fonts and icons on the screen (see FIG.
- the second embodiment of the present invention it is possible to express sentence attribute information even in an environment where voice output is not possible (not allowed).
- the first embodiment of the present invention corresponds to the first embodiment of the present invention described above, and includes a keyboard as the input means 10, a personal computer as the data processing means 20, and a magnetic disk as the storage means 30. Is realized with a configuration including a speaker as the output means 40.
- the analysis means 21 and the attribute information determiner are included in the magnetic disk. (First attribute information determination means) 22, attribute information addition language unit selection means (second attribute information determination means) 23, synthesis means 24, held by a computer program that functions a personal computer (central processing unit) It has been.
- the analyzing means 21 performs morphological analysis and syntax analysis with reference to the dictionary 31, and divides the linguistic expression into a plurality of language units 1 to n.
- the language expression refers to everything expressed in a language.
- the language unit is a unit such as a paragraph, a section, a chapter, or a sentence that constitutes a sentence, a unit such as a word, a phrase, or a phrase that constitutes a sentence, and a newspaper or a web page. It also refers to each single sentence when it consists of multiple sentences.
- the analysis technology is a publicly known technology, so the explanation is omitted.
- the attribute information determining means (first attribute information determining means) 22 refers to the dictionary 31 to search whether or not the vocabulary for determining the attribute information is included in the language units 1 to n.
- the attribute information refers to emotions such as emotions, utterance styles such as readings and DJs.
- the vocabulary includes emoticons (face marks), symbols, and fixed expressions.
- the fixed expressions include fixed phrases such as proverbs.
- FIG. 5 shows an example of correspondence between vocabulary included in the dictionary 31 and attribute information.
- the attribute information of the language unit is determined as “joy”.
- the attribute information of the language unit determined by the attribute information determination means (first attribute information determination means) 22 is converted into the adjacent language unit. Decide whether to give to. For example, if the vocabulary “I am happy” is extracted from the d-th language unit and the attribute information “joy” of the d-th language unit has been determined, whether the attribute information is given to the d—first language unit Please, iteratively decide whether to grant d + 1st language unit! /
- the vocabulary power included in the language unit is also related to the relationship between the language unit and the language unit (connection (Relationship) is analyzed and determined based on the analysis result.
- the analysis (judgment) of the relationship between language units and language units (connection relationship) can be done with at least one of the adjacent language units. It is done by using linguistic unit vocabulary such as conjuncts and conjunctions included, anaphoric references in adjacent language units, relations between words, changes in subject matter, changes in sentence ending expressions, and so on.
- FIG. 6 is a diagram for explaining the concept when analyzing the relationship (connection relationship) of language units “sentences” extracted from “sentences” that also have a plurality of sentence powers as language expressions.
- connection relationship between language units is (1) relationship, (2) no relationship, (3) independent sentence (language unit), (4) adjacent sentence ( Different attribute information is determined for each (language unit), and can be classified into four main categories.
- connection relations (1) to (4) will be described in detail with examples with reference to FIG.
- Sentences are related to sentences when, for example, the topic or tone does not change between the sentences before and after, and the reason or supplement is stated.
- Vocabularies that are determined not to change the topic include conjunctions and conjunction particles.
- the conjunctive conjunction “So”, “There”, the cumulative conjunction “Nao”, “And”, the parallel conjunction “M”, “And”, and the explanation 'Supplemental conjunction “that is”, “Because”
- conjunctions such as “for example” and “from” can be given at the end of the sentence.
- the range in which there is a relationship between words should also be analyzed as (1) a relationship.
- the range related to a word is a range where the same word is used repeatedly, such as “Buy” and “Purchase”. Concluding like an "elementary school student” Tsuki strong! Words are used!
- the rule for assigning attribute information is determined, and attribute information of adjacent sentences is set one by one. Instead of (iteratively) determining the attribute information, it is also possible to set the attribute information in a batch based on the relative position to the sentence containing the vocabulary that determines the attribute information.
