WO2016021937A1 - 문자 데이터의 내용을 문자 데이터 송신자의 음성으로 출력하는 방법 - Google Patents
문자 데이터의 내용을 문자 데이터 송신자의 음성으로 출력하는 방법 Download PDFInfo
- Publication number
- WO2016021937A1 WO2016021937A1 PCT/KR2015/008210 KR2015008210W WO2016021937A1 WO 2016021937 A1 WO2016021937 A1 WO 2016021937A1 KR 2015008210 W KR2015008210 W KR 2015008210W WO 2016021937 A1 WO2016021937 A1 WO 2016021937A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- voice
- data
- text data
- text
- database
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 79
- 230000005540 biological transmission Effects 0.000 claims abstract description 12
- 238000010276 construction Methods 0.000 claims description 29
- 239000000284 extract Substances 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 16
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000013075 data extraction Methods 0.000 claims description 6
- 238000010295 mobile communication Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000008451 emotion Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000238558 Eucarida Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
Images
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/18—Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/04—Protocols specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72475—User interfaces specially adapted for cordless or mobile telephones specially adapted for disabled users
- H04M1/72481—User interfaces specially adapted for cordless or mobile telephones specially adapted for disabled users for visually impaired users
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
- H04M1/72436—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for text messaging, e.g. short messaging services [SMS] or e-mails
Definitions
- the present invention relates to a technique for outputting text data, and more particularly, to a method of outputting text content of text data transmitted to a terminal to a sender's voice.
- the voice call and text message transmission and reception are made through a mobile communication terminal such as a mobile phone or a smart phone.
- the text message is generally output as text that can be visually recognized. That is, the terminal receiving the text message simply outputs the text message in a text format.
- the visually impaired person cannot grasp the contents of the text message, and it is sometimes difficult for the non-visually handicapped person to grasp the contents of the text message during activities such as work, exercise, and driving.
- textual messages are not easy to convey emotions or intimacy due to their limitations.
- a mobile communication terminal is widely used, and as the utilization thereof increases, a technique for stimulating the emotion of a terminal user using a mobile communication terminal is required.
- the present invention is conceived by recognizing the prior art as described above, and an object of the present invention is to enable the text content of text data to be output by the text data sender's voice.
- another object of the present invention is to continuously update the voice information for the text message sender using the voice signals transmitted and received during the voice call with the text message sender, so that the voice closer to the actual sender's voice is output as the call volume increases. To do so for other purposes.
- a method of outputting a text by voice comprising: outputting text through a communication terminal, the transmitting terminal transmitting the text data to the receiving terminal; And outputting, by the receiving terminal, text contents of the text data transmitted by the transmitting terminal to the voice of the text data sender.
- the method may further include establishing a voice database of voice data of the text data sender before the text data receiving step.
- the establishing of the voice database may include storing voice data of the text data sender and text data corresponding to the voice data in a matched state.
- the establishing of the voice database may include storing voice data of the text data sender and text data corresponding to the voice data by sentence, word and syllable.
- the establishing of the voice database may include constructing a voice database of voice data of the text data sender using voice data transmitted and received during a voice call using the transmitting terminal and the receiving terminal.
- the establishing of the voice database may be a step of being established as a voice call between the transmitting terminal and the receiving terminal is repeated.
- the establishing of the voice database may include: in the voice database, text data that does not exist in the pre-established voice database among text data corresponding to voice data constituting a voice call between the transmitting terminal and the receiving terminal.
- the voice data corresponding to the text data and the sentence, the word, and the syllable may be classified and matched and further stored.
- the constructing of the voice database may include: text data existing in a pre-built voice database, among text data corresponding to voice data constituting a voice call between the transmitting terminal and the receiving terminal;
- the voice data corresponding to the data may be updated and stored in a state in which the speech data and the sentence, the word, and the syllable are classified and matched.
- the method may further include quantifying a construction degree of the voice database established through the voice call between the transmitting terminal and the receiving terminal.
- the receiving terminal may further output a grade graded in the grading through the display unit.
- the outputting of the graded grade may output different visual information according to the predetermined grade.
- the quantifying may include quantifying the construction degree of the speech database for each text data sender by adding the stored speech data stored in the speech database and the number of sentences, words, and syllables of the text data.
- weights are assigned to the number of sentences, words and syllables of the voice data and the text data stored separately in the speech database and weighted to the number of sentences, words and syllables, respectively. It may be a step of quantifying the establishment degree of the voice database for each text data sender by summing the values.
- the weight given to the number of sentences may be greater than or equal to the weight given to the number of words, and the weight given to the number of words may be greater than or equal to the weight given to the number of syllables.
- the method may further comprise, before the step of outputting by voice, checking whether there is information in the voice database that matches the information of the text data sender; Extracting voice data corresponding to text data transmitted from the transmitting terminal based on the inquiry result of the querying step; And transmitting the voice data extracted in the extracting step to the receiving terminal.
- the extracting of the voice data may include extracting voice data of the text data sender stored in the voice database. It may be a step.
- the extracting of the voice data may include extracting a machine voice stored in the voice database. have.
- the method may further comprise the steps of querying whether there is information in the voice database that matches the information of the text data sender before outputting to the voice: from the voice database based on the inquiry result of the querying step. Extracting voice data corresponding to the transmitted text data; And transmitting the voice data extracted in the extracting step to a receiving terminal.
- the extracting of the voice data may include matching a sentence corresponding to a sentence included in the text data transmitted by the transmitting terminal.
- a sentence extracting step of extracting speech data from the speech database A word extraction step of extracting voice data matching a word corresponding to a word included in the text data transmitted from the transmitting terminal from a voice database; And a syllable extraction step of extracting speech data matching a syllable corresponding to a syllable included in the text data transmitted by the transmitting terminal from a speech database. It may include.
- the word extraction step is performed after the sentence extraction step.
- the sentence extraction step if the speech data extraction for the predetermined sentence is successfully performed, the word extraction step for the predetermined sentence is not performed, and the syllable extraction is performed.
- the step may be performed after the word extracting step.
- the syllable extraction step for the word may not be performed.
- the sentence extracting step, the word extracting step and the syllable extracting step may be repeatedly performed on two or more sentences included in the text data transmitted by the transmitting terminal.
- a system for outputting a text to a voice a communication network; A transmitting terminal for transmitting text data to a receiving terminal through the communication network; And a receiving terminal that outputs voice data of the text data sender that has transmitted the text data as voice data corresponding to the text data transmitted by the transmitting terminal through the communication network.
- the communication network may include a voice server for establishing a voice database for voice data of the text data sender.
- the voice server may match the voice data of the text data sender with the text data corresponding to the voice data and store the same in the voice database.
- the voice server may store voice data of the text data sender and text data corresponding to the voice data by sentence, word, and syllable.
- the voice server may construct a voice database of voice data of the text data sender using voice data transmitted and received during a voice call using the transmitting terminal and the receiving terminal.
- the voice server may establish the voice database whenever a voice call between the transmitting terminal and the receiving terminal is repeated.
- the voice server corresponds to text data not present in the voice database, among text data corresponding to voice data constituting a voice call between the transmitting terminal and the receiving terminal.
- the voice data may be further stored in a state in which the voice data is classified and matched by sentence, word, and syllable.
- the voice server corresponds to text data that does not exist in the voice database from text data existing in a built-up voice database among text data corresponding to voice data constituting a voice call between the transmitting terminal and the receiving terminal.
- the voice data may be updated and stored in a state in which the voice data is classified and matched by sentence, word, and syllable.
- the voice server may quantify a construction degree of a voice database established through a voice call between the transmitting terminal and the receiving terminal.
- the voice server may grade the degree of construction of the voice database to a predetermined grade according to the quantified value.
- the receiving terminal may output a grade graded to the predetermined grade through a display unit.
- the receiving terminal may output different visual information according to the predetermined class.
- the voice server may quantify the construction degree of the voice database for each text data sender by adding up the number of voice data stored in the voice database and the number of sentences, words and syllables of the text data.
- the voice server assigns weights to the number of sentences, words and syllables of the voice data and the text data stored separately in the voice database, and weights the number of sentences, words and syllables, respectively. Can be quantified by the sender of the text data.
- the weight given to the number of sentences may be greater than or equal to the weight given to the number of words, and the weight given to the number of words may be greater than or equal to the weight given to the number of syllables.
- the voice server receives the text data transmitted from the transmitting terminal, inquires whether there is information that matches the information of the text data sender in the voice database, and then, based on an inquiry result, the transmitting terminal from the voice database.
- the extracted voice data corresponding to the transmitted text data may be extracted and transmitted to the receiving terminal.
- the voice server may extract voice data of the text data sender stored in the voice database.
- the voice server may extract a machine voice stored in the voice database.
- the voice server receives the text data transmitted from the transmitting terminal, inquires whether there is information that matches the information of the text data sender in the voice database, and then, based on an inquiry result, the transmitting terminal from the voice database. Extract the voice data corresponding to the transmitted text data, and transmit the extracted voice data to the receiving terminal, wherein the voice server transmits the extracted voice data from the voice database to the text data transmitted by the transmitting terminal based on the inquiry result.
- the voice server transmits the extracted voice data from the voice database to the text data transmitted by the transmitting terminal based on the inquiry result.
- the voice server transmits the extracted voice data from the voice database to the text data transmitted by the transmitting terminal based on the inquiry result.
- the voice server when voice data corresponding to a sentence corresponding to a predetermined sentence included in the text data transmitted by the transmitting terminal exists in the voice database, the voice corresponding to the sentence corresponding to the predetermined sentence with respect to the predetermined sentence
- the predetermined word is matched to the word corresponding to the predetermined word. Only voice data can be extracted.
- the voice server may perform voice data extraction on two or more sentences included in the text data transmitted by the transmitting terminal.
- the receiving terminal when the transmitting terminal transmits the text data, the receiving terminal can output the contents of the text data transmitted by the transmitting terminal as well as the text.
- the contents of the text data can be output by the voice of the sender who transmitted the text data.
- a voice closer to the actual voice of the text message sender may be output as the call is repeated.
- the text message transmitted by the sender can be output as the sender's voice.
- FIG. 1 is a diagram showing a system for outputting a text to a voice according to an embodiment of the present invention.
- FIG. 2 is a diagram schematically showing a voice database according to an embodiment of the present invention.
- FIG. 3 is a flowchart illustrating a process of extracting voice data according to an embodiment of the present invention.
- FIG. 4 is a diagram exemplarily illustrating a process in which a receiving terminal outputs a sentence of a text message transmitted by a transmitting terminal as a voice using a system for converting a text into a voice according to an embodiment of the present invention.
- FIG. 5 is a flowchart schematically illustrating a method of outputting a text to a voice according to an embodiment of the present invention.
- FIG. 1 is a diagram showing a system for outputting a text to a voice according to an embodiment of the present invention.
- a system for outputting a text by voice includes a transmitting terminal 10, a receiving terminal 20, and a mobile communication network 30.
- the transmitting terminal 10 and the receiving terminal 20 are communication terminals capable of transmitting and receiving text data, and are communication terminals capable of voice calls.
- the communication terminal may be a smartphone or a tablet PC.
- the transmitting terminal 10 and the receiving terminal 20 is shown as a smart phone, a smart phone is an example, in which the transmitting terminal 10 and the receiving terminal 20 of the present invention are limited to a smart phone. It is not.
- the text data transmitted by the transmitting terminal 10 is data that can be displayed as text through the display unit of the receiving terminal 20. More specifically, the text data transmitted by the transmitting terminal 10 is data that is modulated by the transmitting terminal 10 and transmitted to the receiving terminal 20, and the data is received after being transmitted to the receiving terminal 20. The data is demodulated by the terminal 20 and displayed on the display unit as text.
- the character data may be a set of bits.
- the character when a user of the transmitting terminal 10, that is, a sender inputs and transmits a character to the transmitting terminal 10, the character is modulated into text data and then received through the mobile communication network 30. 20).
- the receiving terminal 20 may demodulate the received text data into text that can be visually recognized and display the text on the display unit. In addition, the receiving terminal 20 may output not only the received text data but also various visual information through the display unit.
- Receiving terminal 20 not only can output the text content of the text data transmitted by the transmitting terminal 10 as a character, but also the character of the text data transmitted by the transmitting terminal 10.
- the contents can be output by voice.
- the receiving terminal 20 may output the text content of the text data as the voice of the sender who transmitted the text data. That is, the receiving terminal 20 may output the text content of the text data as a voice of the user of the transmitting terminal 10.
- the receiving terminal 20 may be provided with a speaker to enable audio output.
- the reception terminal 20 may receive voice data corresponding to the text data from the outside in order to output the text content of the text data transmitted by the transmitting terminal 10 to the voice.
- the receiving terminal 20 may output voice data received from the outside through a speaker.
- the voice data is data that can be demodulated in the receiving terminal 20 and output through the speaker, and can be a set of bits.
- the receiving terminal 20 may demodulate the text data transmitted from the mobile communication network 30, and then output the text contents through the display unit, or demodulate the voice data transmitted from the mobile communication network 30, and then You can also output the signal through the speaker.
- the mobile communication network 30 may include a text server 200 and a voice server 100.
- the mobile communication network 30 may transmit and receive text data and voice data using the text server 200 and the voice server 100.
- the text server 200 may receive the text data from the transmitting terminal 10 and transmit the text data to the receiving terminal 20.
- the text server 200 may include a text database 210 that stores text data received from the transmitting terminal 10.
- the voice server 100 includes a voice database 110 stored in a state where text data and voice data corresponding to the text data are matched.
- the voice database 110 is data stored in a state where text data and voice data are matched for each speaker.
- the text database 110 may store text data and voice data matched with each other by sentence, word, and / or syllable.
- the voice database 110 may store text data corresponding to "Hello, how are you?" And voice data corresponding thereto.
- the voice database 110 may store two sentences, "Hello?" And “How are you,” with text data and corresponding voice data matched, and "Hi” "," “Well,” “breaking” words, each of the words for each word and the corresponding voice data may be stored in a matching state, "in”, “good”, “ha”, Character data for each syllable and its equivalent, broken into syllables “three", “yo", “yo”, “ism”, “well”, “ji”, "my”, “poetry”, and “jo”
- the voice data may be stored in a matched state. Such information may be stored in the voice database 110 for each speaker.
- FIG. 2 is a diagram schematically showing a voice database 110 according to an embodiment of the present invention.
- text data and voice data are stored in matched state for each speaker. That is, in the voice database 110 according to an embodiment of the present invention, the text data and the voice data are stored in a matched state, but the text data and the voice data may be stored in the state classified by the speaker.
- the voice database 110 not only the text data and the corresponding voice data are divided and stored for each speaker, but also for each speaker, each sentence, each word, and each syllable are divided. Text data and voice data are stored.
- the voice database 110 may be constructed from a call made between the transmitting terminal 10 and the receiving terminal 20. That is, the voice database 110 may be constructed using voice data extracted from a call made between the transmitting terminal 10 and the receiving terminal 20.
- the voice server 100 may extract voice data constituting a call made between the transmitting terminal 10 and the receiving terminal 20.
- the voice server 100 may extract voice data constituting the call in real time or after the call ends.
- the voice server 100 may store voice data constituting a call for each sentence, each word, and each syllable according to a speaker.
- the voice server 100 may extract text data corresponding to the voice data from the voice data.
- the voice server 100 is a text of each sentence, word, syllable from the speech data "Hello? How are you?" You can extract the data.
- the text extraction from the voice data may be performed through a known voice recognition technology.
- the text extraction from the speech data may be performed through text extraction for all syllables of the speech data through speech recognition in syllable units.
- text data extraction for all syllables is performed, the speech data and the text data are matched for each syllable, the speech data and the text data are matched for each word, and then the speech data and the text data are matched for each sentence.
- a voice database 110 in which text data and voice data are matched for each word, word, and sentence may be constructed.
- the voice server 100 may establish a voice database 110 whenever a voice call between the transmitting terminal 10 and the receiving terminal 20 is repeated. That is, the voice server 100 may update the voice database 110 whenever a voice call between the transmitting terminal 10 and the receiving terminal 20 is repeated.
- the voice server 100 searches whether the voice data constituting the call exists in the pre-established voice database 110 and then, if the voice data constituting the call does not exist in the pre-built voice database 110.
- the voice data may be stored by matching text data corresponding to the voice data. In this case, the voice data may be stored in a state in which the text data is matched by syllable, word, and sentence.
- the voice server 100 may maintain voice data existing in the pre-built voice database 110, or the pre-built voice.
- the voice data existing in the database 110 may be updated with the latest data.
- the voice server 100 may update the voice database 110 in a manner of updating the pre-built voice database 110.
- the voice database 110 is updated as the number of calls between the transmitting terminal 10 and the receiving terminal 20 increases, so that voice information regarding the speaker of the transmitting terminal 10 may be gradually supplemented. That is, as the amount of communication between the transmitting terminal 10 and the receiving terminal 20 increases, voice data may become closer to the actual voice of the text speaker. This is because a larger number of voice data for syllables can express various characters as voices, and a larger number of voice data for words or sentences can output a voice closer to the actual voice.
- the voice server 100 may quantify the construction degree of the voice database 110 established through the voice call between the transmitting terminal 10 and the receiving terminal 20. That is, the degree to which the voice database 110 is constructed may be quantitatively evaluated according to a predetermined criterion.
- the quantitatively evaluated values may be classified into predetermined grades. That is, the voice server 100 may grade the construction degree of the voice database 110 to a predetermined grade according to a value in which the construction degree of the voice database 110 is quantified.
- the quantified value and / or the grade according to the quantified value by the voice server 100 may be stored in the voice database 110 or a separate storage medium, and transmitted to the receiving terminal 20.
- the receiving terminal 20 may receive a grade according to the quantified value and / or quantified value from the voice server 100 and output different visual information for each predetermined grade. For example, assuming that the construction degree of the voice database 110 is divided into five grades, the reception terminal 20 may output five asterisks ( ⁇ ) through the display unit in the case of the first grade. In case of class 2, 4 stars can be printed. In case of class 3, 3 stars, 4 stars can be 2 stars, and 5 stars can be 1 star.
- the visual information represented by an asterisk ( ⁇ ) is just an example, and the construction degree of the voice database 110 may be displayed through the display unit through various visual information.
- the weighted values may be summed to quantify the construction degree of the voice database 110.
- the construction degree of the voice database 110 may be quantified as 1,000 * a + 10,000 * b + 100,000 * c.
- weights assigned to the number of sentences, the number of words and the number of syllables, respectively may be given as follows in consideration of the completeness of the sentence. That is, the weight given to the number of sentences is greater than or equal to the weight given to the number of words, and the weight given to the number of words is preferably set to be greater than or equal to the weight given to the number of syllables (that is, , A ⁇ b ⁇ c) in the above example.
- the voice server 100 may inquire voice data corresponding to text data received from the outside from the voice database 110. In this case, the voice server 100 may query voice data corresponding to text data received from the outside for each speaker. The voice server 100 may extract voice data corresponding to the text data from the voice database 110 and transmit the extracted voice data to the receiving terminal 20. For example, when a person A transmits text data to the receiving terminal 20 using the transmitting terminal 10, the voice server 100 transmits information about the speaker A from the voice database 110. By inquiring, voice data for the A speaker can be extracted, and the extracted voice data of A can be transmitted to the receiving terminal 20.
- the voice server 100 may query voice data corresponding to text data received from the outside by sentence, word, and syllable.
- the voice server 100 may query text data in the order of sentences, words, and syllables.
- FIG. 3 is a flowchart illustrating a process of extracting voice data according to an embodiment of the present invention.
- the voice server 100 extracts voice data from the voice database 110 through the following process.
- the voice server 100 receives text data from the outside (S301). For example, as illustrated in FIG. 1, the voice server 100 may receive text data from the text server 200.
- the voice server 100 inquires whether information on the person who has received the received text data exists in the voice database 110 (S303). As a result of the inquiry of the voice server 100, if information on the sender of the text data is stored in the voice database 110, the process of extracting the sender's voice data corresponding to the text data is performed. A process of converting into machine voice is performed (S315).
- the voice server 100 when the search result of the voice server 100 stores the information about the text data sender in the voice database 110, the voice server 100 indicates that a sentence corresponding to a sentence of the text data is a voice database ( In step 110, it is checked whether it exists.
- the voice server 100 extracts voice data (sentence) matching the sentence of text data from the voice database 110 (S307).
- the voice server 100 inquires whether a word corresponding to a word of the text data exists in the voice database 110 ( S309).
- the voice server 100 When the word corresponding to the word of the text data exists in the voice database 110, the voice server 100 extracts the voice data (word) matching the word of the text data from the voice database 110 (S311). On the contrary, when the word corresponding to the word of the text data does not exist in the voice database 110, the voice server 100 extracts the voice data (syllable) matching the syllable of the text data (S313).
- the voice server 100 may extract the voice data of all the text data by repeating the above-described processes S305 to S313 for each sentence of the text data.
- the voice server 100 transmits the extracted voice data to the receiving terminal 20 so that the receiving terminal 20 can output a text to the sender's voice.
- the voice server 100 receives a message to the receiving terminal 20 that the voice conversion cannot be performed because the voice data is insufficient.
- the text data may be converted into pre-stored machine voices and transmitted to the receiving terminal 20.
- the voice server 100 may convert only the syllables that lack voice data into machine voices, or convert the entire sentence into machine voices, and perform voice conversion on insufficient syllables. You may not.
- the machine voice may be stored in the voice database 110 like voice data of each sender, and the voice data of various known syllables, words, and sentences is stored in the voice database 110 in a state of matching with the text data. There may be.
- the text data may be converted into a pre-stored machine voice.
- the machine voice may be stored in the voice database 110 in advance.
- FIG. 4 is a diagram illustrating an example of a process in which a receiving terminal 20 outputs a sentence of a text message transmitted by the transmitting terminal 10 as a voice using a system for converting text into voice according to an embodiment of the present invention. It is a figure shown.
