1. A pronunciation error detection system comprising: a speech recognition module configured to receive speech input from a user; a language model module configured to recognize and interpret the speech input; an error detection module configured to compare the recognized speech input with a database of correct pronunciations, and identify pronunciation errors; and a feedback module configured to provide feedback to the user on the detected pronunciation errors.

2. The system of claim 1, wherein the language model module comprises a machine learning algorithm trained on a corpus of correctly pronounced words.

3. The system of claim 1, wherein the error detection module comprises a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.

4. The system of claim 1, wherein the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.

5. The system of claim 1, wherein the feedback module provides feedback to the user in real-time during speech input.

6. The system of claim 1, further comprising a database of common pronunciation errors for a specific language, wherein the error detection module uses the database to identify pronunciation errors specific to that language.

7. A method for detecting pronunciation errors in speech input, comprising: receiving speech input from a user; recognizing and interpreting the speech input using a language model module; comparing the recognized speech input with a database of correct pronunciations using an error detection module, and identifying pronunciation errors; and providing feedback to the user on the detected pronunciation errors using a feedback module.

8. The method of claim 7, wherein the language model module comprises a machine learning algorithm trained on a corpus of correctly pronounced words. 9.The method of claim 7, wherein the error detection module comprises a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.

10. The method of claim 7, wherein the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.   INCORRECT PRONUNCIATION IDENTIFICATION FRAMEWORK Abstract A pronunciation error detection system may be included in certain embodiments of the current disclosure. This system may contain a voice recognition module that is set up to take input from a user in the form of spoken words. A language model module that is set up to detect and interpret the voice input may also be included in embodiments. A pronunciation error detection module may also be included in certain embodiments. This module's purpose is to compare the recognised voice input with a database of accurate pronunciations in order to find mistakes in the user's pronunciation. In certain embodiments, there is additionally a feedback module that may be set to give the user with feedback on any pronunciation mistakes that are found. Fig. 1 , Claims:Claims :

1. A pronunciation error detection system comprising: a speech recognition module configured to receive speech input from a user; a language model module configured to recognize and interpret the speech input; an error detection module configured to compare the recognized speech input with a database of correct pronunciations, and identify pronunciation errors; and a feedback module configured to provide feedback to the user on the detected pronunciation errors.

2. The system of claim 1, wherein the language model module comprises a machine learning algorithm trained on a corpus of correctly pronounced words.

3. The system of claim 1, wherein the error detection module comprises a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.

4. The system of claim 1, wherein the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.

5. The system of claim 1, wherein the feedback module provides feedback to the user in real-time during speech input.

6. The system of claim 1, further comprising a database of common pronunciation errors for a specific language, wherein the error detection module uses the database to identify pronunciation errors specific to that language.

7. A method for detecting pronunciation errors in speech input, comprising: receiving speech input from a user; recognizing and interpreting the speech input using a language model module; comparing the recognized speech input with a database of correct pronunciations using an error detection module, and identifying pronunciation errors; and providing feedback to the user on the detected pronunciation errors using a feedback module.

8. The method of claim 7, wherein the language model module comprises a machine learning algorithm trained on a corpus of correctly pronounced words. 9.The method of claim 7, wherein the error detection module comprises a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.

10. The method of claim 7, wherein the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.

Description:INCORRECT PRONUNCIATION IDENTIFICATION FRAMEWORK
Field of the Invention
[0001] The present invention relates to a language learning system. More particularly, embodiments of the present invention relate to information processing technology to determine incorrect pronunciation identification and suggesting appropriate solution to improve speaking skill of speaker.
Background
[0002] The background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] Pronunciation is an essential aspect of communication, as it can greatly impact the clarity, accuracy, and effectiveness of conveying meaning. Poor pronunciation can result in miscommunication, misunderstandings, and even embarrassment. It can also hinder language learners' ability to communicate effectively in academic, professional, or social settings. Moreover, accurate pronunciation is essential for effective language learning. Studies have shown that learners who master correct pronunciation have better comprehension, retention, and overall language proficiency compared to those who do not. Additionally, proficiency in pronunciation can enhance learners' confidence and motivation to continue learning the language. In many languages, including English, the pronunciation of words can be influenced by various factors such as accent, dialect, and regional differences, making it challenging for non-native speakers to master correct pronunciation. This can be particularly problematic in contexts where accurate communication is critical, such as in academic and professional settings, where language learners may struggle to convey complex ideas and concepts.
[0004] Given these considerations, there is a growing need for tools which can help language learners and speakers improve their communication skills. Patent literature disclosed various technique for language learning. Few of them are discussed below.
[0005] The WO2021000756A1 (By: CINDY LIEN) - An English text spelling and reading annotation method, a spelling and reading method and apparatus thereof, a storage medium, and an electronic device. The English text spelling and reading annotation method comprises: obtaining English text data to be processed and pronunciation data of the English text data (S110); segmenting the English text data into at least one spelling and reading unit (S120), the spelling and reading unit comprising one or more letters forming a basic pronunciation unit or a combined pronunciation unit; according to the pronunciation data, respectively performing pronunciation annotation on at least one spelling and reading unit, so as to enable the pronunciation annotation to be fused in the English text data (S130); and providing the English text data which fuses the pronunciation annotation for the spelling and reading units, so as to enable a reader to directly read the English text by means of the pronunciation annotation (S140), thereby effectively helping an English learner to spell and read the English text by using English Phonics, and improving the English learning efficiency.
[0006] The KR10-2014-0122172A (By: CHO,KeonHee) - The present invention relates to language learning using a touch screen for learning the Hangul in various ways according to touched patterns. The present invention relates to a method and a system for learning a language using a touch screen. The method comprises: a step of detecting the touch of a user; a step of analyzing information on the touched patterns and spaces of the user; a step of selecting a learning function according to the touched patterns and spaces of the user; a step of searching learning data related with the touched space information in learning DB according to the selected learning function; and a step of providing the searched learning data to the user through a sound output or an image output. The present invention enables local residents and foreigners who want to learn the Hangul to conveniently learn letters, words, syntactic words, and sentences through the interface of a touch screen; thereby improving Hangul learning efficiency and enabling intensive learning.
[0007] The CN101465078A (By: CAI WENSHENG) - The invention relates to an English phonetics teaching auxiliary tool and an industrial application method thereof. The method comprises the following steps: (1), an alphabet for three kinds of corresponding relations of English, Chinese Pinyin and Latin is obtained; (2), the letters with consonant in pronunciation are respectively combined together, after the finals, i.e. the vowels, are removed, a pure consonant list or initial list is formed; (3), a Yunmu list or vowel list is formed by vowel letters and a combination thereof, vowel letters, semivowel letter and a combination thereof and whole identify centering vowels; (4), the word tonic accent symbols and the long and the short tone symbols are marked; and the recorded pronunciation information is accepted by applying an electronic device for the teaching auxiliary tool, or after the words are input to the electronic device letter by letter, the words are spelled and displays according to the steps (1), (2) and (3), or the words are pronounced syllable by syllable. The invention is simple and feasible, and achieves the purposes that the student can pronounce the letters or the words when encountering the letters or the words, spell out the corresponding words after listening to the sound and read above 90 percent of words by the student self. Therefore, the word learning ability, the memory ability and the listening, speaking, reading and writing abilities of the students are obviously enhanced.
[0008] However, known solutions are non-efficient and required sophisticated technological investment. Thus, there is need in this domain.

Summary
[0009] The following presents a simplified summary of various aspects of this disclosure in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements nor delineate the scope of such aspects. Its purpose is to present some concepts of this disclosure in a simplified form as a prelude to the more detailed description that is presented later.
[00010] The following paragraphs provide additional support for the claims of the subject application.
[00011] The present invention relates to a language learning system. More particularly, embodiments of the present invention relate to information processing technology to determine incorrect pronunciation identification and suggesting appropriate solution to improve speaking skill of speaker.
[00012] Embodiments of the present disclosure may include a pronunciation error detection system including a speech recognition module configured to receive speech input from a user. Embodiments may also include a language model module configured to recognize and interpret the speech input. Embodiments may also include an error detection module configured to compare the recognized speech input with a database of correct pronunciations, and identify pronunciation errors. Embodiments may also include a feedback module configured to provide feedback to the user on the detected pronunciation errors.
[00013] In some embodiments, the language model module may include a machine learning algorithm trained on a corpus of correctly pronounced words. In some embodiments, the error detection module may include a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.
[00014] In some embodiments, the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal. In some embodiments, the feedback module provides feedback to the user in real-time during speech input. In some embodiments, the system may include a database of common pronunciation errors for a specific language. In some embodiments, the error detection module uses the database to identify pronunciation errors specific to that language.
[00015] Embodiments of the present disclosure may also include a method for detecting pronunciation errors in speech input, upon receiving the speech input from a user. Embodiments may also include recognizing and interpreting the speech input using a language model module. Embodiments may also include comparing the recognized speech input with a database of correct pronunciations using an error detection module, and identifying pronunciation errors. Embodiments may also include providing feedback to the user on the detected pronunciation errors using a feedback module.
[00016] In some embodiments, the language model module may include a machine learning algorithm trained on a corpus of correctly pronounced words. In some embodiments, the error detection module may include a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module. In some embodiments, the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.
Brief Description of the Drawings
[00017] The features and advantages of the present disclosure would be more clearly understood from the following description taken in conjunction with the accompanying drawings in which:
[00018] FIG. 1 is a block diagram illustrating a pronunciation error detection system, according to some embodiments of the present disclosure.
[00019] FIG. 2 is a flowchart illustrating a method for detecting pronunciation errors in speech input, according to some embodiments of the present disclosure.

Detailed Description
[00020] In the following detailed description of the invention, reference is made to the accompanying drawings that form a part hereof, and in which is shown, by way of illustration, specific embodiments in which the invention may be practiced. In the drawings, like numerals describe substantially similar components throughout the several views. These embodiments are described in sufficient detail to claim those skilled in the art to practice the invention. Other embodiments may be utilized and structural, logical, and electrical changes may be made without departing from the scope of the present invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is defined only by the appended claims and equivalents thereof.
[00021] The use of the terms “a” and “an” and “the” and “at least one” and similar referents in the context of describing the invention (especially in the context of the following claims) are to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. The use of the term “at least one” followed by a list of one or more items (for example, “at least one of A and B”) is to be construed to mean one item selected from the listed items (A or B) or any combination of two or more of the listed items (A and B), unless otherwise indicated herein or clearly contradicted by context. The terms “comprising,” “having,” “including,” and “containing” are to be construed as open-ended terms (i.e., meaning “including, but not limited to,”) unless otherwise noted. Recitation of ranges of values herein are merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g., “such as”) provided herein, is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention unless otherwise claimed. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the invention.
[00022] The present invention relates to a language learning system. More particularly, embodiments of the present invention relate to information processing technology to determine incorrect pronunciation identification and suggesting appropriate solution to improve speaking skill of speaker.
[00023] FIG. 1 is a block diagram that describes a pronunciation error detection system 100, according to some embodiments of the present disclosure. In some embodiments, the pronunciation error detection system 100 may include a speech recognition module 110 configured to receive speech input from a user, a language model module 120 configured to recognize and interpret the speech input, and a feedback module 140 configured to provide feedback to the user based on the detected pronunciation errors. The pronunciation error detection system 100 may also include an error detection module 130 configured to compare the recognized speech input with a database of correct pronunciations, and identify pronunciation errors.
[00024] In some embodiments, the language model module 120 may include a machine learning algorithm trained on a corpus of correctly pronounced words. In some embodiments, the error detection module 130 may include a neural network trained to detect pronunciation errors based on input from the speech recognition module 110 and the language model module 120. In some embodiments, the feedback module 140 may provide feedback to the user in the form of a visual display, an auditory signal, or a tactile signal. In some embodiments, the feedback module 140 may provide feedback to the user in real-time during speech input. In some embodiments, the pronunciation error detection system 100 may include a database of common pronunciation errors for a specific language. The error detection module 130 may use the database to identify pronunciation errors specific to that language.
[00025] FIG. 2 is a flowchart that describes a method for detecting pronunciation errors in speech input, according to some embodiments of the present disclosure. In some embodiments, at 210, the method may include receiving speech input from a user. At 220, the method may include recognizing and interpreting the speech input using a language model module. At 230, the method may include comparing the recognized speech input with a database of correct pronunciations using an error detection module, and identifying pronunciation errors. At 240, the method may include providing feedback to the user on the detected pronunciation errors using a feedback module.
[00026] In some embodiments, the language model module 120 may comprise a machine learning algorithm trained on a corpus of correctly pronounced words. In some embodiments, the error detection module 130 may comprise a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module 110 and the language model module. In some embodiments, the feedback module 140 may provide feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.
[00027] The pronunciation error detection system 100 may contain a voice recognition module that is set up to take input from a user in the form of spoken words. The language model module 120 that is set up to detect and interpret the voice input may also be included in embodiments. A pronunciation error detection module may also be included in certain embodiments. The pronunciation error detection module purpose is to compare the recognised voice input with a database of accurate pronunciations in order to find mistakes in the user's pronunciation. In certain embodiments, there is additionally the feedback module 140 that may be set to give the user with feedback on any pronunciation mistakes that are found.
[00028] The language model module 120 may, in certain implementations, comprise a machine learning algorithm that has been trained on a corpus of properly uttered words. The voice recognition module and the language model module 120 both provide information to the error detection module, which may comprise a neural network that has been trained to recognise incorrect pronunciations based on the information provided by both modules.
[00029] The user may get input from the feedback module 140 in the form of a visual display, an aural signal, or a tactile signal, according to some implementations of this module. In some implementations, the feedback module 140 communicates with the user in real time while the user is in the process of providing voice input. A database of frequent pronunciation mistakes for a certain language could be included in the system according to one implementation of the system. In some implementations, the error detection module 130 consults the database in order to locate incorrect pronunciations that are peculiar to the target language.
[00030] A method for identifying pronunciation problems in voice input may also be included in embodiments of the present disclosure. This method may involve the step of receiving speech input from a user. The language model module 120 may also be used in certain embodiments in order to recognise and understand the user's spoken input. Some embodiments further comprise recognising pronunciation problems by comparing the voice input that was detected to a database of accurate pronunciations using an error detection module. In certain embodiments, there is also the possibility of employing the feedback module 140 to provide the user with feedback on the identified incorrect pronunciations.
[00031] The language model module 120 may, in certain implementations, comprise a machine learning algorithm that has been trained on a corpus of properly uttered words. The voice recognition module and the language model module 120 both provide information to the error detection module, which may comprise a neural network that has been trained to recognise incorrect pronunciations based on the information provided by both modules. The user may get input from the feedback module 140 in the form of a visual display, an aural signal, or a tactile signal, according to some implementations of this module.
[00032] Example embodiments herein have been described above with reference to block diagrams and flowchart illustrations of methods and apparatuses. It will be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by various means including hardware, software, firmware, and a combination thereof. For example, in one embodiment, each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations can be implemented by computer program instructions. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functions specified in the flowchart block or blocks.
[00033] Throughout the present disclosure, the term ‘processing means’ or ‘microprocessor’ or ‘processor’ or ‘processors’ includes, but is not limited to, a general purpose processor (such as, for example, a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a microprocessor implementing other types of instruction sets, or a microprocessor implementing a combination of types of instruction sets) or a specialized processor (such as, for example, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), or a network processor).
[00034] The term “non-transitory storage device” or “storage” or “memory,” as used herein relates to a random access memory, read only memory and variants thereof, in which a computer can store data or software for any duration.
[00035] Operations in accordance with a variety of aspects of the disclosure is described above would not have to be performed in the precise order described. Rather, various steps can be handled in reverse order or simultaneously or not at all.
[00036] While several implementations have been described and illustrated herein, a variety of other means and/or structures for performing the function and/or obtaining the results and/or one or more of the advantages described herein may be utilized, and each of such variations and/or modifications is deemed to be within the scope of the implementations described herein. More generally, all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and/or configurations will depend upon the specific application or applications for which the teachings is/are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific implementations described herein. It is, therefore, to be understood that the foregoing implementations are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, implementations may be practiced otherwise than as specifically described and claimed. Implementations of the present disclosure are directed to each individual feature, system, article, material, kit, and/or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and/or methods, if such features, systems, articles, materials, kits, and/or methods are not mutually inconsistent, is included within the scope of the present disclosure.

 

Claims
I/We Claim:
1. A pronunciation error detection system comprising:

a speech recognition module configured to receive speech input from a user;

a language model module configured to recognize and interpret the speech input;

an error detection module configured to compare the recognized speech input with a database of correct pronunciations, and identify pronunciation errors; and

a feedback module configured to provide feedback to the user on the detected pronunciation errors.

2. The system of claim 1, wherein the language model module comprises a machine learning algorithm trained on a corpus of correctly pronounced words.

3. The system of claim 1, wherein the error detection module comprises a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.

4. The system of claim 1, wherein the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.

5. The system of claim 1, wherein the feedback module provides feedback to the user in real-time during speech input.

6. The system of claim 1, further comprising a database of common pronunciation errors for a specific language, wherein the error detection module uses the database to identify pronunciation errors specific to that language.

7. A method for detecting pronunciation errors in speech input, comprising:

receiving speech input from a user;

recognizing and interpreting the speech input using a language model module;

comparing the recognized speech input with a database of correct pronunciations using an error detection module, and identifying pronunciation errors; and

providing feedback to the user on the detected pronunciation errors using a feedback module.

8. The method of claim 7, wherein the language model module comprises a machine learning algorithm trained on a corpus of correctly pronounced words.

9.The method of claim 7, wherein the error detection module comprises a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.

10. The method of claim 7, wherein the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.
 

INCORRECT PRONUNCIATION IDENTIFICATION FRAMEWORK
Abstract
A pronunciation error detection system may be included in certain embodiments of the current disclosure. This system may contain a voice recognition module that is set up to take input from a user in the form of spoken words. A language model module that is set up to detect and interpret the voice input may also be included in embodiments. A pronunciation error detection module may also be included in certain embodiments. This module's purpose is to compare the recognised voice input with a database of accurate pronunciations in order to find mistakes in the user's pronunciation. In certain embodiments, there is additionally a feedback module that may be set to give the user with feedback on any pronunciation mistakes that are found.

Fig. 1 , Claims:Claims
I/We Claim:
1. A pronunciation error detection system comprising:

a speech recognition module configured to receive speech input from a user;

a language model module configured to recognize and interpret the speech input;

an error detection module configured to compare the recognized speech input with a database of correct pronunciations, and identify pronunciation errors; and

a feedback module configured to provide feedback to the user on the detected pronunciation errors.

2. The system of claim 1, wherein the language model module comprises a machine learning algorithm trained on a corpus of correctly pronounced words.

3. The system of claim 1, wherein the error detection module comprises a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.

4. The system of claim 1, wherein the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.

5. The system of claim 1, wherein the feedback module provides feedback to the user in real-time during speech input.

6. The system of claim 1, further comprising a database of common pronunciation errors for a specific language, wherein the error detection module uses the database to identify pronunciation errors specific to that language.

7. A method for detecting pronunciation errors in speech input, comprising:

receiving speech input from a user;

recognizing and interpreting the speech input using a language model module;

comparing the recognized speech input with a database of correct pronunciations using an error detection module, and identifying pronunciation errors; and

providing feedback to the user on the detected pronunciation errors using a feedback module.

8. The method of claim 7, wherein the language model module comprises a machine learning algorithm trained on a corpus of correctly pronounced words.

9.The method of claim 7, wherein the error detection module comprises a neural network that has been trained to detect pronunciation errors based on input from the speech recognition module and the language model module.

10. The method of claim 7, wherein the feedback module provides feedback to the user in the form of a visual display, an auditory signal, or a tactile signal.