- the rules for assigning the attribute information include the following: “Assign the same attribute information to the three sentences before and after the sentence that includes the vocabulary that determines the attribute information”, ”And“ assuming there is a relationship until a sentence with different attribute information appears ”
- a vocabulary that determines that the topic has changed includes a conjunction.
- the conjunctive conjunctions “Tokoro”, “Now”, the conjunctive conjunctions “but”, “but”, the contrasting choices “or”, “or”, etc. can be mentioned.
- the change in tone appears prominently at the end of the sentence. For example, if the final particle or auxiliary verb changes, such as “It was fun, I ’ll see you again.” If there is a plan to respond to this question, please tell me? This may be the case where the type of sentence such as a command sentence has changed. However, the change in the expression at the end of the sentence has less impact than others. . For example, if the subject matter does not change even if the sentence end expression changes, (1) it is often determined that there is a relationship.
- greetings and quoted parts of e-mails that begin with “>” should be analyzed as (3) independent sentences (language units).
- independent sentences language units
- an independent sentence for example, a greeting sentence such as "Good morning” or "Thank you for taking care of” is a composite dictionary.
- the prosody is often assigned to the text, so it can be used as it is, and it is sufficient to read out the quoted part in the standard prosody.
- the attribute information of each sentence should be retained without being affected by each other's attribute information.
- the topic or word tone does not change, such as “I felt sad.
- the synthesizing means 24 refers to the synthesizing dictionary 32, and if the attribute information determining means (first attribute information determining means) 22 does not extract any vocabulary for determining attribute information, A synthetic speech is generated with a standard prosody without attribute information as a whole, and output to the output means 40. Also, attribute information determination means (first attribute information determination means) 22 determines sentence attribute information, and attribute information addition language unit selection means (second attribute information determination means) 23 determines the range of sentences to which each attribute information is assigned. If determined, a prosody corresponding to the determined attribute information is added to generate a synthesized speech and output it to the output means 40.
- the operation of the present embodiment having the above configuration will be described in detail with reference to the correspondence example between the vocabulary and attribute information in FIG. 5 and the example sentence in FIG.
- FIG. 8 shows an example in which the above sentence is divided into six sentences (language units) by the analysis means 21 activated on the personal computer.
- Attribute information determination means (first attribute information determination means) 22 activated on the personal 'computer includes a vocabulary for determining attribute information in the above six sentences with reference to the dictionary 31. Search whether or not. Referring to FIG. 5, “!” And “( ⁇ .” Are “joy”, “warm” and “-me” are “anger” ⁇ Decision means (first attribute information decision means) 22, as shown in Fig. 9, the attribute information of the first sentence is "joy”, the attribute information of the fourth sentence is "anger”, Decide information as “joy”.
- attribute information is added by the attribute information addition language unit selection means (second attribute information determination means) 23 activated on the personal computer.
- the attribute information addition language unit selection means (second attribute information determination means) 23 determines whether or not to give the attribute information of “joy” of the first sentence also to the second sentence. However, since the first sentence is a greeting sentence “Ohayo ⁇ ” ((3) Independence), the standard prosody is used, and the attribute information of “joy” is discarded. Also, no attribute information is given.
- the attribute information addition language unit selection means (second attribute information determination means) 23 determines whether or not the attribute information of "anger” in the fourth sentence is also given to the third and fifth sentences. .
- the 5th sentence starts with a conjunctive conjunction, which is “by the way”, so it is judged that the topic has changed here ((2) unrelated). Do not give the attribute information of “anger”.
- the 4th and 3rd sentences there is no vocabulary that determines whether the topic or tone has changed from the 4th sentence in the 3rd sentence!
- the attribute information addition language unit selection means (second attribute information determination means) 23 determines whether or not the third sentence “anger” attribute information is also given to the second sentence.
- the attribute information addition language unit selection means (second attribute information determination means) 23 determines whether or not the third sentence “anger” attribute information is also given to the second sentence.
- the second sentence there is no vocabulary to determine whether the topic or tone has changed from the third sentence, but there is no vocabulary that determines attribute information different from “anger” ((1) relation), 3 Attach the same “anger” attribute information as the sentence.
- the attribute information addition language unit selection means (second attribute information determination means) 23 determines whether or not the sixth sentence “joy” attribute information is also given to the fifth sentence.
- “Accept” and “Examination” are related to the word, so it is decided to give the same attribute information ((1) relationship), and the 5th sentence also has the attribute of “joy” Give information.
- FIG. 10 shows a state in which attribute information is given to an adjacent sentence (language unit) by the attribute information addition language unit selection means (second attribute information determination means) 23 from the state of FIG. ! /
- the synthesizing means 24 activated on the personal computer refers to the synthesizing dictionary 32 and gives a prosody to the sentence with attribute information in FIG.
- the input text is finally read out in the output means 40 as follows.
- FIG. 11 shows an output result when the same text as FIG. 7 is assigned attribute information to each sentence using the speech synthesis system of Patent Document 2.
- the input text is read as follows.
- the range of sentences to which attribute information is added differs between the present embodiment and the prior art (Patent Document 2).
- the attribute information specific vocabulary is not included. In this way, the speaker's emotions in the second sentence (second sentence, third sentence, and fifth sentence) cannot be expressed.
- the process of spreading the attribute information before and after the sentence that does not include the attribute information specific vocabulary is performed as appropriate, it is possible to express how the emotion moves and not feel uncomfortable. The way of speaking is realized.
- emotion attribute information is added has been described above, but the present invention is also effective in the case of adding utterance style attribute information.
- An example in which utterance style attribute information is added is described below.
- the dictionary 31 is associated with attribute information “DJ tone” for the vocabulary “Let ’s go!”.
- the input sentence is, "Hello, everybody. Retsusu down in charge of is Hanako. Today's lesson is be a verb. Now, I'm cormorant! Including today's lesson” is assumed to be.
- the analysis means 21 the input sentence "Hello, everyone.”, “This is Hanako of lessons in charge.”, "Today's lesson is be a verb.”, "Come on, including today's lesson or Divide it into four sentences.
- the attribute information determination means (first attribute information determination means) 22 extracts the vocabulary “Saa! Let's!” To determine attribute information from the fourth sentence, and sets the attribute information of the fourth sentence to “DJ Key.
- the attribute information addition language unit selection means (second attribute information determination means) 23 determines whether or not the fourth sentence "DJ tone" attribute information is also given to the third sentence.
- the same attribute information is decided to be given because the word “lesson” is used repeatedly, and the attribute information of “DJ tone” is also given to the 3rd sentence.
- the attribute information addition language unit selection means (second attribute information determination means) 23 determines whether or not the third sentence "DJ tone" attribute information is also given to the second sentence. In the 3rd sentence and the 2nd sentence, it is decided to give the same attribute information because the word “lesson” is repeatedly used, and the attribute information of “DJ tone” is also given to the second sentence.
- the attribute information addition language unit selection means (second attribute information determination means) 23 determines whether or not the attribute information of the second sentence "DJ tone" is also given to the first sentence. However, since the first sentence is a greeting sentence, the standard prosody is used and no attribute information is given. As a result, the input sentence is finally read out by the output means 40 as follows.
- the first example is the operation until input sentence is analyzed, sentence attribute information is determined, and the range of sentences (language unit) to which attribute information is added is determined by the connection relation of the sentence (language unit). Since it is the same as that, description is abbreviate
- the expression adding means 25 activated on the personal computer is referred to the expression dictionary 33 and the expression information corresponding to the attribute information is displayed. Is granted.
- the expression information of the system pre-selected by the operator is given from the change of the font stored in the expression dictionary 33 in association with the attribute information, the icon display of symbols, figures, pictograms, etc. .
- FIG. 12 shows an example of correspondence between attribute information and expression information included in the expression dictionary 33.
- the above sentence is divided into six sentences, the attribute information of each sentence is determined, and until the range of sentences to which the attribute information is assigned is the same as in the first embodiment, input up to this point
- the attribute information is given to the text as follows.
- the expression assigning means 25 refers to the expression dictionary 33 and assigns information necessary for expressing the result by font change.
- the attribute information “joy” is associated with “pop”, and the attribute information “anger” is associated with “gothic”. Therefore, the above example sentences are each expressed in fonts corresponding to the attribute information as shown in FIG.
- icon display as expression information.
- the position where the icon is given is only the beginning and end of the language unit to which the attribute information is given as shown in FIG. 14, and the beginning of the language unit to which the attribute information is given as shown in FIG. Desirable to be able to choose.
- the degree of emphasis! / Can also be set in a stepwise manner by the above-described (1) to (3) V, shift method. For example, if the strength of a sentence containing a vocabulary that determines attribute information is 10, then the next sentence can be set in multiple steps, 5 for the next sentence and 3 for the next sentence.
- add strength is an optional item for attribute information addition processing so that the operator can select and set in advance.
- the present invention is not limited to these descriptions, and attribute information determined based on a dictionary is spread to other language units. It does not deviate from the gist of the present invention including an additional attribute information determining means Various modifications can be made within the range.
- the present invention has been described with reference to an example in which the present invention is applied to a speech synthesis system and a text display system, but the present invention can also be applied to other application systems.
- the present invention can be applied to uses such as a speech synthesis system that expresses attribute information such as sentence emotions and speech styles by sound, and a program for realizing the functions of the speech synthesizer by a computer.
- the present invention can also be applied to various text output systems such as a device having a display means for visually expressing the attribute information and a device for transmitting and receiving sentences.
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2008517872A JP5321058B2 (ja) | 2006-05-26 | 2007-05-23 | 情報付与システム、情報付与方法、情報付与プログラム及び情報付与プログラム記録媒体 |
US12/302,698 US8340956B2 (en) | 2006-05-26 | 2007-05-23 | Information provision system, information provision method, information provision program, and information provision program recording medium |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2006147096 | 2006-05-26 | ||
JP2006-147096 | 2006-05-26 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2007138944A1 true WO2007138944A1 (ja) | 2007-12-06 |
Family
ID=38778464
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2007/060490 WO2007138944A1 (ja) | 2006-05-26 | 2007-05-23 | 情報付与システム、情報付与方法、情報付与プログラム及び情報付与プログラム記録媒体 |
Country Status (3)
Country | Link |
---|---|
US (1) | US8340956B2 (ja) |
JP (1) | JP5321058B2 (ja) |
WO (1) | WO2007138944A1 (ja) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2217899A1 (en) * | 2007-12-12 | 2010-08-18 | Nokia Corporation | Methods, apparatuses, and computer program products for semantic media conversion from source data to audio/video data |
JP2015075993A (ja) * | 2013-10-10 | 2015-04-20 | 富士ゼロックス株式会社 | 情報処理装置及び情報処理プログラム |
WO2018235326A1 (ja) * | 2017-06-23 | 2018-12-27 | 大日本印刷株式会社 | コンピュータプログラム、フォント切替装置及びフォント切替方法 |
JP2019514131A (ja) * | 2016-05-09 | 2019-05-30 | ネイバー コーポレーションNAVER Corporation | 顔文字が共に提供される翻訳文提供方法、ユーザ端末、サーバ及びコンピュータプログラム |
JP2020012867A (ja) * | 2018-07-13 | 2020-01-23 | 日本電信電話株式会社 | 韻律制御装置、韻律制御方法及びプログラム |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012198277A (ja) * | 2011-03-18 | 2012-10-18 | Toshiba Corp | 文書読み上げ支援装置、文書読み上げ支援方法および文書読み上げ支援プログラム |
GB2501067B (en) * | 2012-03-30 | 2014-12-03 | Toshiba Kk | A text to speech system |
CN103543979A (zh) * | 2012-07-17 | 2014-01-29 | 联想(北京)有限公司 | 一种输出语音的方法、语音交互的方法及电子设备 |
GB2516965B (en) | 2013-08-08 | 2018-01-31 | Toshiba Res Europe Limited | Synthetic audiovisual storyteller |
US9361290B2 (en) | 2014-01-18 | 2016-06-07 | Christopher Bayan Bruss | System and methodology for assessing and predicting linguistic and non-linguistic events and for providing decision support |
SG11201708285RA (en) * | 2014-09-09 | 2017-11-29 | Botanic Tech Inc | Systems and methods for cinematic direction and dynamic character control via natural language output |
WO2019246239A1 (en) | 2018-06-19 | 2019-12-26 | Ellipsis Health, Inc. | Systems and methods for mental health assessment |
US20190385711A1 (en) | 2018-06-19 | 2019-12-19 | Ellipsis Health, Inc. | Systems and methods for mental health assessment |
CN114446323B (zh) * | 2022-01-25 | 2023-03-10 | 电子科技大学 | 一种动态多维度的音乐情感分析方法及*** |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05324708A (ja) * | 1992-05-20 | 1993-12-07 | Agency Of Ind Science & Technol | 文脈構造解析装置 |
JPH08123812A (ja) * | 1994-10-21 | 1996-05-17 | Nippon Telegr & Teleph Corp <Ntt> | 話題構造認識方法及び装置 |
JP2004259238A (ja) * | 2003-02-25 | 2004-09-16 | Kazuhiko Tsuda | 自然言語解析における感情理解システム |
JP2004272807A (ja) * | 2003-03-11 | 2004-09-30 | Matsushita Electric Ind Co Ltd | 文字列処理装置および文字列処理方法 |
JP2005222294A (ja) * | 2004-02-05 | 2005-08-18 | Seiko Epson Corp | 文章の感情認識装置及び文章の感情認識方法ならびにそのプログラム |
Family Cites Families (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4931934A (en) * | 1988-06-27 | 1990-06-05 | Snyder Thomas E | Method and system for measuring clarified intensity of emotion |
JPH04119467A (ja) * | 1990-09-10 | 1992-04-20 | Nippon Telegr & Teleph Corp <Ntt> | 自然言語翻訳方法 |
JPH05100692A (ja) | 1991-05-31 | 1993-04-23 | Oki Electric Ind Co Ltd | 音声合成装置 |
US5860064A (en) * | 1993-05-13 | 1999-01-12 | Apple Computer, Inc. | Method and apparatus for automatic generation of vocal emotion in a synthetic text-to-speech system |
JPH1078952A (ja) * | 1996-07-29 | 1998-03-24 | Internatl Business Mach Corp <Ibm> | 音声合成方法、音声合成装置、ハイパーテキストの制御方法及び制御装置 |
US5836771A (en) * | 1996-12-02 | 1998-11-17 | Ho; Chi Fai | Learning method and system based on questioning |
US6947893B1 (en) * | 1999-11-19 | 2005-09-20 | Nippon Telegraph & Telephone Corporation | Acoustic signal transmission with insertion signal for machine control |
JP2001209820A (ja) * | 2000-01-25 | 2001-08-03 | Nec Corp | 感情表出装置及びプログラムを記録した機械読み取り可能な記録媒体 |
US6963839B1 (en) * | 2000-11-03 | 2005-11-08 | At&T Corp. | System and method of controlling sound in a multi-media communication application |
US20020194006A1 (en) * | 2001-03-29 | 2002-12-19 | Koninklijke Philips Electronics N.V. | Text to visual speech system and method incorporating facial emotions |
JP2002304188A (ja) * | 2001-04-05 | 2002-10-18 | Sony Corp | 単語列出力装置および単語列出力方法、並びにプログラムおよび記録媒体 |
EP1256937B1 (en) * | 2001-05-11 | 2006-11-02 | Sony France S.A. | Emotion recognition method and device |
JP2002366186A (ja) * | 2001-06-11 | 2002-12-20 | Hitachi Ltd | 音声合成方法及びそれを実施する音声合成装置 |
US7853863B2 (en) * | 2001-12-12 | 2010-12-14 | Sony Corporation | Method for expressing emotion in a text message |
US7401020B2 (en) * | 2002-11-29 | 2008-07-15 | International Business Machines Corporation | Application of emotion-based intonation and prosody to speech in text-to-speech systems |
JP2003295882A (ja) * | 2002-04-02 | 2003-10-15 | Canon Inc | 音声合成用テキスト構造、音声合成方法、音声合成装置及びそのコンピュータ・プログラム |
GB0215123D0 (en) * | 2002-06-28 | 2002-08-07 | Ibm | Method and apparatus for preparing a document to be read by a text-to-speech-r eader |
US20040024822A1 (en) * | 2002-08-01 | 2004-02-05 | Werndorfer Scott M. | Apparatus and method for generating audio and graphical animations in an instant messaging environment |
AU2002950502A0 (en) * | 2002-07-31 | 2002-09-12 | E-Clips Intelligent Agent Technologies Pty Ltd | Animated messaging |
US7360151B1 (en) * | 2003-05-27 | 2008-04-15 | Walt Froloff | System and method for creating custom specific text and emotive content message response templates for textual communications |
US7434176B1 (en) * | 2003-08-25 | 2008-10-07 | Walt Froloff | System and method for encoding decoding parsing and translating emotive content in electronic communication |
JP2005135169A (ja) * | 2003-10-30 | 2005-05-26 | Nec Corp | 携帯端末およびデータ処理方法 |
JP4409279B2 (ja) | 2003-12-22 | 2010-02-03 | 株式会社日立製作所 | 音声合成装置及び音声合成プログラム |
EP1667031A3 (en) * | 2004-12-02 | 2009-01-14 | NEC Corporation | HTML-e-mail creation system |
JP5259050B2 (ja) * | 2005-03-30 | 2013-08-07 | 京セラ株式会社 | 音声合成機能付き文字情報表示装置、およびその音声合成方法、並びに音声合成プログラム |
US7720784B1 (en) * | 2005-08-30 | 2010-05-18 | Walt Froloff | Emotive intelligence applied in electronic devices and internet using emotion displacement quantification in pain and pleasure space |
US7983910B2 (en) * | 2006-03-03 | 2011-07-19 | International Business Machines Corporation | Communicating across voice and text channels with emotion preservation |
US20070266090A1 (en) * | 2006-04-11 | 2007-11-15 | Comverse, Ltd. | Emoticons in short messages |
-
2007
- 2007-05-23 WO PCT/JP2007/060490 patent/WO2007138944A1/ja active Search and Examination
- 2007-05-23 JP JP2008517872A patent/JP5321058B2/ja active Active
- 2007-05-23 US US12/302,698 patent/US8340956B2/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05324708A (ja) * | 1992-05-20 | 1993-12-07 | Agency Of Ind Science & Technol | 文脈構造解析装置 |
JPH08123812A (ja) * | 1994-10-21 | 1996-05-17 | Nippon Telegr & Teleph Corp <Ntt> | 話題構造認識方法及び装置 |
JP2004259238A (ja) * | 2003-02-25 | 2004-09-16 | Kazuhiko Tsuda | 自然言語解析における感情理解システム |
JP2004272807A (ja) * | 2003-03-11 | 2004-09-30 | Matsushita Electric Ind Co Ltd | 文字列処理装置および文字列処理方法 |
JP2005222294A (ja) * | 2004-02-05 | 2005-08-18 | Seiko Epson Corp | 文章の感情認識装置及び文章の感情認識方法ならびにそのプログラム |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2217899A1 (en) * | 2007-12-12 | 2010-08-18 | Nokia Corporation | Methods, apparatuses, and computer program products for semantic media conversion from source data to audio/video data |
JP2015075993A (ja) * | 2013-10-10 | 2015-04-20 | 富士ゼロックス株式会社 | 情報処理装置及び情報処理プログラム |
JP2019514131A (ja) * | 2016-05-09 | 2019-05-30 | ネイバー コーポレーションNAVER Corporation | 顔文字が共に提供される翻訳文提供方法、ユーザ端末、サーバ及びコンピュータプログラム |
WO2018235326A1 (ja) * | 2017-06-23 | 2018-12-27 | 大日本印刷株式会社 | コンピュータプログラム、フォント切替装置及びフォント切替方法 |
JPWO2018235326A1 (ja) * | 2017-06-23 | 2020-04-23 | 大日本印刷株式会社 | コンピュータプログラム、フォント切替装置及びフォント切替方法 |
JP2020012867A (ja) * | 2018-07-13 | 2020-01-23 | 日本電信電話株式会社 | 韻律制御装置、韻律制御方法及びプログラム |
JP7125599B2 (ja) | 2018-07-13 | 2022-08-25 | 日本電信電話株式会社 | 韻律制御装置、韻律制御方法及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
US20090287469A1 (en) | 2009-11-19 |
US8340956B2 (en) | 2012-12-25 |
JPWO2007138944A1 (ja) | 2009-10-01 |
JP5321058B2 (ja) | 2013-10-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5321058B2 (ja) | 情報付与システム、情報付与方法、情報付与プログラム及び情報付与プログラム記録媒体 | |
Taylor | Text-to-speech synthesis | |
US8498867B2 (en) | Systems and methods for selection and use of multiple characters for document narration | |
US8346557B2 (en) | Systems and methods document narration | |
KR101594057B1 (ko) | 텍스트 데이터의 처리 방법 및 장치 | |
Aylett et al. | Building and designing expressive speech synthesis | |
JP2007264284A (ja) | 感情付加装置、感情付加方法及び感情付加プログラム | |
JPWO2016002879A1 (ja) | 音声合成装置、音声合成方法およびプログラム | |
JP4964695B2 (ja) | 音声合成装置及び音声合成方法並びにプログラム | |
JP2006236037A (ja) | 音声対話コンテンツ作成方法、装置、プログラム、記録媒体 | |
JP2005215888A (ja) | テキスト文の表示装置 | |
Kehoe et al. | Designing help topics for use with text-to-speech | |
KR20080060909A (ko) | 문장 상태에 따른 음성을 합성하여 출력하는 방법 및 이를이용한 음성합성기 | |
JP4409279B2 (ja) | 音声合成装置及び音声合成プログラム | |
JP3578961B2 (ja) | 音声合成方法及び装置 | |
Trouvain et al. | Speech synthesis: text-to-speech conversion and artificial voices | |
JP6289950B2 (ja) | 読み上げ装置、読み上げ方法及びプログラム | |
JP3589972B2 (ja) | 音声合成装置 | |
JP2002268664A (ja) | 音声変換装置及びプログラム | |
JP2011180368A (ja) | 合成音声修正装置および合成音声修正方法 | |
JPH11296193A (ja) | 音声合成装置 | |
JP2002366175A (ja) | 音声コミュニケーション支援装置およびその方法 | |
JP2002108378A (ja) | 文書読み上げ装置 | |
JP2007122510A (ja) | 提示装置及び提示プログラム | |
JP2006302149A (ja) | 日本語入力装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 07743924 Country of ref document: EP Kind code of ref document: A1 |
|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2008517872 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 12302698 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 07743924 Country of ref document: EP Kind code of ref document: A1 |
|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) |