- a system for converting text into voice includes a transmitting terminal 10, a receiving terminal 20, and a mobile communication network 30.
- the mobile communication network 30 includes a text server 200 and a voice server 100, and the voice server 100 is provided with a voice database 110.
- the voice database 110 included in the voice server 100 is constructed not only with text data matched with voice data for each speaker, but also the text data and voice data are sentence-by-sentence and word-by-word. For each syllable, each syllable is constructed to match the voice data.
- FIG. 4 the example of FIG.
- the speech database 110 associated with the speaker A includes the phrase “hello” and the phrase “hello”, the phrase “well”, “no”, “hello”, “ha”
- Voice data matching the syllables "Three”, “Yo”, “Well”, “G”, “My”, “Poetry” and “Jo” are stored in the state of matching each sentence, word, syllable. have.
- the transmitting terminal 10 transmits a text message, "Hello, how are you?"
- the text data is transmitted to the text server 200, and the text server 200 receives the received text.
- the data is transmitted to the receiving terminal 20 and the voice server 100.
- the voice server 100 inquires whether the information of the sender A, which has transmitted the received text data, exists in the database. As assumed, since the information of A exists in the database, the voice server 100 performs sentence matching. That is, the voice server 100 inquires whether a sentence included in the received text data exists in the voice database 110. As assumed, since the first sentence "hello" exists in the voice database 110, the voice server 100 extracts the voice data (A voice_sentence1) matching "hello".
- the voice server 100 inquires whether the second sentence "Let's get along well" exists in the voice database 110. As assumed, since the voice database 110 does not have information corresponding to the sentence "Let's do well", the voice server 100 performs word matching. That is, the voice server 100 inquires whether a word included in the received text data exists in the voice database 110. As presupposed, the first sentence and the second word are present in the voice database 110 in the second sentence "Let's get along well", so that the voice server 100 matches the voice data (A voice_word 1) with "now". And voice data matching A and " well " However, since there is no voice data matching "stay” in the voice database 110, the voice server 100 performs syllable matching for the third word of the second sentence.
- the voice server 100 is A voice_syllable 8, A voice, which is voice data matching each of the syllables “ji”, “my”, “hour”, and “jo” that constitutes the third word "stay.” Extract syllable 9, syllable A syllable 10, and syllable A syllable 11.
- the method of outputting a text to a voice according to an embodiment of the present invention may be a method using a system for outputting the above-described text to a voice. That is, the subject of the method for outputting a text to a voice according to an embodiment of the present invention may be at least one of the components constituting the system described above.
- FIG. 5 is a flowchart schematically illustrating a method of outputting a text to a voice according to an embodiment of the present invention.
- a method of outputting a text to a voice according to an embodiment of the present invention may be performed according to each step shown.
- the method performs a step of constructing a voice database 110 in which text data and voice data match for each speaker (S510).
- the voice data may be stored in the state of matching the text data by sentence, word, and syllable for each speaker.
- the voice database 110 may be constructed by various methods.
- the voice database 110 may be constructed using voice data transmitted during a voice call made through the receiving terminal 20 and the transmitting terminal 10.
- the transmitting terminal 10 transmits the text data to the receiving terminal 20 (S520).
- the text data transmitted by the transmitting terminal 10 may be transmitted to the receiving terminal 20 through the text server 200 and may be transmitted to the voice server 100 through the text server 200.
- the voice server 100 inquires whether the information about the sender or the transmission terminal 10 which transmitted the text data transmitted by the transmission terminal 10 exists in the voice database 110. If the information about the sender who transmitted the text data exists in the voice database 110, the voice server 100 extracts the voice data matching the text data from the voice database 110 (S530). Preferably, the voice server 100 extracts the voice data close to the actual speaker's voice by sequentially inquiring voice data matching the text data by sentence, word, and syllable.
- the voice server 100 transmits the voice data matching the text data to the receiving terminal 20.
- the reception terminal 20 outputs voice data matching the text data through the speaker (S540).
- the receiving terminal 20 may output a voice corresponding to the text data as the voice of the person who transmitted the text data.
- the reception terminal 20 may output the text through the speaker while outputting the text through the display unit.
- the receiving terminal 20 has a button or icon for selecting whether to output the voice, the receiving terminal 20 may be configured to output the voice when the button is pressed or the icon is selected.
- the reception terminal 20 may output visual information corresponding to a grade indicating the construction degree of the voice database 110 through the display unit, and show the construction degree of the voice database 110 to the user of the reception terminal 20.
- the user of the reception terminal 20 can intuitively grasp the construction degree of the voice database 110 through the time information indicating the construction degree of the voice database 110.
- the user of the reception terminal 20 can indirectly grasp the degree of exchange through a voice call with the user of the transmission terminal 10 through the construction degree of the voice database 110. Therefore, it is possible to induce a voice call between the user of the receiving terminal 20 and the user of the transmitting terminal 10.
- the voice information of the speaker of the transmitting terminal 10, which is databased by the above method, may be used not only for the text data transmitted from the transmitting terminal 10 but also for conversion of any other text data.
- the reception terminal 20 may output a book, a document, or the like stored in the reception terminal 20 as a speaker's voice of the transmission terminal 10 having a database.
- the reception terminal 20 may output a song by the speaker's voice of the database-based transmission terminal 10.
- the voice output may be changed to the voice of the speaker of the database-typed transmission terminal 10.
- the response of Siri which is an application for iOS, may be changed to the voice of the speaker of the transmitting terminal 10.
- the user of the reception terminal 20 can feel as if he is actually talking to the talker of the transmission terminal 10, so that the communication terminal can be converted to a companion, like a companion animal.
- the above-described method may be implemented in a form that is programmed and stored in a computer-readable recording medium.
- the voice conversion and databaseization operation is described as being performed in the mobile communication network 30, but the present invention is not limited thereto. That is, the operation may be performed in the transmitting terminal 10 or the receiving terminal 20, some of which may be performed on a server of the mobile communication network 30, and some of them may be performed in the transmitting terminal 10 or the receiving terminal 20. ) May be performed.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
Abstract
Description
Claims (42)
- 통신 단말을 통해 음성을 출력하는 방법에 있어서,송신 단말이, 문자 데이터를 수신 단말로 전송하는 단계; 및상기 수신 단말이, 상기 송신 단말이 전송한 문자 데이터의 문자 내용을 상기 문자 데이터 송신자의 음성으로 출력하는 단계;를 포함하는 문자를 음성으로 출력하는 방법.
- 제 1 항에 있어서,상기 문자 데이터 수신 단계 이전에,상기 문자 데이터 송신자의 음성 데이터에 대한 음성 데이터베이스를 구축하는 단계;를 더 포함하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 2 항에 있어서,상기 음성 데이터베이스를 구축하는 단계는, 상기 문자 데이터 송신자의 음성 데이터와 상기 음성 데이터에 상응하는 문자 데이터를 매칭시킨 상태로 저장하는 단계인 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 3 항에 있어서,상기 음성 데이터베이스를 구축하는 단계는, 상기 문자 데이터 송신자의 음성 데이터와 상기 음성 데이터에 상응하는 문자 데이터를 문장별, 어절별 및 음절별로 구분하여 저장하는 단계인 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 4 항에 있어서,상기 음성 데이터베이스를 구축하는 단계는, 상기 송신 단말과 상기 수신 단말을 이용한 음성 통화 중 송수신된 음성 데이터를 이용하여 상기 문자 데이터 송신자의 음성 데이터에 대한 음성 데이터베이스를 구축하는 단계인 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 5 항에 있어서,상기 음성 데이터베이스를 구축하는 단계는, 상기 송신 단말과 상기 수신 단말 사이의 음성 통화가 반복됨에 따라 구축되는 단계인 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 6 항에 있어서,상기 음성 데이터베이스를 구축하는 단계는, 상기 송신 단말과 상기 수신 단말 사이의 음성 통화를 구성하는 음성 데이터에 상응하는 문자 데이터 중에서 기 구축된 음성 데이터베이스에 존재하지 않는 문자 데이터를 상기 음성 데이터베이스에 존재하지 않는 문자 데이터에 상응하는 음성 데이터와 문장별, 어절별 및 음절별로 구분하여 매칭시킨 상태로 더 저장하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 7 항에 있어서,상기 음성 데이터베이스를 구축하는 단계는, 상기 송신 단말과 상기 수신 단말 사이의 음성 통화를 구성하는 음성 데이터에 상응하는 문자 데이터 중에서 기 구축된 음성 데이터베이스에 존재하는 문자 데이터를 상기 음성 데이터베이스에 존재하지 않는 문자 데이터에 상응하는 음성 데이터와 문장별, 어절별 및 음절별로 구분하여 매칭시킨 상태로 갱신 저장하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 8 항에 있어서,상기 음성 데이터베이스를 구축하는 단계 이후에, 상기 송신 단말과 상기 수신 단말 사이의 음성 통화를 통해 구축된 음성 데이터베이스의 구축 정도를 정량화하는 단계;를 더 포함하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 9 항에 있어서,상기 정량화하는 단계 이후에, 상기 정량화하는 단계에서 정량화된 값에 따라 음성 데이터베이스의 구축 정도를 소정 등급으로 그레이딩하는 단계;를 더 포함하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 9 항에 있어서,상기 그레이딩하는 단계 이후에, 상기 수신 단말이, 디스플레이부를 통해 상기 그레이딩하는 단계에서 그레이딩된 등급을 출력하는 단계;를 더 포함하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 11 항에 있어서,상기 그레이딩된 등급을 출력하는 단계는, 상기 소정 등급에 따라 서로 다른 시각 정보를 출력하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 9 항에 있어서,상기 정량화하는 단계는, 상기 음성 데이터베이스에 구분하여 저장된 음성 데이터와 문자 데이터의 문장별, 어절별 및 음절별 개수를 합산하여 음성 데이터베이스의 구축 정도를 문자 데이터 송신자 별로 정량화하는 단계인 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 9 항에 있어서,상기 정량화하는 단계는, 상기 음성 데이터베이스에 구분하여 저장된 음성 데이터와 문자 데이터의 문장별, 어절별 및 음절별 개수에 각각 가중치를 부여하고, 문장별, 어절별 및 음절별 개수에 각각 가중치가 부여된 값을 합산하여 음성 데이터베이스의 구축 정도를 문자 데이터 송신자 별로 정량화하는 단계인 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 14 항에 있어서,상기 문장별 개수에 부여되는 가중치는, 상기 어절별 개수에 부여되는 가중치 보다 크거나 같고, 상기 어절별 개수에 부여되는 가중치는, 상기 음절별 개수에 부여되는 가중치보다 크거나 같은 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 2 항 내지 제 4 항 중 어느 한 항에 있어서,상기 음성으로 출력하는 단계 이전에,상기 음성 데이터베이스에서 상기 문자 데이터 송신자의 정보와 일치하는 정보가 존재하는지를 조회하는 단계;상기 조회하는 단계의 조회 결과를 기초로 음성 데이터베이스로부터 상기 송신 단말이 전송한 문자 데이터에 상응하는 음성 데이터를 추출하는 단계; 및상기 추출하는 단계에서 추출한 음성 데이터를 수신 단말로 전송하는 단계;를 더 포함하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 16 항에 있어서,상기 조회하는 단계의 조회 결과, 상기 음성 데이터베이스에 상기 문자 데이터 송신자의 정보와 일치하는 정보가 존재하는 경우, 상기 음성 데이터를 추출하는 단계는, 상기 음성 데이터베이스에 저장된 상기 문자 데이터 송신자의 음성 데이터를 추출하는 단계인 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 16 항에 있어서,상기 조회하는 단계의 조회 결과, 상기 음성 데이터베이스에 상기 문자 데이터 송신자의 정보와 일치하는 정보가 존재하지 않는 경우, 상기 음성 데이터를 추출하는 단계는, 상기 음성 데이터베이스에 저장된 기계 음성을 추출하는 단계인 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 4 항에 있어서,상기 음성으로 출력하는 단계 이전에,상기 음성 데이터베이스에서 상기 문자 데이터 송신자의 정보와 일치하는 정보가 존재하는지 조회하는 단계:상기 조회하는 단계의 조회 결과를 기초로 음성 데이터베이스로부터 상기 송신 단말이 전송한 문자 데이터에 상응하는 음성 데이터를 추출하는 단계; 및상기 추출하는 단계에서 추출한 음성 데이터를 수신 단말로 전송하는 단계;를 더 포함하고,상기 음성 데이터를 추출하는 단계는,상기 송신 단말이 전송한 문자 데이터에 포함된 문장과 상응하는 문장에 매칭되는 음성 데이터를 음성 데이터베이스로부터 추출하는 문장 추출단계;상기 송신 단말이 전송한 문자 데이터에 포함된 어절과 상응하는 어절에 매칭되는 음성 데이터를 음성 데이터베이스로부터 추출하는 어절 추출단계; 및상기 송신 단말이 전송한 문자 데이터에 포함된 음절과 상응하는 음절에 매칭되는 음성 데이터를 음성 데이터베이스로부터 추출하는 음절 추출단계;를 포함하는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 19 항에 있어서,상기 어절 추출단계는, 상기 문장 추출단계 이후에 수행되되,상기 문장 추출단계에서, 소정 문장에 대한 음성 데이터 추출이 성공적으로 수행되면, 상기 소정 문장에 대한 어절 추출단계는 수행되지 않고,상기 음절 추출단계는, 상기 어절 추출단계 이후에 수행되되,상기 어절 추출단계에서, 소정 어절에 대한 음성 데이터 추출이 성공적으로 수행되면, 상기 소정 어절에 대한 음절 추출단계는 수행되지 않는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 제 20 항에 있어서,상기 문장 추출단계, 상기 어절 추출단계 및 상기 음절 추출단계는, 상기 송신 단말이 전송한 문자 데이터에 포함된 2 이상의 문장에 대해 반복적으로 수행되는 것을 특징으로 하는 문자를 음성으로 출력하는 방법.
- 통신망;상기 통신망을 통해 문자 데이터를 수신 단말로 전송하는 송신 단말; 및상기 통신망을 통해 상기 송신 단말이 전송한 문자 데이터에 상응하는 음성 데이터로서, 상기 문자 데이터를 전송한 문자 데이터 송신자의 음성 데이터를 출력하는 수신 단말;을 포함하는 문자를 음성으로 출력하는 시스템.
- 제 22 항에 있어서,상기 통신망은, 상기 문자 데이터 송신자의 음성 데이터에 대한 음성 데이터베이스를 구축하는 음성 서버를 구비하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 23 항에 있어서,상기 음성 서버는, 상기 문자 데이터 송신자의 음성 데이터와 상기 음성 데이터에 상응하는 문자 데이터를 매칭시켜 상기 음성 데이터베이스에 저장하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 24 항에 있어서,상기 음성 서버는, 상기 문자 데이터 송신자의 음성 데이터와 상기 음성 데이터에 상응하는 문자 데이터를 문장별, 어절별 및 음절별로 구분하여 저장하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 25 항에 있어서,상기 음성 서버는, 상기 송신 단말과 상기 수신 단말을 이용한 음성 통화 중 송수신된 음성 데이터를 이용하여 상기 문자 데이터 송신자의 음성 데이터에 대한 음성 데이터베이스를 구축하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 26 항에 있어서,상기 음성 서버는, 상기 송신 단말과 상기 수신 단말 사이의 음성 통화가 반복될 때 마다 상기 음성 데이터베이스를 구축하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 27 항에 있어서,상기 음성 서버는, 상기 송신 단말과 상기 수신 단말 사이의 음성 통화를 구성하는 음성 데이터에 상응하는 문자 데이터 중에서 기 구축된 음성 데이터베이스에 존재하지 않는 문자 데이터를 상기 음성 데이터베이스에 존재하지 않는 문자 데이터에 상응하는 음성 데이터와 문장별, 어절별 및 음절별로 구분하여 매칭시킨 상태로 더 저장하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 28 항에 있어서,상기 음성 서버는, 상기 송신 단말과 상기 수신 단말 사이의 음성 통화를 구성하는 음성 데이터에 상응하는 문자 데이터 중에서 기 구축된 음성 데이터베이스에 존재하는 문자 데이터를 상기 음성 데이터베이스에 존재하지 않는 문자 데이터에 상응하는 음성 데이터와 문장별, 어절별 및 음절별로 구분하여 매칭시킨 상태로 갱신 저장하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 29 항에 있어서,상기 음성 서버는, 상기 송신 단말과 상기 수신 단말 사이의 음성 통화를 통해 구축된 음성 데이터베이스의 구축 정도를 정량화하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 30 항에 있어서,상기 음성 서버는, 상기 정량화된 값에 따라 음성 데이터베이스의 구축 정도를 소정 등급으로 그레이딩하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 30 항에 있어서,상기 수신 단말은, 상기 소정 등급으로 그레이딩된 등급을 디스플레이부를 통해 출력하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 32 항에 있어서,상기 수신 단말은, 상기 소정 등급에 따라 서로 다른 시각 정보를 출력하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 30 항에 있어서,상기 음성 서버는, 상기 음성 데이터베이스에 구분하여 저장된 음성 데이터와 문자 데이터의 문장별, 어절별 및 음절별 개수를 합산하여 음성 데이터베이스의 구축 정도를 문자 데이터 송신자 별로 정량화하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 30 항에 있어서,상기 음성 서버는, 상기 음성 데이터베이스에 구분하여 저장된 음성 데이터와 문자 데이터의 문장별, 어절별 및 음절별 개수에 각각 가중치를 부여하고, 문장별, 어절별 및 음절별 개수에 각각 가중치가 부여된 값을 합산하여 음성 데이터베이스의 구축 정도를 문자 데이터 송신자 별로 정량화하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 35 항에 있어서,상기 문장별 개수에 부여되는 가중치는, 상기 어절별 개수에 부여되는 가중치 보다 크거나 같고, 상기 어절별 개수에 부여되는 가중치는, 상기 음절별 개수에 부여되는 가중치보다 크거나 같은 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 23 항 내지 제 25 항 중 어느 한 항에 있어서,상기 음성 서버는, 상기 송신 단말이 전송한 문자 데이터를 수신하고, 상기 음성 데이터베이스에서 상기 문자 데이터 송신자의 정보와 일치하는 정보가 존재하는지 조회한 다음, 조회 결과를 기초로 상기 음성 데이터베이스로부터 상기 송신 단말이 전송한 문자 데이터에 상응하는 음성 데이터를 추출하여, 추출한 상기 음성 데이터를 상기 수신 단말로 전송하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 37 항에 있어서,상기 조회 결과, 상기 음성 데이터베이스에 상기 문자 데이터 송신자의 정보와 일치하는 정보가 존재하는 경우, 상기 음성 서버는, 상기 음성 데이터베이스에 저장된 상기 문자 데이터 송신자의 음성 데이터를 추출하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 37 항에 있어서,상기 조회 결과, 상기 음성 데이터베이스에 상기 문자 데이터 송신자의 정보와 일치하는 정보가 존재하지 않는 경우, 상기 음성 서버는, 상기 음성 데이터베이스에 저장된 기계 음성을 추출하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 36 항에 있어서,상기 음성 서버는, 상기 송신 단말이 전송한 문자 데이터를 수신하고, 상기 음성 데이터베이스에서 상기 문자 데이터 송신자의 정보와 일치하는 정보가 존재하는지 조회한 다음, 조회 결과를 기초로 상기 음성 데이터베이스로부터 상기 송신 단말이 전송한 문자 데이터에 상응하는 음성 데이터를 추출하여, 추출한 상기 음성 데이터를 상기 수신 단말로 전송하되,상기 음성 서버는, 상기 조회 결과를 기초로 상기 음성 데이터베이스로부터 상기 송신 단말이 전송한 문자 데이터에 상응하는 음성 데이터를 추출함에 있어서, 상기 송신 단말이 전송한 문자 데이터에 포함된 문자 내용을 상기 음성 데이터베이스로부터 조회하여, 상기 송신 단말이 전송한 문자 데이터에 포함된 문장과 상응하는 문장에 매칭되는 음성 데이터, 상기 송신 단말이 전송한 문자 데이터에 포함된 어절과 상응하는 어절에 매칭되는 음성 데이터 및 상기 송신 단말이 전송한 문자 데이터에 포함된 음절과 상응하는 음절에 매칭되는 음성 데이터 중 적어도 하나를 추출하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 40 항에 있어서,상기 음성 서버는, 상기 송신 단말이 전송한 문자 데이터에 포함된 소정 문장과 상응하는 문장에 매칭되는 음성 데이터가 상기 음성 데이터베이스에 존재할 경우, 상기 소정 문장에 대해서는 상기 소정 문정과 상응하는 문장에 매칭되는 음성 데이터만 추출하고, 상기 송신 단말이 전송한 문자 데이터에 포함된 소정 어절과 상응하는 어절에 매칭되는 음성 데이터가 상기 음성 데이터베이스에 존재할 경우, 상기 소정 어절에 대해서는 상기 소정 어절과 상응하는 어절에 매칭되는 음성 데이터만 추출하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
- 제 41 항에 있어서,상기 음성 서버는, 상기 송신 단말이 전송한 문자 데이터에 포함된 2 이상의 문장에 대해 음성 데이터 추출을 수행하는 것을 특징으로 하는 문자를 음성으로 출력하는 시스템.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201580001904.9A CN105556999A (zh) | 2014-08-06 | 2015-08-05 | 将文本数据的内容输出成发送方语音的方法 |
US14/913,882 US9812121B2 (en) | 2014-08-06 | 2015-08-05 | Method of converting a text to a voice and outputting via a communications terminal |
EP15830674.6A EP3035718B1 (en) | 2014-08-06 | 2015-08-05 | Method for outputting text data content as voice of text data sender |
JP2016562268A JP6459080B2 (ja) | 2014-08-06 | 2015-08-05 | 文字データの内容を文字データ送信者の音声で出力する方法 |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2014-0101232 | 2014-08-06 | ||
KR20140101232 | 2014-08-06 | ||
KR1020150110072A KR101703214B1 (ko) | 2014-08-06 | 2015-08-04 | 문자 데이터의 내용을 문자 데이터 송신자의 음성으로 출력하는 방법 |
KR10-2015-0110072 | 2015-08-04 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016021937A1 true WO2016021937A1 (ko) | 2016-02-11 |
Family
ID=55448064
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2015/008210 WO2016021937A1 (ko) | 2014-08-06 | 2015-08-05 | 문자 데이터의 내용을 문자 데이터 송신자의 음성으로 출력하는 방법 |
Country Status (7)
Country | Link |
---|---|
US (1) | US9812121B2 (ko) |
EP (1) | EP3035718B1 (ko) |
JP (1) | JP6459080B2 (ko) |
KR (1) | KR101703214B1 (ko) |
CN (1) | CN105556999A (ko) |
TW (1) | TWI613641B (ko) |
WO (1) | WO2016021937A1 (ko) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105868419A (zh) * | 2016-06-02 | 2016-08-17 | 泉港区奇妙工业设计服务中心 | 一种童伴机器人搜索学习装置 |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101834546B1 (ko) * | 2013-08-28 | 2018-04-13 | 한국전자통신연구원 | 핸즈프리 자동 통역 서비스를 위한 단말 장치 및 핸즈프리 장치와, 핸즈프리 자동 통역 서비스 방법 |
EP3235218B1 (en) | 2014-12-11 | 2021-08-25 | Bitdefender IPR Management Ltd. | Systems and methods for securing network endpoints |
CN105096934B (zh) * | 2015-06-30 | 2019-02-12 | 百度在线网络技术(北京)有限公司 | 构建语音特征库的方法、语音合成方法、装置及设备 |
CN106603573A (zh) * | 2017-01-17 | 2017-04-26 | 国家电网公司 | 一种对非智能话机终端推送文本消息的装置和方法 |
US10147415B2 (en) * | 2017-02-02 | 2018-12-04 | Microsoft Technology Licensing, Llc | Artificially generated speech for a communication session |
TWI690814B (zh) * | 2017-12-15 | 2020-04-11 | 鴻海精密工業股份有限公司 | 文字資訊處理裝置及方法、電腦存儲介質及移動終端 |
US10726843B2 (en) * | 2017-12-20 | 2020-07-28 | Facebook, Inc. | Methods and systems for responding to inquiries based on social graph information |
US11398218B1 (en) * | 2018-04-26 | 2022-07-26 | United Services Automobile Association (Usaa) | Dynamic speech output configuration |
CN110634466B (zh) * | 2018-05-31 | 2024-03-15 | 微软技术许可有限责任公司 | 具有高感染力的tts处理技术 |
WO2020145428A1 (ko) * | 2019-01-08 | 2020-07-16 | 엘지전자 주식회사 | 단말기 |
CN109979440B (zh) * | 2019-03-13 | 2021-05-11 | 广州市网星信息技术有限公司 | 关键词样本确定方法、语音识别方法、装置、设备和介质 |
CN113096645A (zh) * | 2021-03-31 | 2021-07-09 | 闽江学院 | 电话语音的处理方法 |
CN113268981B (zh) * | 2021-05-27 | 2023-04-28 | 咪咕音乐有限公司 | 一种信息处理方法、装置及电子设备 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20010035173A (ko) * | 2001-01-10 | 2001-05-07 | 백종관 | 음성 합성 훈련 툴킷을 이용한 개인용 음성 합성기 및 그방법 |
KR20060061612A (ko) * | 2004-12-02 | 2006-06-08 | 주식회사 팬택 | 문자 메시지의 음성 안내 방법 및 그에 따른 저장매체 및그에 따른 통신 단말기 |
KR20070010360A (ko) * | 2005-07-18 | 2007-01-24 | 주식회사 팬택앤큐리텔 | 이동 통신 단말기의 음성 서비스 방법 |
KR20070049730A (ko) * | 2005-11-09 | 2007-05-14 | 엘지전자 주식회사 | 무선 통신망을 통한 음성 정보 서비스 방법 |
WO2008132758A2 (en) * | 2007-04-25 | 2008-11-06 | Kirusa, Inc. | Method and system for voice sms messaging |
Family Cites Families (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US706510A (en) * | 1901-11-27 | 1902-08-12 | Augustus Beitney | Art of manufacturing plate-ice. |
KR100259918B1 (ko) * | 1998-03-05 | 2000-06-15 | 윤종용 | 핸즈프리키트의 쇼트메시지 음성합성 장치 및 방법 |
JP2001350490A (ja) * | 2000-06-09 | 2001-12-21 | Fujitsu Ltd | テキスト音声変換装置及び方法 |
FI115868B (fi) * | 2000-06-30 | 2005-07-29 | Nokia Corp | Puhesynteesi |
KR20020091920A (ko) * | 2001-06-01 | 2002-12-11 | 엘지전자 주식회사 | 이동통신 단말기에서의 음성 및 문자 통화 장치 |
US7177801B2 (en) * | 2001-12-21 | 2007-02-13 | Texas Instruments Incorporated | Speech transfer over packet networks using very low digital data bandwidths |
JP3806030B2 (ja) * | 2001-12-28 | 2006-08-09 | キヤノン電子株式会社 | 情報処理装置及び方法 |
WO2004032112A1 (en) * | 2002-10-04 | 2004-04-15 | Koninklijke Philips Electronics N.V. | Speech synthesis apparatus with personalized speech segments |
US20040267531A1 (en) * | 2003-06-30 | 2004-12-30 | Whynot Stephen R. | Method and system for providing text-to-speech instant messaging |
US8666746B2 (en) * | 2004-05-13 | 2014-03-04 | At&T Intellectual Property Ii, L.P. | System and method for generating customized text-to-speech voices |
US7706510B2 (en) * | 2005-03-16 | 2010-04-27 | Research In Motion | System and method for personalized text-to-voice synthesis |
US7716052B2 (en) * | 2005-04-07 | 2010-05-11 | Nuance Communications, Inc. | Method, apparatus and computer program providing a multi-speaker database for concatenative text-to-speech synthesis |
US8224647B2 (en) * | 2005-10-03 | 2012-07-17 | Nuance Communications, Inc. | Text-to-speech user's voice cooperative server for instant messaging clients |
US7584104B2 (en) * | 2006-09-08 | 2009-09-01 | At&T Intellectual Property Ii, L.P. | Method and system for training a text-to-speech synthesis system using a domain-specific speech database |
JP2008129434A (ja) * | 2006-11-22 | 2008-06-05 | Oki Electric Ind Co Ltd | 音声合成サーバシステム |
US8886537B2 (en) * | 2007-03-20 | 2014-11-11 | Nuance Communications, Inc. | Method and system for text-to-speech synthesis with personalized voice |
JP2009025658A (ja) * | 2007-07-20 | 2009-02-05 | Oki Electric Ind Co Ltd | 音声合成装置、音声合成システム |
US7996473B2 (en) * | 2007-07-30 | 2011-08-09 | International Business Machines Corporation | Profile-based conversion and delivery of electronic messages |
CN101378530A (zh) * | 2007-08-30 | 2009-03-04 | 乐金电子(中国)研究开发中心有限公司 | 一种短信收发方法、***及短信服务器 |
CN101593516B (zh) | 2008-05-28 | 2011-08-24 | 国际商业机器公司 | 语音合成的方法和*** |
CN101605307A (zh) * | 2008-06-12 | 2009-12-16 | 深圳富泰宏精密工业有限公司 | 文本短信语音播放***及方法 |
JP2010020166A (ja) * | 2008-07-11 | 2010-01-28 | Ntt Docomo Inc | 音声合成モデル生成装置、音声合成モデル生成システム、通信端末、及び音声合成モデル生成方法 |
EP2205010A1 (en) * | 2009-01-06 | 2010-07-07 | BRITISH TELECOMMUNICATIONS public limited company | Messaging |
TWI415110B (zh) | 2009-03-02 | 2013-11-11 | Ibm | 用於語音合成之方法及系統 |
KR20110051580A (ko) * | 2009-11-10 | 2011-05-18 | 엘지전자 주식회사 | 음성 프로파일을 이용한 맞춤형 tts 서비스 제공 방법 및 그 단말 |
CN102117614B (zh) * | 2010-01-05 | 2013-01-02 | 索尼爱立信移动通讯有限公司 | 个性化文本语音合成和个性化语音特征提取 |
JP5423970B2 (ja) * | 2010-01-26 | 2014-02-19 | 日本電気株式会社 | 音声メール実現システム、音声メール実現サーバ、その方法及びそのプログラム |
CN102655544A (zh) | 2011-03-01 | 2012-09-05 | 联想(北京)有限公司 | 一种发起通信的方法及通信终端 |
CN102740244A (zh) | 2011-04-13 | 2012-10-17 | 深圳市汉讯通科技有限公司 | 一种语音短信***及其实现方法 |
TWI574254B (zh) | 2012-01-20 | 2017-03-11 | 華碩電腦股份有限公司 | 用於電子系統的語音合成方法及裝置 |
CN103856626A (zh) * | 2012-11-29 | 2014-06-11 | 北京千橡网景科技发展有限公司 | 个性声音的定制方法和装置 |
CN103281683B (zh) | 2013-06-08 | 2016-08-17 | 网易(杭州)网络有限公司 | 一种发送语音消息的方法及装置 |
CN103794206B (zh) * | 2014-02-24 | 2017-04-19 | 联想(北京)有限公司 | 将文本数据转换为语音数据的方法以及终端设备 |
-
2015
- 2015-08-04 KR KR1020150110072A patent/KR101703214B1/ko active IP Right Grant
- 2015-08-05 US US14/913,882 patent/US9812121B2/en active Active
- 2015-08-05 JP JP2016562268A patent/JP6459080B2/ja active Active
- 2015-08-05 EP EP15830674.6A patent/EP3035718B1/en active Active
- 2015-08-05 CN CN201580001904.9A patent/CN105556999A/zh active Pending
- 2015-08-05 TW TW104125413A patent/TWI613641B/zh active
- 2015-08-05 WO PCT/KR2015/008210 patent/WO2016021937A1/ko active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20010035173A (ko) * | 2001-01-10 | 2001-05-07 | 백종관 | 음성 합성 훈련 툴킷을 이용한 개인용 음성 합성기 및 그방법 |
KR20060061612A (ko) * | 2004-12-02 | 2006-06-08 | 주식회사 팬택 | 문자 메시지의 음성 안내 방법 및 그에 따른 저장매체 및그에 따른 통신 단말기 |
KR20070010360A (ko) * | 2005-07-18 | 2007-01-24 | 주식회사 팬택앤큐리텔 | 이동 통신 단말기의 음성 서비스 방법 |
KR20070049730A (ko) * | 2005-11-09 | 2007-05-14 | 엘지전자 주식회사 | 무선 통신망을 통한 음성 정보 서비스 방법 |
WO2008132758A2 (en) * | 2007-04-25 | 2008-11-06 | Kirusa, Inc. | Method and system for voice sms messaging |
Non-Patent Citations (1)
Title |
---|
See also references of EP3035718A4 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105868419A (zh) * | 2016-06-02 | 2016-08-17 | 泉港区奇妙工业设计服务中心 | 一种童伴机器人搜索学习装置 |
Also Published As
Publication number | Publication date |
---|---|
KR101703214B1 (ko) | 2017-02-06 |
US20160210960A1 (en) | 2016-07-21 |
EP3035718A1 (en) | 2016-06-22 |
JP2017531197A (ja) | 2017-10-19 |
EP3035718A4 (en) | 2017-04-05 |
TWI613641B (zh) | 2018-02-01 |
US9812121B2 (en) | 2017-11-07 |
CN105556999A (zh) | 2016-05-04 |
KR20160017625A (ko) | 2016-02-16 |
EP3035718B1 (en) | 2018-03-21 |
TW201633289A (zh) | 2016-09-16 |
JP6459080B2 (ja) | 2019-01-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2016021937A1 (ko) | 문자 데이터의 내용을 문자 데이터 송신자의 음성으로 출력하는 방법 | |
WO2016175354A1 (ko) | 인공지능 대화 장치 및 방법 | |
WO2018128238A1 (ko) | 디스플레이 장치를 이용한 가상 상담 시스템 및 방법 | |
WO2021251539A1 (ko) | 인공신경망을 이용한 대화형 메시지 구현 방법 및 그 장치 | |
EP1854756A1 (en) | Elevator car inside display | |
WO2020213785A1 (ko) | 발화 패턴의 무한성 개선을 위한 딥러닝 기반의 텍스트 문장 자동 생성시스템 | |
WO2015133790A1 (ko) | 번역 채팅 서비스 제공 장치 및 방법 | |
WO2016182400A1 (ko) | 통신정보 표시 및 접속기능이 구비된 모바일 장치 및 시스템과 그 방법 | |
WO2019164078A1 (ko) | 주제문 추출 가능한 실시간 다자 통역 무선 송수신 시스템 및 이를 이용한 송수신 방법 | |
WO2015037871A1 (ko) | 텍스트 인식을 이용한 음성재생 서비스 제공 시스템, 서버 및 단말 | |
WO2020149621A1 (ko) | 영어 말하기 평가 시스템 및 방법 | |
JP2009239466A (ja) | 電話受付システム、電話受付方法、プログラム、及び記録媒体 | |
WO2013094982A1 (ko) | 정보처리 방법 및 시스템과 기록매체 | |
WO2022255850A1 (ko) | 다국어 번역 지원이 가능한 채팅시스템 및 제공방법 | |
KR100747689B1 (ko) | 통신기기 음성인식 문자변환시스템 | |
JP2005109782A (ja) | Ctiサーバ、記録媒体、および電話対応支援システム。 | |
JPH10304068A (ja) | 音声情報交換方式 | |
WO2013094979A1 (ko) | 통신 단말 및 그 통신 단말의 정보처리 방법 | |
KR20050052943A (ko) | 여행자용 키워드 기반 음성번역 시스템 및 그 방법 | |
AU2019338745B2 (en) | Telephone exchange, hold tone notification method, and hold tone notification program | |
WO2015069020A1 (ko) | 코드변환을 이용한 번역 시스템 및 그 방법 | |
JPH09116648A (ja) | 携帯用通信装置 | |
WO2023003072A1 (ko) | 인공 지능 모델을 이용하여 음성 인식 서비스를 제공하는 장치 및 방법 | |
WO2013069900A1 (ko) | 서브셋 폰트를 이용한 메시지 서비스 시스템 및 방법 | |
WO2010087562A1 (ko) | 사용자의 감정정보를 제공하는 서버의 운영 방법 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201580001904.9 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14913882 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2015830674 Country of ref document: EP |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15830674 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2016562268 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |