WO2023022323A1 - Procédé, dispositif et programme d'évaluation de la difficulté d'écoute d'un énoncé en langue étrangère - Google Patents

Procédé, dispositif et programme d'évaluation de la difficulté d'écoute d'un énoncé en langue étrangère Download PDF

Info

Publication number
WO2023022323A1
WO2023022323A1 PCT/KR2022/005165 KR2022005165W WO2023022323A1 WO 2023022323 A1 WO2023022323 A1 WO 2023022323A1 KR 2022005165 W KR2022005165 W KR 2022005165W WO 2023022323 A1 WO2023022323 A1 WO 2023022323A1
Authority
WO
WIPO (PCT)
Prior art keywords
foreign language
evaluating
difficulty
listening
voice
Prior art date
Application number
PCT/KR2022/005165
Other languages
English (en)
Korean (ko)
Inventor
박봉래
Original Assignee
박봉래
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 박봉래 filed Critical 박봉래
Publication of WO2023022323A1 publication Critical patent/WO2023022323A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B19/00—Teaching not covered by other main groups of this subclass
    • G09B19/06—Foreign languages
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00—Electrically-operated educational appliances
    • G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
    • 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
    • G10L15/00—Speech recognition
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • 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
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • 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
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/16—Speech classification or search using artificial neural networks
    • 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
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
    • G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
    • G10L15/197—Probabilistic grammars, e.g. word n-grams
    • 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
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/488—Data services, e.g. news ticker

Definitions

  • the present invention relates to a method, apparatus, and program for evaluating the listening difficulty of foreign language speech.
  • listening ability should be improved based on elements that make listening difficult and the degree to which the elements are intertwined, that is, listening difficulty. It makes sense and is most effective to gradually expand listening training from vocalizations with a low level of listening difficulty to vocalizations with a high level of difficulty, that is, with minimal elements that make listening difficult and not so complicated.
  • the problem to be solved by the present invention is to provide a method, apparatus, and program for evaluating the listening difficulty of foreign language speech.
  • a method for evaluating listening difficulty of a foreign language voice for solving the above problems includes acquiring the foreign language voice, acquiring a foreign language text corresponding to the foreign language voice, and the foreign language voice and the foreign language text. Evaluating the listening difficulty of the foreign language voice based on
  • the step of evaluating the listening difficulty may include the step of evaluating the voice difficulty of the foreign language voice, the step of evaluating the expression difficulty of the foreign language text, and the foreign language voice by combining the voice difficulty evaluation result and the expression difficulty evaluation result. It may include the step of evaluating the listening difficulty of.
  • the step of evaluating the listening difficulty may include a reference phoneme sequence extraction step of extracting a reference phoneme sequence based on the foreign language text, and one or more candidate phoneme sequences by applying a predetermined pronunciation conversion rule to the foreign language text or the reference phoneme sequence. It may include a candidate phoneme sequence generating step of generating and an optimal phoneme string selection step of selecting one of the one or more candidate phoneme sequences as an optimal phoneme sequence.
  • the step of selecting the optimal phoneme sequence may include performing phoneme segment analysis by applying each of the one or more candidate phoneme sequences to the foreign language speech, and performing phoneme segment analysis with the best fit for the foreign language speech based on a result of the phoneme segment analysis. It may include acquiring information about phoneme sequences.
  • the step of evaluating the listening difficulty may include evaluating the listening difficulty of the foreign language speech through comparison between the standard phoneme sequence and the optimum phoneme sequence.
  • the evaluation of the listening difficulty may include evaluating the listening difficulty of the foreign language speech based on hearing loss pronunciation pattern information detected from the reference phoneme sequence or the optimal phoneme sequence.
  • the step of evaluating the listening difficulty may include obtaining one or more components included in the foreign language text, obtaining a frequency of occurrence of the one or more components from a language database, and calculating the frequency of occurrence of the one or more components. It may include evaluating the listening difficulty of the foreign language voice based on.
  • the evaluating of the listening difficulty may include obtaining information on the number of verbs included in the foreign language text and evaluating the listening difficulty of the foreign language voice based on the number of verbs included in the foreign language text.
  • the method of evaluating the listening difficulty of the foreign language voice may further include determining whether or not to display a subtitle corresponding to the foreign language voice according to a result of evaluating the listening difficulty of the foreign language voice.
  • the step of determining whether to display the subtitles may include determining a standard difficulty level and determining whether to display a subtitle corresponding to the foreign language audio by comparing the listening difficulty of the foreign language voice with the standard difficulty level. there is.
  • the determining of the standard difficulty level may include acquiring a user's listening ability and determining the reference level of difficulty based on the user's listening level.
  • the step of evaluating the listening difficulty may further include analyzing a hearing loss factor included in the foreign language voice.
  • the analyzing of the hearing loss factor may further include storing the foreign language voice and information about the hearing loss factor included in the foreign language voice.
  • the method for evaluating the listening difficulty of the foreign language voice includes providing a user with one or more foreign language voices, evaluating a listening result of the user for the one or more foreign language voices, and responding to the foreign language voices that the user has not heard.
  • the method may further include obtaining a weak hearing loss factor of the user.
  • the method of evaluating the listening difficulty of the foreign language voice may further include acquiring the foreign language voice for learning including the weak hearing loss factor and providing the foreign language voice for learning to the user.
  • An apparatus for evaluating hearing difficulty of foreign language speech for solving the above problems includes a memory for storing one or more instructions and a processor for executing the one or more instructions stored in the memory, wherein the processor comprises: By executing the one or more instructions, the steps of acquiring a foreign language voice, obtaining a foreign language text corresponding to the foreign language voice, and evaluating the listening difficulty of the foreign language voice based on the foreign language voice and the foreign language text are performed. do.
  • a listening difficulty evaluation program for foreign language voices stored in a computer-readable recording medium is combined with a computer, which is hardware, to acquire foreign language voices, and correspond to the foreign language voices. Obtaining a foreign language text of the foreign language voice and evaluating the listening difficulty of the foreign language voice based on the foreign language voice and the foreign language text.
  • FIG. 1 is a diagram illustrating a listening difficulty evaluation system for foreign language speech according to an embodiment of the present invention.
  • FIG. 2 is a hardware configuration diagram of an apparatus for evaluating the hearing difficulty of foreign language speech according to another embodiment of the present invention.
  • FIG. 3 is a flowchart of a method for evaluating the listening difficulty of foreign language speech according to another embodiment of the present invention.
  • FIG. 4 is a configuration diagram illustrating a language database according to an embodiment of the present invention.
  • FIG. 5 is a flowchart for explaining in detail the method for evaluating the listening difficulty of foreign language voices shown in FIG. 3 .
  • FIG. 6 is a flowchart for explaining in detail the voice difficulty evaluation method of the foreign language voice shown in FIG. 5 .
  • FIG. 7 is a diagram comparing a phoneme sequence suitable for speech and an unsuitable phoneme sequence in relation to phoneme sequence extraction according to an embodiment of the present invention.
  • FIG. 8 is a diagram for explaining a process of extracting a standard phoneme sequence in a system for evaluating the listening difficulty of foreign language speech according to an embodiment of the present invention.
  • FIG. 9 is an exemplary view illustrating an operating method of a phoneme interval analysis model according to an embodiment of the present invention.
  • FIG. 10 is a flowchart for explaining in detail the method for evaluating the expression difficulty of a foreign language voice shown in FIG. 5 .
  • 11 is a flowchart illustrating a method for diagnosing and constructing learning contents according to an embodiment.
  • FIG. 12 is an exemplary diagram for explaining a method for diagnosing foreign language listening according to an embodiment of the present invention.
  • unit or “module” used in the specification means a hardware component such as software, FPGA or ASIC, and "unit” or “module” performs certain roles. However, “unit” or “module” is not meant to be limited to software or hardware.
  • a “unit” or “module” may be configured to reside in an addressable storage medium and may be configured to reproduce one or more processors.
  • a “unit” or “module” may refer to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Functions provided within components and “units” or “modules” may be combined into smaller numbers of components and “units” or “modules” or may be combined into additional components and “units” or “modules”. can be further separated.
  • computers and computing devices refer to all types of hardware devices including at least one processor, and may be understood as encompassing software configurations operating in the corresponding hardware devices according to embodiments.
  • a computer may be understood as including a smartphone, a tablet PC, a desktop computer, a laptop computer, and user clients and applications running on each device, but is not limited thereto.
  • each step described in this specification is described as being performed by a computing device, the subject of each step is not limited thereto, and at least some of the steps may be performed by different devices according to embodiments.
  • FIG. 1 is a diagram illustrating a listening difficulty evaluation system for foreign language speech according to an embodiment of the present invention.
  • the listening difficulty evaluation system for foreign language speech includes an apparatus 100 for evaluating listening difficulty of foreign language speech, a user terminal 200, an external server 300, and a network 400.
  • an apparatus 100 for evaluating listening difficulty of foreign language speech includes a user terminal 200, an external server 300, and a network 400.
  • the listening difficulty evaluation system for foreign language speech shown in FIG. 1 is according to an embodiment, and its components are not limited to the embodiment shown in FIG. 1, and may be added, changed, or deleted as necessary. .
  • the apparatus 100 acquires foreign language speech and foreign language text corresponding thereto, and listens to the foreign language speech based on the foreign language speech and foreign language text. difficulty can be assessed.
  • the computing device 100 may evaluate the listening difficulty of foreign language speech using a pre-learned artificial intelligence model.
  • the method for evaluating the listening difficulty of foreign language speech performed by the computing device 100 may be implemented in the form of a web or application.
  • the computing device 100 may be connected to the user terminal 200 through the network 400 to provide an application to the user terminal 200, and as the user downloads, installs, and executes the application, a foreign language voice is provided. can provide a listening difficulty evaluation service of
  • the methods according to the disclosed embodiments may be performed by the user terminal 200 .
  • some steps may be performed by the user terminal 200 and some other steps may be performed by the computing device 100 .
  • the user terminal 200 includes an operating system for driving a method for evaluating the listening difficulty of a foreign language voice provided in the form of a web or application, and outputs a user interface (UI) provided as the web or application is executed.
  • UI user interface
  • It may be a smart phone including a display in a predetermined area to do so.
  • the user terminal 200 is a wireless communication device that ensures portability and mobility, and includes navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet ) may include all kinds of handheld-based wireless communication devices such as terminals, smart pads, tablet PCs, etc., but are not limited thereto.
  • PCS Personal Communication System
  • GSM Global System for Mobile communications
  • PDC Personal Digital Cellular
  • PHS Personal Handyphone System
  • PDA Personal Digital Assistant
  • IMT International Mobile Telecommunication
  • CDMA Code Division Multiple Access
  • W-CDMA Wide-Code Division Multiple Access
  • Wibro Wireless Broadband Internet
  • handheld-based wireless communication devices such as terminals, smart pads, tablet PCs, etc., but are not limited thereto.
  • the network 400 may refer to a connection structure capable of exchanging information between nodes such as a plurality of terminals and servers.
  • the network 400 includes a local area network (LAN), a wide area network (WAN), a world wide web (WWW), a wired and wireless data communication network, a telephone network, a wired and wireless television communication network, and the like. can do.
  • wireless data communication networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi (Wi-Fi) , Internet (Internet), LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC ( It may include a Near-Field Communication) network, a satellite broadcasting network, an analog broadcasting network, a Digital Multimedia Broadcasting (DMB) network, etc., but is not limited thereto.
  • 3GPP 3rd Generation Partnership Project
  • 5GPP 5th Generation Partnership Project
  • LTE Long Term Evolution
  • WIMAX Worldwide Interoperability for Microwave Access
  • Wi-Fi Wi-Fi
  • Internet Internet
  • LAN Local Area Network
  • Wireless LAN Wireless Local Area Network
  • WAN Wide Area
  • the external server 300 may be connected to the computing device 100 through the network 400, and various information and data necessary for the computing device 100 to perform a method for evaluating the listening difficulty of foreign language speech. It can store and manage, or store and manage various types of information and data generated by performing a method for evaluating the listening difficulty of a foreign language voice.
  • the external server 300 may be a storage server provided separately outside the computing device 100, but is not limited thereto.
  • FIG. 2 is a hardware configuration diagram of an apparatus for evaluating the hearing difficulty of foreign language speech according to another embodiment of the present invention.
  • a computing device 100 includes one or more processors 110, a memory 120 for loading a computer program 151 executed by the processor 110, and a bus ( 130), a communication interface 140, and a storage 150 for storing the computer program 151.
  • processors 110 the processors 110
  • memory 120 for loading a computer program 151 executed by the processor 110
  • bus 130 the bus
  • communication interface 140 the communication interface
  • storage 150 for storing the computer program 151.
  • FIG. 2 only components related to the embodiment of the present invention are shown. Therefore, those skilled in the art to which the present invention pertains can know that other general-purpose components may be further included in addition to the components shown in FIG. 2 .
  • the processor 110 controls the overall operation of each component of the computing device 100 .
  • the processor 110 includes a Central Processing Unit (CPU), a Micro Processor Unit (MPU), a Micro Controller Unit (MCU), a Graphic Processing Unit (GPU), or any type of processor well known in the art of the present invention. It can be.
  • CPU Central Processing Unit
  • MPU Micro Processor Unit
  • MCU Micro Controller Unit
  • GPU Graphic Processing Unit
  • the processor 110 may perform an operation for at least one application or program for executing a method according to embodiments of the present invention
  • the computing device 100 may include one or more processors.
  • the processor 110 may temporarily and/or permanently store signals (or data) processed in the processor 110 (RAM: Random Access Memory, not shown) and ROM (ROM: Read -Only Memory, not shown) may be further included.
  • the processor 110 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.
  • SoC system on chip
  • Memory 120 stores various data, commands and/or information. Memory 120 may load computer program 151 from storage 150 to execute methods/operations according to various embodiments of the present invention. When the computer program 151 is loaded into the memory 120, the processor 110 may perform the method/operation by executing one or more instructions constituting the computer program 151.
  • the memory 120 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.
  • the bus 130 provides a communication function between components of the computing device 100 .
  • the bus 130 may be implemented in various types of buses such as an address bus, a data bus, and a control bus.
  • the communication interface 140 supports wired and wireless Internet communication of the computing device 100 . Also, the communication interface 140 may support various communication methods other than Internet communication. To this end, the communication interface 140 may include a communication module well known in the art. In some embodiments, communication interface 140 may be omitted.
  • the storage 150 may non-temporarily store the computer program 151 .
  • the storage 150 may store various types of information necessary to provide the listening difficulty evaluation process of the foreign language speech.
  • the storage 150 may be a non-volatile memory such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or the like, a hard disk, a removable disk, or a device well known in the art. It may be configured to include any known type of computer-readable recording medium.
  • ROM read only memory
  • EPROM erasable programmable ROM
  • EEPROM electrically erasable programmable ROM
  • flash memory or the like, a hard disk, a removable disk, or a device well known in the art. It may be configured to include any known type of computer-readable recording medium.
  • Computer program 151 may include one or more instructions that when loaded into memory 120 cause processor 110 to perform methods/operations in accordance with various embodiments of the invention. That is, the processor 110 may perform the method/operation according to various embodiments of the present disclosure by executing the one or more instructions.
  • the computer program 151 includes steps of acquiring a foreign language voice, acquiring a foreign language text corresponding to the foreign language voice, and evaluating the listening difficulty of the foreign language voice based on the foreign language voice and the foreign language text. It may include one or more instructions for performing a method for evaluating the listening difficulty of foreign language speech, including steps.
  • Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof.
  • a software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.
  • Components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium.
  • Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, such as C, C++ , Java (Java), can be implemented in a programming or scripting language such as assembler (assembler). Functional aspects may be implemented in an algorithm running on one or more processors.
  • FIG. 3 is a flowchart of a method for evaluating the listening difficulty of foreign language speech according to another embodiment of the present invention.
  • step S110 the computing device 100 may obtain a foreign language voice.
  • 'foreign language' means a language different from the learner's native language.
  • 'foreign language' may mean a language other than Korean (eg, English), but from the viewpoint of a person who speaks another language (eg, English), it is desirable that 'foreign language' may be Korean. do. That is, the foreign language and related foreign language voice and text in the present invention are understood as a concept that is not limited to a specific language or excludes a specific language.
  • the foreign language voice may be a voice prepared in advance for learning or a foreign language voice that can be heard in a foreign language movie or drama.
  • the foreign language voice may preferably be sequentially received in units of sentences, but is not limited thereto.
  • the computing device 100 may acquire foreign language text corresponding to the foreign language voice.
  • the foreign language text may refer to a script corresponding to a foreign language voice.
  • the foreign language text may be received from the outside, and when the foreign language text is not received, the computing device 100 may extract the text through Speech to Text (STT) for the foreign language voice obtained in step S110. .
  • STT Speech to Text
  • the foreign language text obtained in step S120 may be the simplest and most basic standard text corresponding to the foreign language voice obtained in step S110.
  • the voice comment is “I'm gonna”
  • the received or recognized foreign language text can be a simple and basic standard “I am going to”. This is because it is much easier to calculate the listening difficulty when calculating the listening difficulty based on this.
  • the computing device 100 may transform it into a standard format.
  • step S130 the computing device 100 may evaluate the listening difficulty of the foreign language voice based on the foreign language voice and the foreign language text.
  • a language database for analyzing foreign language speech and text and evaluating the listening difficulty of foreign language speech may be defined.
  • the language database may be stored in the computing device 100 or the external server 300, but is not limited thereto.
  • FIG. 4 an example of a language database for analyzing foreign language voices and texts and evaluating listening difficulty of foreign language voices is shown.
  • the language database 500 may include a pronunciation pattern database 510 that stores information about pronunciation patterns for a specific language and an expression pattern database 520 that stores information about expression patterns.
  • the pronunciation pattern database 510 includes information on foreign language pronunciation patterns. Pronunciation pattern information may include various linguistic information or linguistic statistical information related to pronunciation at the time of vocalization.
  • the pronunciation pattern database 510 may include information about words, sentences, phoneme strings, and phoneme intervals.
  • the pronunciation pattern database 510 may include pattern information about pronunciation with hearing loss.
  • the hearing loss pronunciation patterns stored in the pronunciation pattern database 510 include patterns in which identical consonants appear in succession, patterns in which similar consonants appear in succession, patterns in which similar vowels appear in succession, and pronunciations such as t, p, and k are hardened. It may include a pattern and the like to be, but is not limited thereto.
  • the pronunciation pattern database 510 may store information about pronunciation conversion rules of various types.
  • a rule in which a weak vowel is omitted when a spontaneous consonant and a weak vowel are consecutive e.g., 'support' can be converted to /sport/ and pronounced
  • a non-voluntary consonant and a consonant when a consonant is consecutive It may include rules for omitting consonants, rules for weakening (schwa) when short vowels are not stressed, rules for omitting weak vowels that start sentences, and rules for only strong vowels appearing when weak vowels and strong vowels are consecutive. , but not limited thereto.
  • rules such as abbreviation, deletion, conversion, etc. related to specific pronunciation, such as a rule for converting to ch when consonant t and consonant r are consecutive, may be included.
  • Spontaneous consonants are consonants such as s, z, f, v, sh, ch, r, and l that can be uttered on their own without being supported by vowels, and involuntary consonants are p, t, k, b, d, g and In principle, consonants are not produced unless there is a vowel.
  • the pronunciation conversion rules may be applied consecutively. For example, when a spontaneous consonant and a weak vowel are continued again in a state in which a phonetic conversion has occurred according to a rule in which a single vowel is weakened when there is no stress, a rule in which a weak vowel is omitted may be continuously applied.
  • pronunciation conversion rules and other pronunciation patterns stored in the pronunciation pattern database 510 is not limited by the above examples and other descriptions of this specification, and various pronunciation conversion rules and other pronunciation patterns for the target language Information on this may be stored in the pronunciation pattern database 510.
  • the pronunciation pattern database 510 includes statistical information about the frequency of occurrence of pronunciation patterns and the frequency of application of pronunciation conversion rules, the frequency of occurrence of specific phoneme sequences in which pronunciation patterns appear and specific phoneme sequences to which pronunciation conversion rules are applied. Statistical information on frequency of occurrence may additionally be included.
  • the expression pattern database 520 provides foreign language expression pattern information.
  • Expression pattern information may include linguistic information or linguistic statistical information related to the expression of foreign language text.
  • the expression pattern database 520 may store statistical information related to each frequency of occurrence in relation to expression patterns of components constituting foreign language text.
  • the expression pattern may be understood as a concept including attributes of components constituting foreign language text or patterns of foreign language expression methods derived through a combination of components.
  • the expression pattern database 520 may manage information capable of determining whether words included in foreign language speech or foreign language text are verbs in relation to expression patterns.
  • Information on expression patterns stored in the expression pattern database 520 is not limited by the above examples and other descriptions of this specification, and information on various expression patterns for a target language is stored in the expression pattern database 520. can be stored
  • FIG. 5 is a flowchart for explaining in detail the method for evaluating the listening difficulty of foreign language voices shown in FIG. 3 .
  • the computing device 100 may evaluate the voice difficulty and expression difficulty of the foreign language voice, respectively, and synthesize them.
  • the computing device 100 may evaluate the voice difficulty of the foreign language voice.
  • the voice difficulty is listening difficulty evaluated based on the properties of the foreign language voice itself, and the voice difficulty may be evaluated by considering both the foreign language voice and the foreign language text, but is not limited thereto.
  • the computing device 100 may evaluate the expression difficulty of the foreign language text.
  • the expression difficulty is listening difficulty evaluated based on the properties of the foreign language text itself, and the expression difficulty may be evaluated using only the foreign language text, but is not limited thereto.
  • step S230 the computing device 100 may evaluate the listening difficulty of the foreign language voice by integrating the voice difficulty evaluation result and the expression difficulty evaluation result.
  • FIG. 6 is a flowchart for explaining in detail the voice difficulty evaluation method of the foreign language voice shown in FIG. 5 .
  • the voice difficulty of a foreign language voice is the listening difficulty evaluated based on the properties of the foreign language voice itself, and the voice difficulty may be evaluated by considering both the foreign language voice and the foreign language text, but is not limited thereto.
  • the computing device 100 determines a phoneme sequence corresponding to a foreign language voice and uses it to evaluate the voice difficulty of the foreign language voice.
  • a phoneme sequence corresponding to a foreign language voice may be simply determined by referring to a phoneme dictionary (providing phoneme information for each word) for each word in the foreign language text.
  • a phoneme dictionary providing phoneme information for each word
  • problems such as the upper part of FIG. 7 may occur. That is, when the actual voice is not a standard vocalization as shown in the lower part of FIG. 7 and some phonemes are omitted or modified, the phoneme sequence extracted based on the phoneme dictionary does not match the actual voice, resulting in overall confusion and incorrect analysis of phoneme sections. It can be.
  • all possible phoneme sequence candidates are generated by considering all possible pronunciation transformation patterns, and after extracting the degree of fit of each phoneme sequence candidate to the actual voice, the most suitable phoneme sequence You need to find candidates.
  • step S310 the computing device 100 may extract a reference phoneme sequence based on the foreign language text obtained in step S120 of FIG. 3.
  • the computing device 100 performs an operation of extracting phoneme strings and phoneme sections based on foreign language text. Specifically, the computing device 100 extracts a phoneme sequence and a phoneme interval based on phoneme interval information for each word or sentence managed by the language database 500 .
  • the reference phoneme sequence and phoneme interval information may be basically obtained by combining phoneme sequence and phoneme interval information of words managed by the language database 500 .
  • phoneme interval information for each individual phoneme may be stored in the language database 500 . For example, when speaking at normal speed, phoneme interval information may be stored as 200 ms for long vowels and 40 ms for consonants. In this case, when extracting phoneme sequences and phoneme intervals of words, phoneme interval information for each phoneme constituting a word may be referred to.
  • the computing device 100 may check whether the foreign language text is in the basic form, restore the foreign language text to the basic form if the foreign language text is not in the basic form, and extract a reference phoneme sequence and phoneme interval from the restored foreign language text.
  • the basic form means a basic form of syntax before the form of words is transformed by contraction or the like.
  • the computing device 100 converts the corresponding part into a basic form such as 'should have, do not, what are you, want to' After restoring with , the basic phoneme sequence and phoneme interval can be extracted from the restored foreign language text.
  • the computing device 100 extracts a reference phoneme sequence along with phoneme intervals from foreign language text.
  • the computing device 100 may extract a reference phoneme sequence by basically referring to a phoneme dictionary for each word.
  • this method may not reflect the part where the phoneme configuration and phoneme interval length of the word may change depending on the preceding and preceding words even in the same word.
  • the computing device 100 may extract a reference phoneme sequence using the language database 500 according to the disclosed embodiment.
  • the language database 500 may store basic phoneme sequence and phoneme interval information for each possible text and provide phoneme sequence and phoneme interval information for each text.
  • phoneme sequence and phoneme interval information for each text may be provided through a neural network model as shown in FIG.
  • the computing device 100 may extract phoneme sequence and phoneme interval information for each text provided by the neural network model of the language database 500 as a reference phoneme sequence.
  • step S320 the computing device 100 applies a preset pronunciation conversion rule to the foreign language text obtained in step S120 of FIG. can create
  • the candidate phoneme sequence generated in step S320 may basically include a reference phoneme sequence.
  • the computing device 100 may generate a basic phoneme sequence by receiving a pronunciation sequence for each word from the language database 500, and combine pronunciation conversion rules of the language database 500 into the generated basic phoneme sequence.
  • new candidate phoneme sequences can be generated.
  • information about which pronunciation rules are applied to which part of each candidate phoneme string can be separately stored and managed.
  • the computing device 100 may refer to the pronunciation conversion rules stored in the language database 500 and extract the reference phoneme sequence and all modified phoneme sequences derivable from the reference phoneme sequence as candidate phoneme sequences.
  • the computing device 100 may select one of the one or more candidate phoneme sequences generated in step S320 as an optimal phoneme sequence. In addition, the computing device 100 may select an optimal phoneme sequence and extract the length of phoneme intervals for each constituent phoneme.
  • the computing device 100 performs phoneme interval analysis by applying each of the plurality of candidate phoneme sequences generated in step S320 to the foreign language voice, and through this, the optimal phoneme sequence having the greatest suitability for the foreign language voice is determined. can be selected
  • the phoneme interval analysis may be performed based on a Gaussian Hidden Markov Model or a Gaussian Neural Network model, but is not limited thereto.
  • the computing device 100 may input candidate phoneme sequences to the model and obtain a phoneme sequence and a phoneme interval having the greatest suitability for foreign language speech as output.
  • the above-described phoneme segment analysis models output a degree of fit along with phoneme segment length information in the corresponding phoneme sequence when a voice and a phoneme sequence are input.
  • the computing device 100 may select the most suitable phoneme sequence and phoneme interval acoustically as the optimal phoneme sequence to be evaluated by substituting each candidate phoneme sequence for the foreign language voice.
  • FIG. 9 an example of a method for determining the suitability of a phoneme sequence using a phoneme segment analysis model is shown.
  • the computing device 100 may output a phoneme sequence and a phoneme period based on a phoneme period analysis model such as a Gaussian Hidden Markov Model or a Gaussian Neural Network model, as described above.
  • a phoneme period analysis model such as a Gaussian Hidden Markov Model or a Gaussian Neural Network model, as described above.
  • the computing device 100 may input information about the voice waveform of the foreign language voice and the candidate phoneme string to the phoneme segment analysis model.
  • acoustic feature values of a foreign language voice corresponding to a voice waveform of a foreign language voice may be input to a phoneme interval analysis model, but is not limited thereto.
  • the phoneme segment analysis model applies each of the candidate phoneme sequences to foreign language speech and outputs the degree of fit for each phoneme sequence. Thereafter, the computing device 100 may select the output candidate phoneme sequence having the highest suitability as the optimal phoneme sequence.
  • the phoneme segment analysis model outputs the degree of suitability for the input speech for each of the five candidate phoneme strings, and the computing device 100 may select the output candidate phoneme string having the highest degree of suitability as the optimal phoneme string.
  • step S340 the computing device 100 may evaluate the voice difficulty of the foreign language speech using the basic phoneme sequence extracted in step S310 and the optimal phoneme sequence obtained in step S330.
  • the computing device 100 extracts one or more hearing loss factors from the reference phoneme sequence and the optimal phoneme sequence using hearing loss pronunciation pattern (or hearing loss factor) information provided from the language database 500, and extracts the extracted hearing loss factors.
  • the voice difficulty of foreign language speech may be evaluated based on the hearing loss factor and the frequency of occurrence of the hearing loss factor.
  • the computing device 100 may evaluate the voice difficulty of the foreign language speech through comparison between the standard phoneme sequence obtained in step S310 and the optimal phoneme sequence obtained in step S330.
  • a phoneme segment hearing loss factor indicating that hearing is difficult as the length of the phoneme segment decreases when compared with a preset standard utterance may be applied to the voice difficulty evaluation. That is, short phoneme intervals can be regarded as difficult to hear because they are pronounced quickly.
  • the voice difficulty can be evaluated higher.
  • the computing device 100 may evaluate the voice difficulty based on hearing loss pronunciation pattern information detected from the reference phoneme sequence or the optimal phoneme sequence.
  • a similar phoneme continuous hearing loss factor indicating that hearing is difficult due to a continuous arrangement of phonemes having similar pronunciations may be applied.
  • Pseudophoneme successive hearing loss factors are based on assimilation. In this case, even if the length of the phoneme section is not short or the pronunciation is not modified, it is uttered as an entire pronunciation that seems to be omitted, so it may be difficult to listen. For example, “is certain” sounds like /i- certain/, and “have books” tends to sound like /ha- books/.
  • a partial phonemic hearing loss factor representing a phenomenon that is unfamiliar to hearing due to a low frequency of encounter in general can be applied.
  • foreign language texts or foreign language voices that may cause awkwardness in listening may correspond to the factor of partial phonemic fever hearing loss. For example, if “want to” is pronounced as “wanna”, the phonetic conversion is performed, so it may be difficult to hear according to the principle. there is.
  • misperception-induced hearing loss factors related to pronunciation that may cause misrecognition may be applied.
  • the factor of misinterpretation-induced hearing loss means that it is difficult to hear because the entire pronunciation or a part of the pronunciation is mistakenly associated with another foreign language word or another foreign language word. For example, if “call her” sounds like “caller”, hearing “caller” rather than “her” may be difficult to hear. Also, if “apply to” sounds like “a fly to” and fly rather than apply comes to mind, the content of listening can be greatly ruined. This phenomenon can occur when the viewer is more familiar with fly than apply.
  • the computing device 100 may perform voice difficulty evaluation based on pronunciation conversion rules such as various types of contraction, deletion, and conversion applied to the optimal phoneme sequence.
  • the pronunciation conversion rules applied to the optimal phoneme sequence refer to one or more pronunciation conversion rules applied when generating the candidate phoneme sequence selected as the optimal phoneme sequence (step S320 of FIG. 6).
  • a pronunciation conversion hearing loss factor may be applied, which means that listening is difficult because a number of pronunciation conversions are included compared to the reference vocalization.
  • the pronunciation conversion hearing loss factor means that the more prepared pronunciation rules are applied, the more difficult it is to hear.
  • the degree of hearing loss induction of the prepared pronunciation rules can be classified using weights. Even if the phoneme interval is not short, there is a feature that the difficulty related to listening increases if the phoneme conversion is performed. For example, in “suit you”, [t y] is converted to [ch].
  • FIG. 10 is a flowchart for explaining in detail the method for evaluating the expression difficulty of foreign language text shown in FIG. 5 .
  • step S410 the computing device 100 may acquire one or more elements included in the foreign language text acquired in step S120 of FIG. 3.
  • the components may include sentences, sentence structures, phrases, words, n-grams, etc. constituting foreign language text, but are not limited thereto.
  • the foreign language text itself including each component is also understood as a concept included in the component referred to in the present embodiment.
  • step S420 the computing device 100 may analyze the attribute of the component acquired in step S410.
  • step S430 the computing device 100 may evaluate the expression difficulty of the foreign language text.
  • the computing device 100 may refer to the language database 500, acquire components in the foreign language text in step S410, and analyze expression deafness factors based on the components in step S420.
  • the expressive hearing loss factor may include a syntactic complexity criterion hearing loss factor based on the length of the foreign language text and the number of verbs included in the foreign language text, and a frequency criterion hearing loss factor based on the frequency of occurrence of each component included in the foreign language text. It may, but is not limited thereto.
  • the hearing loss factor based on syntactic complexity means that the longer and more complex a foreign language text is, the more difficult it is to hear. Accordingly, the computing device 100 may determine that the expression difficulty of the foreign language text increases as the length of the foreign language text increases and the number of verbs included in the foreign language text increases.
  • the frequency-based hearing loss factor means that it is difficult to hear when each component is an expression that is difficult to encounter in everyday life.
  • expression difficulty may be evaluated based on statistics of expression patterns corresponding to each component included in the foreign language text. That is, based on various statistics, when the expression pattern of a specific component is not statistically well used, the expression difficulty can be calculated higher.
  • the hearing loss factor is based on the frequency of vocabulary; if the frequency is determined based on idioms, the hearing loss factor is based on the frequency of idioms; It can be said to be a gram frequency-based hearing loss factor, and the types of frequency-based hearing loss factors are not limited thereto.
  • the vocabulary frequency-based hearing loss factor can be understood as a concept that includes a case in which a proper noun or an unregistered word that is not registered as a standard is included in a foreign language text.
  • the factor of hearing loss based on n-gram is when it is difficult to recognize a combination of words. For example, “Thank you” is easy to hear, but “Thank me” is not easily heard. It can be selected as a hearing loss factor.
  • the computing device 100 may obtain components of the foreign language text and check the frequency of occurrence of each component by referring to the language database 500 . As the occurrence frequency of each component is lower, the computing device 100 may evaluate the expression difficulty of the foreign language text higher.
  • the computing device 100 obtains each component as follows and refers to the language database 500 for at least one of the acquired components. to check the frequency of occurrence. In addition, the computing device 100 may evaluate the listening difficulty higher as the occurrence frequency of each component is lower.
  • Sentence frequency of occurrence of the sentence itself
  • Sentence structure One of the syntax types derived during syntax analysis
  • a method of evaluating expression difficulty of foreign language text based on the frequency of occurrence of components may be set in various ways.
  • the maximum value and the minimum value of the occurrence frequency of the component may be calculated as a difficulty level of 0 to a difficulty level of 100, respectively.
  • the listening difficulty may be calculated by assigning weights to the frequency of occurrence of each component and summing them.
  • 11 is a flowchart illustrating a method for diagnosing and constructing learning contents according to an embodiment.
  • Diagnosis and learning contents are contents used to diagnose a user's foreign language listening ability and support customized learning, and are characterized by generating contents by extracting one or more factors of hearing loss in order to diagnose and reinforce the user's foreign language listening ability.
  • the method for diagnosing and constructing learning contents includes acquiring foreign language speech and text (S510), extracting a reference phoneme sequence from the foreign language text (S520), and candidate phonemes from the foreign language text using the reference phoneme sequence. Generating a sequence (S530), extracting an optimal phoneme sequence based on the candidate phoneme sequence (S540), extracting a voice hearing loss factor by comparing the optimal phoneme sequence and the reference phoneme sequence (S550), from a foreign language text It may include extracting the expression hearing loss factor (S560) and storing the foreign language voice or foreign language text in which the voice hearing loss factor or the expression hearing loss factor is confirmed (S570).
  • the computing device 100 receives (S510) foreign language voice and foreign language text.
  • the computing device 100 refers to the language database 500 and extracts a reference phoneme sequence from the foreign language text (S520).
  • the computing device 100 refers to the reference phoneme sequence and the language database 500 to generate candidate phoneme sequences that can be uttered from the foreign language text (S530).
  • the computing device 100 extracts an optimal phoneme sequence optimally corresponding to the foreign language voice from the candidate phoneme sequences generated in step S530 (S540).
  • the computing device 100 After extracting the reference phoneme sequence and the optimal phoneme sequence, the computing device 100 extracts a voice hearing loss factor by comparing both phoneme sequences (S550). A detailed method of extracting the hearing loss factor by the computing device 100 is as described above.
  • the computing device 100 refers to the language database 500 to detect one or more expression patterns from the foreign language text, and extracts expression hearing loss factors based on the detected expression patterns (S560).
  • a detailed method of extracting the hearing loss factor by the computing device 100 is as described above.
  • the computing device 100 stores the foreign language voice or foreign language text for which at least one of the two hearing loss factors is confirmed as diagnosis and learning content (S570), thereby diagnosing and learning content. complete the build
  • Diagnosis and learning contents formed through a series of configurations and steps as described above can be used for diagnosing the foreign language listening ability of learners learning a foreign language and supporting customized learning.
  • the computing device 100 acquires a foreign language video and foreign language voice and text (eg, script) information included in the foreign language video, and determines the listening difficulty of each acquired foreign language voice. can be evaluated
  • the computing device 100 may determine whether to display subtitles according to the listening difficulty evaluation result. In an embodiment, the computing device 100 may determine whether to display subtitles by determining a standard level of difficulty and comparing the level of difficulty of listening to a foreign language voice included in a foreign language video with the level of level of difficulty.
  • the computing device 100 may determine the user's listening ability by using the diagnosis and learning content generated according to the above-described embodiment to determine the reference difficulty level. According to the user's listening ability, the computing device 100 does not display subtitles for voices of low difficulty that the user can sufficiently hear, and displays subtitles for voices of high difficulty that are difficult for the user to hear. You can make listening learning possible naturally while watching videos. On the other hand, the user's listening ability may simply be set by the user.
  • the computing device 100 may provide customized training content that supports listening training tailored to each user.
  • the computing device 100 outputs a foreign language voice included in the stored diagnostic and learning content, and compares and analyzes the foreign language voice determined to be audible and the foreign language voice determined to be difficult to hear, thereby determining factors for vulnerable hearing loss. Diagnose.
  • the computing device 100 may provide one or more foreign language voices to the learner and evaluate the learner's listening result for the provided foreign language voice. For example, by querying whether or not the foreign language voice was heard from the learner and receiving a response, providing a quiz corresponding to the foreign language voice and checking the correct answer received from the learner, or having the learner listen to the foreign language voice. It is possible to evaluate the input result by directly inputting as heard, but is not limited thereto.
  • the computing device 100 may determine a difference in a hearing loss factor between a voice that can be heard by a learner and a voice that cannot be heard, and analyze a weak hearing loss factor based on the difference. For example, the computing device 100 may obtain a learner's weak hearing loss factor corresponding to a foreign language voice that the learner has not heard. Diagnosis results according to the disclosed embodiment may be displayed as a graph as shown in FIG. 12 to improve readability.
  • the computing device 100 may provide customized training voices for each hearing loss factor.
  • the content for customized training may be provided as a foreign language voice tagged with factors of hearing loss, which may be generated and stored using the diagnosis and learning content generation method described with reference to FIG. 11 . That is, the computing device 100 may obtain a foreign language voice including a factor of a weak hearing loss that the user cannot hear well, and provide it to the user as customized training content.
  • the computing device 100 may detect a foreign language voice identified as a weak hearing loss factor for the user, and support customized listening training based on the detected foreign language voice.
  • a foreign language voice identified as a weak hearing loss factor for the user, and support customized listening training based on the detected foreign language voice.
  • the above-described customized training content may be provided separately.
  • the present invention can easily carry out diagnosis of foreign language listening ability and listening training accordingly, in addition to the above-described foreign language listening difficulty evaluation method.
  • This has the effect of maximizing learning efficiency and listening training effect by minimizing unnecessary and redundant learning that takes a long time for foreign language learners who want to improve their foreign language listening skills and actively responding to their foreign language listening skills.
  • the computing device 100 can provide diagnosis contents targeting foreign language trainees and training contents specialized for the foreign language trainees. Therefore, it is possible to more easily induce improvement of foreign language listening comprehension.
  • the present invention is expected to contribute to the development of the foreign language education industry as an exemplary application of artificial intelligence technology such as deep learning to the education industry.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Signal Processing (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

La divulgation concerne un procédé d'évaluation de la difficulté d'écoute d'un énoncé en langue étrangère, réalisé par un dispositif informatique, comprenant les étapes consistant à : obtenir l'énoncé en langue étrangère ; obtenir un texte en langue étrangère correspondant à l'énoncé en langue étrangère ; et évaluer la difficulté d'écoute de l'énoncé en langue étrangère sur la base de l'énoncé en langue étrangère et du texte en langue étrangère.
PCT/KR2022/005165 2021-08-16 2022-04-11 Procédé, dispositif et programme d'évaluation de la difficulté d'écoute d'un énoncé en langue étrangère WO2023022323A1 (fr)

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
KR10-2021-0107761 2021-08-16
KR20210107761 2021-08-16
KR20210125411 2021-09-22
KR10-2021-0125411 2021-09-22
KR20210126013 2021-09-23
KR10-2021-0126013 2021-09-23

Publications (1)

Publication Number Publication Date
WO2023022323A1 true WO2023022323A1 (fr) 2023-02-23

Family

ID=85239556

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/005165 WO2023022323A1 (fr) 2021-08-16 2022-04-11 Procédé, dispositif et programme d'évaluation de la difficulté d'écoute d'un énoncé en langue étrangère

Country Status (1)

Country Link
WO (1) WO2023022323A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007249755A (ja) * 2006-03-17 2007-09-27 Ibm Japan Ltd ドキュメントを理解する難易度を評価するシステムおよびその方法
JP4736476B2 (ja) * 2005-03-04 2011-07-27 富士ゼロックス株式会社 翻訳費用の見積りを行う装置および方法
KR20180129166A (ko) * 2017-05-25 2018-12-05 주식회사 스터디맥스 학습자의 음성입력을 이용한 학습 시스템 및 그 방법
JP6468584B2 (ja) * 2014-08-18 2019-02-13 弘信 岡崎 外国語の難易度判定装置
KR101981332B1 (ko) * 2012-12-26 2019-05-23 주식회사 케이티 청취 난이도를 이용하여 학습 데이터를 생성하는 서버 및 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4736476B2 (ja) * 2005-03-04 2011-07-27 富士ゼロックス株式会社 翻訳費用の見積りを行う装置および方法
JP2007249755A (ja) * 2006-03-17 2007-09-27 Ibm Japan Ltd ドキュメントを理解する難易度を評価するシステムおよびその方法
KR101981332B1 (ko) * 2012-12-26 2019-05-23 주식회사 케이티 청취 난이도를 이용하여 학습 데이터를 생성하는 서버 및 방법
JP6468584B2 (ja) * 2014-08-18 2019-02-13 弘信 岡崎 外国語の難易度判定装置
KR20180129166A (ko) * 2017-05-25 2018-12-05 주식회사 스터디맥스 학습자의 음성입력을 이용한 학습 시스템 및 그 방법

Similar Documents

Publication Publication Date Title
WO2020145439A1 (fr) Procédé et dispositif de synthèse vocale basée sur des informations d'émotion
WO2020190050A1 (fr) Appareil de synthèse vocale et procédé associé
WO2020190054A1 (fr) Appareil de synthèse de la parole et procédé associé
CN107481713B (zh) 一种混合语言语音合成方法及装置
WO2020231181A1 (fr) Procédé et dispositif pour fournir un service de reconnaissance vocale
WO2019139431A1 (fr) Procédé et système de traduction de parole à l'aide d'un modèle de synthèse texte-parole multilingue
WO2019139430A1 (fr) Procédé et appareil de synthèse texte-parole utilisant un apprentissage machine, et support de stockage lisible par ordinateur
Ramani et al. A common attribute based unified HTS framework for speech synthesis in Indian languages
WO2020027619A1 (fr) Procédé, dispositif et support d'informations lisible par ordinateur pour la synthèse vocale à l'aide d'un apprentissage automatique sur la base d'une caractéristique de prosodie séquentielle
WO2019139428A1 (fr) Procédé de synthèse vocale à partir de texte multilingue
US8751230B2 (en) Method and device for generating vocabulary entry from acoustic data
WO2015005679A1 (fr) Procédé, appareil et système de reconnaissance vocale
KR20110068490A (ko) 외국어 학습 장치 및 그 제공 방법
KR101819459B1 (ko) 음성 인식 오류 수정을 지원하는 음성 인식 시스템 및 장치
WO2018174397A1 (fr) Dispositif électronique et procédé de commande
WO2021029643A1 (fr) Système et procédé de modification d'un résultat de reconnaissance vocale
WO2020209647A1 (fr) Procédé et système pour générer une synthèse texte-parole par l'intermédiaire d'une interface utilisateur
KR102140391B1 (ko) 검색 방법 및 이 방법을 적용하는 전자 장치
JPWO2018043138A1 (ja) 情報処理装置および情報処理方法、並びにプログラム
EP3818518A1 (fr) Appareil électronique et son procédé de commande
WO2021085661A1 (fr) Procédé et appareil de reconnaissance vocale intelligent
CN114255738A (zh) 语音合成方法、装置、介质及电子设备
WO2023022323A1 (fr) Procédé, dispositif et programme d'évaluation de la difficulté d'écoute d'un énoncé en langue étrangère
WO2018074658A1 (fr) Terminal et procédé de mise en œuvre d'un effet de sous-titrage hybride
WO2023096274A1 (fr) Système pour l'apprentissage simultané de plusieurs langues

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: 22858565

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE