A translation machine and a translation method
By identifying and translating key features in children's audio data, combined with a book library and environmental detection, the accuracy and applicability of same-language translation were achieved. This solved the problem of existing translation machines having difficulty understanding content narrated by young children, and improved the performance and user experience of the translation machine.
Patent Information
- Application Number
- CN202210882818.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-26
- Publication Date
- 2025-10-24
- Estimated Expiration
- 2042-07-26
AI Technical Summary
Existing translation machines can only translate between languages, resulting in poor translation performance, especially when young children are telling stories, which family members or strangers cannot understand accurately.
The system uses a first acquisition unit to collect children's audio data, a first recognition unit to identify key audio features and convert them into text content, a pre-acquired book library to find target sentences, and a translation unit to play the translated text content. The translation process is optimized by combining environmental detection and image recognition.
The translation performance of the translator has been improved, ensuring that the content spoken by young children is accurately understood in the same language, reducing misunderstandings and crying, and enhancing their enthusiasm for reading.
Smart Images
Figure CN115273834B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of translation, and particularly relates to a translation machine and a translation method. BACKGROUND
[0002] Translation is a scene frequently used by people in daily life. In daily life, on-site translation is mainly adopted by personnel, and in some special scenes, electronic devices are also supported for translation. However, all electronic devices currently involve translation between languages, such as translation from Chinese to English and translation from English to Chinese. Since only translation between languages can be performed, the translation performance of the current translation machine is poor. SUMMARY
[0003] The application provides a translation machine and a translation method, which can solve the problem of poor translation performance of the translation machine.
[0004] The application provides a translation machine, which comprises:
[0005] A first acquisition unit is configured to acquire first audio data of a baby;
[0006] A first identification unit is configured to identify a first key audio feature in the first audio data, the first key audio feature being an audio feature capable of accurately identifying text content, and the first audio data having an audio feature incapable of identifying text content;
[0007] A second identification unit is configured to convert the first key audio feature into first key text content, and based on the first key text content, find a target baby book including the first key text content in a pre-acquired book library, and identify a first target sentence in the target baby book matching the first key text content;
[0008] A first translation unit is configured to take the first target sentence as first translation text content of the first audio data;
[0009] A playing unit is configured to play second audio data corresponding to the first translation text content.
[0010] The application further provides a translation method, which comprises:
[0011] Acquiring first audio data of a baby;
[0012] Identifying a first key audio feature in the first audio data, the first key audio feature being an audio feature capable of accurately identifying text content, and the first audio data having an audio feature incapable of identifying text content;
[0013] convert the first key audio feature into first key text content, and based on the first key text content, find a target children's book including the first key text content in a pre-acquired book library, and identify a first target sentence in the target children's book matching the first key text content;
[0014] convert the first target sentence into first translated text content of the first audio data;
[0015] play second audio data corresponding to the first translated text content.
[0016] The application further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement steps in the translation method.
[0017] In the embodiment of the application, the translation machine comprises: a first acquisition unit configured to acquire first audio data of a child; a first identification unit configured to identify a first key audio feature in the first audio data, the first key audio feature being an audio feature that can accurately identify text content, and the first audio data having audio features that cannot identify text content; a second identification unit configured to convert the first key audio feature into first key text content, and based on the first key text content, find a target children's book including the first key text content in a pre-acquired book library, and identify a first target sentence in the target children's book matching the first key text content; a first translation unit configured to convert the first target sentence into first translated text content of the first audio data; and a playing unit configured to play second audio data corresponding to the first translated text content. In the embodiment of the application, the translation machine can translate audio data of a child, thereby improving the translation performance of the translation machine. BRIEF DESCRIPTION OF DRAWINGS
[0018] Figure 1 is a structural schematic diagram of a translation machine provided by the embodiment of the application;
[0019] Figure 2 is a structural schematic diagram of a translation machine provided by the embodiment of the application;
[0020] Figure 3 is a structural schematic diagram of a translation machine provided by the embodiment of the application;
[0021] Figure 4 is a structural schematic diagram of a translation machine provided by the embodiment of the application;
[0022] Figure 5 is a structural schematic diagram of a translation machine provided by the embodiment of the application;
[0023] Figure 6 It is a flowchart of a translation method provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0024] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.
[0025] Figure 1 This is a structural diagram of a translation machine provided by an embodiment of the present invention. Figure 1 Shown include:
[0026] The first collecting unit 101 is used to collect first audio data of the child;
[0027] The first recognition unit 102 is configured to recognize a first key audio feature in the first audio data, where the first key audio feature is an audio feature that can accurately recognize text content, and the first audio data may contain audio features that cannot recognize text content;
[0028] a second recognition unit 103 configured to convert the first key audio feature into a first key text content, and based on the first key text content, search a pre-acquired book library for a target children's book that includes the first key text content, and identify a first target sentence in the target children's book that matches the first key text content;
[0029] A first translation unit 104 is configured to use the first target sentence as a first translated text content of the first audio data;
[0030] The playing unit 105 is configured to play the second audio data corresponding to the first translated text content.
[0031] The above-mentioned first audio data can be the audio data spoken by a child when telling a story from a book. For example, a child reads a book at home and wants to tell the content of the book to his or her family when he or she goes to another place, such as his or her hometown. However, since the audio of the child's speech is not very accurate or the speaking speed is too fast, the family may not be able to hear clearly. In this way, the translation machine provided by the present invention can translate the child's audio.
[0032] The first key audio feature can be an audio feature in the first audio data that can accurately identify specific text content, and the audio feature is also an audio feature that can be clearly heard by others, so that the specific content told by the child can be identified through the text content corresponding to the audio feature, so that the audio feature that cannot identify the text content can be translated. To enable other personnel to clearly hear the specific content told by the child.
[0033] The book library can be a database established for the child alone, for example, when the child reads at home, the books read by the child are recorded in time, and the database is established, so that the books told by the child can be accurately and quickly queried.
[0034] In the embodiment of the application, the audio data of the child can be translated, and the translation is in the same language, so that the translation performance of the translation machine can be improved. In addition, since the content told by the child is translated, the possibility that the child cries because others cannot understand the content told by the child can be avoided, the enthusiasm of the child in reading can be improved, and the problem that the child loses the enthusiasm of reading because others cannot clearly hear the content told by the child can be avoided.
[0035] In the embodiment of the application, the translation machine can be a handheld translation machine or a wearable translation machine.
[0036] In one embodiment, as shown in Figure 2 The translation machine further comprises:
[0037] The second acquisition unit 106 is configured to acquire third audio data of the child, the third audio data being audio data that is continuous with the first audio data and has a pause interval;
[0038] The third identification unit 107 is configured to identify a second key audio feature in the third audio data, the second key audio feature being an audio feature that can accurately identify text content, and the second audio data having an audio feature that cannot identify text content;
[0039] The second identification unit 103 is specifically configured to convert the first key audio feature into first key text content, and convert the second key audio feature into second key text content, and based on the first key text content and the second key text content, find a target children's book including the first key text content and the second key text content in a pre-acquired book library, identify a first target sentence in the target children's book that matches the first key text content, and a second target sentence in the target children's book that matches the second key text content, the first target sentence and the second target sentence being consecutive sentences in the target children's book.
[0040] The first translation unit 104 is specifically configured to take the first target sentence as the first translated text content of the first audio data, and take the second target sentence as the second translated text content of the third audio data.
[0041] The playing unit 105 is further configured to play the fourth audio data corresponding to the second translated text content.
[0042] The pause interval represents the pause between different sentences told by the infant.
[0043] The first target sentence in the target infant book that matches the first key text content is the first target sentence in the target infant book that includes the first key text content.
[0044] The first target sentence in the target infant book that matches the second key text content is the first target sentence in the target infant book that includes the second key text content.
[0045] In this way, the first translated text content and the second translated text content can be accurately determined through the two target sentences, because the possibility that the two sentences match the audio told by the infant but are not continuous can be avoided, thereby improving the accuracy of translation.
[0046] In an embodiment, as shown in Figure 3 The translation machine further includes:
[0047] The detection unit 108 is configured to detect whether the current environment satisfies an infant audio translation condition, wherein the infant audio translation condition includes:
[0048] The current location does not belong to a pre-recorded resident location of the infant;
[0049] The current environment includes personnel other than the pre-recorded associated family members of the infant;
[0050] The first collection unit 101 is specifically configured to collect first audio data of the infant when the current environment satisfies the infant audio translation condition.
[0051] The pre-recorded resident location can be the home of the child. If it is the home of the child, no translation is needed because when the child narrates at home, the parents are present and can understand the content of the narration based on the books the child has read, even if the child does not narrate clearly. Therefore, no translation is needed at the resident location. Outside the resident location, the child may narrate to other people, such as grandparents or other people at home, who do not know which books the child has read and are not familiar with the child's way of speaking. Therefore, the content of the narration may not be clear to these people, and translation is needed.
[0052] The people other than the associated family members of the child are people who have less contact with the child. These people do not know which books the child has read and are not familiar with the child's way of speaking. Therefore, the content of the narration may not be clear to these people, and translation is needed.
[0053] In this embodiment, translation is only performed in specific scenarios, so that the power consumption of translation can be saved,
[0054] In an embodiment, as shown in Figure 4 The translation machine further includes:
[0055] The collection unit 109 is configured to collect image information of the child, identify whether the image information indicates that the child is reading a book, extract book feature information or a book name from the image information when the image information indicates that the child is reading a book, search for the book currently read by the child in a network based on the book feature information or the book name, and obtain an electronic book corresponding to the book, and store the electronic book in the book library.
[0056] The collection unit can automatically collect the book currently read by the child during reading of the book, search for the book currently read by the child in the network based on the extracted feature information or book name, and record the content of the book in the book library, so that the audio data of the child can be accurately translated during translation.
[0057] In an embodiment, the collection unit is further configured to collect a set of audio data of the child during reading of the book, and a book image corresponding to each audio data in the book, establish a mapping relationship between the audio data and the book image, and store the mapping relationship in the book library. The book image corresponding to each audio data in the book is a current image of the book displayed by the image information when the child outputs the audio data.
[0058] The second identifying unit 103 is specifically configured to:
[0059] convert the first key audio feature into first key text content, and based on the first key text content, find a target children's book including the first key text content in a pre-acquired book library, identify a candidate sentence in the target children's book matching the first key text content, and extract a book page image including the candidate sentence in the target children's book; and match the book page image with a target book image, when the book page image matches the target book image, take the candidate sentence as the first target sentence; wherein the target book image is a book image having a mapping relationship with historical audio data matching the first audio data in the audio data set and extracted based on the mapping relationship.
[0060] The historical audio data matching the first audio data can be that the audio data told by the children when translating is the same or similar to the audio data told by the children when reading the book, that is, the same text content is told.
[0061] This embodiment can establish the mapping relationship between the audio data of the children when reading the book and the book image, so that when translating, the candidate sentence in the target children's book found and the corresponding image content in the target book can be matched with the pre-recorded book image content, when matching, it means that the image content of the candidate sentence and the book image of the audio content told by the children when reading are the same, so the candidate sentence can be determined as the first target sentence, and the accuracy of translation can be improved.
[0062] In an embodiment, as shown in Figure 5 The translation machine further comprises:
[0063] The third acquisition unit 110 is configured to acquire fifth audio data of the children, the fifth audio data including M pieces of audio data before the first audio data and N pieces of audio data after the first audio data, M and N being positive integers.
[0064] The fourth identifying unit 111 is configured to identify the speech rate of the fifth audio data and the first audio data, and compare the speech rate with a preset speech rate threshold.
[0065] The second translation unit 112 is configured to extract M key audio features of the M pieces of audio data, convert the M key audio features into M key text contents, identify M target sentences in the target children's book that match the M key text contents based on the M key text contents, and take the M target sentences as translated text contents of the M pieces of audio data; and when the speech rate reaches a preset speech rate threshold, identify N target sentences in the target children's book that are continuous with the first target sentence, and take the N target sentences as translated text contents of the N pieces of audio data.
[0066] The playing unit 105 is further configured to play audio data corresponding to the translated text contents of the M pieces of audio data, and play audio data corresponding to the translated text contents of the N pieces of audio data.
[0067] The speech rate reaching the preset speech rate threshold can be understood as that the book content told by the children is relatively fast, and the relatively fast telling often indicates that the children are particularly familiar with the content of the book, that is, the book content currently told by the children is accurate, but the children cannot pronounce standardly, so some people may not be able to hear clearly.
[0068] In this embodiment, when the speech rate reaches the preset speech rate threshold, some sentences after the sentences can be directly found based on the translated front sentences, and the sentences in the book corresponding to the audio data after the sentences can be found, so that the translation calculation amount can be saved, and the translation efficiency can be improved.
[0069] In this embodiment, when the speech rate does not reach the preset speech rate threshold, the N pieces of audio data can be translated sentence by sentence.
[0070] In the embodiment of the present application, the translation machine comprises: a first acquisition unit configured to acquire first audio data of children; a first identification unit configured to identify first key audio features in the first audio data, the first key audio features being audio features that can accurately identify text contents, and the first audio data having audio features that cannot identify text contents; a second identification unit configured to convert the first key audio features into first key text contents, and based on the first key text contents, find a target children's book including the first key text contents in a pre-acquired book library, and identify a first target sentence in the target children's book that matches the first key text contents; a first translation unit configured to take the first target sentence as first translated text contents of the first audio data; and a playing unit configured to play second audio data corresponding to the first translated text contents. In the embodiment of the present application, the translation machine can translate the audio data of the children, so that the translation performance of the translation machine can be improved.
[0071] Figure 6 is a flowchart of a translation method provided by an embodiment of the present application, as shown in Figure 6
[0072] 601, collecting first audio data of a young child;
[0073] 602, identifying a first key audio feature in the first audio data, the first key audio feature being an audio feature that can accurately identify text content, and the first audio data having audio features that cannot identify text content;
[0074] 603, converting the first key audio feature into first key text content, and based on the first key text content, searching a pre-acquired book library for a target young child book that includes the first key text content, and identifying a first target sentence in the target young child book that matches the first key text content;
[0075] 604, taking the first target sentence as first translation text content of the first audio data;
[0076] 605, playing second audio data corresponding to the first translation text content.
[0077] Optionally, the method further includes:
[0078] collecting third audio data of the young child, the third audio data being audio data that is continuous with the first audio data and has a pause interval;
[0079] identifying a second key audio feature in the third audio data, the second key audio feature being an audio feature that can accurately identify text content, and the second audio data having audio features that cannot identify text content;
[0080] the converting the first key audio feature into first key text content, and based on the first key text content, searching a pre-acquired book library for a target young child book that includes the first key text content, and identifying a first target sentence in the target young child book that matches the first key text content, includes:
[0081] convert the first key audio feature into first key text content and the second key audio feature into second key text content, and based on the first key text content and the second key text content, find a target children's book including the first key text content and the second key text content in a pre-acquired book library, and identify a first target sentence in the target children's book matching the first key text content and a second target sentence in the target children's book matching the second key text content, the first target sentence and the second target sentence being consecutive sentences in the target children's book;
[0082] The first target sentence as the first translation text content of the first audio data includes:
[0083] The first target sentence as the first translation text content of the first audio data, and the second target sentence as the second translation text content of the third audio data.
[0084] Optionally, the method further comprises:
[0085] detecting whether a current environment satisfies a children's audio translation condition, wherein the children's audio translation condition includes:
[0086] the current location does not belong to a pre-recorded resident location of the children;
[0087] the current environment includes personnel other than pre-recorded associated family members of the children;
[0088] The first audio data of the children includes:
[0089] When the current environment satisfies the children's audio translation condition, collecting the first audio data of the children.
[0090] Optionally, the method further comprises:
[0091] Collecting image information of the children, identifying whether the image information indicates that the children are reading a book, extracting book feature information or a book name from the image information when the image information indicates that the children are reading a book, and based on the book feature information or the book name, finding a reading book currently being read by the children in a network, and acquiring an electronic book corresponding to the reading book, and storing the electronic book into the book library.
[0092] Optionally, the method further comprises:
[0093] collecting an audio data set of the infant during the reading of the book, and each audio data in the audio data set corresponding to a book image in the reading of the book, and establishing a mapping relationship between the audio data and the book image, and storing the mapping relationship in the book library, wherein the book image corresponding to each audio data in the reading of the book is a current image of the reading book displayed by the image information when the infant outputs the audio data;
[0094] The first key audio feature is converted into first key text content, and based on the first key text content, a target infant book including the first key text content is searched in a pre-acquired book library, and a first target sentence in the target infant book matching the first key text content is identified, including:
[0095] The first key audio feature is converted into first key text content, and based on the first key text content, a target infant book including the first key text content is searched in a pre-acquired book library, and a first target sentence in the target infant book matching the first key text content is identified, including:
[0096] Optionally, the method further comprises:
[0097] The fifth audio data of the infant is collected, the fifth audio data includes M audio data before the first audio data, and also includes N audio data after the first audio data, M and N are positive integers;
[0098] The speech rate of the fifth audio data and the first audio data is identified, and the speech rate is compared with a preset speech rate threshold;
[0099] extracting M key audio features of the M pieces of audio data, converting the M key audio features into M key text contents, and identifying M target sentences in the target children's book that match the M key text contents based on the M key text contents, and taking the M target sentences as translated text contents of the M pieces of audio data; and when the speech rate reaches a preset speech rate threshold, identifying N target sentences in the target children's book that are continuous with the first target sentence, and taking the N target sentences as translated text contents of the N pieces of audio data.
[0100] the playing of the second audio data corresponding to the first translated text content comprises:
[0101] playing audio data corresponding to the translated text contents of the M pieces of audio data, and playing audio data corresponding to the translated text contents of the N pieces of audio data.
[0102] The application further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement steps in the translation method.
[0103] It should be noted that, in this document, the terms "comprising", "containing" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a list of elements not only includes those elements, but also includes other elements not explicitly listed, or inherent to such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element. In addition, it should be pointed out that the scope of the methods and apparatus in the embodiments of the present application is not limited to the order of performing the functions shown or discussed, but can also include performing the functions in a substantially simultaneous manner or in the reverse order, for example, the described method can be performed in an order different from that described, and various steps can also be added, omitted or combined. In addition, the features described with reference to certain examples can be combined in other examples.
[0104] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned example methods can be realized by means of software and a necessary general hardware platform, and of course, can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a computer software product in essence or in the form of a part that contributes to the prior art, which is stored in a storage medium (such as a ROM / RAM, a magnetic disc, an optical disc), and includes a plurality of instructions for causing a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in various embodiments of the present application.
[0105] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the above-mentioned specific embodiments, and the above-mentioned specific embodiments are only illustrative and not restrictive. Those skilled in the art can make many forms under the inspiration of the present application without departing from the scope of the present application and the scope protected by the claims.
Claims
1. A translation machine, characterized by, The machine comprises: a first acquisition unit configured to acquire first audio data of a baby; a first identification unit configured to identify a first key audio feature in the first audio data, the first key audio feature being an audio feature capable of accurately identifying text content, and the first audio data having an audio feature incapable of identifying text content; a second identification unit configured to convert the first key audio feature into first key text content, and based on the first key text content, search a pre-acquired book library for a target baby book including the first key text content, and identify a first target sentence in the target baby book matching the first key text content; a first translation unit configured to take the first target sentence as first translated text content of the first audio data; a playing unit configured to play second audio data corresponding to the first translated text content; The machine further comprises: a detection unit configured to detect whether a current environment satisfies a baby audio translation condition, wherein the baby audio translation condition comprises: the current location not belonging to a pre-recorded regular location of the baby; the current environment including personnel other than pre-recorded associated family members of the baby; The first acquisition unit is specifically configured to acquire first audio data of a baby when the current environment satisfies the baby audio translation condition.
2. The translation machine of claim 1, wherein, The machine further comprises: a second acquisition unit configured to acquire third audio data of the baby, the third audio data being audio data continuous with the first audio data and having a pause interval; a third identification unit configured to identify a second key audio feature in the third audio data, the second key audio feature being an audio feature capable of accurately identifying text content, and the second audio data having an audio feature incapable of identifying text content; The second identification unit is specifically configured to convert the first key audio feature into first key text content, and convert the second key audio feature into second key text content, and based on the first key text content and the second key text content, search a pre-acquired book library for a target baby book including the first key text content and the second key text content, and identify a first target sentence in the target baby book matching the first key text content, and a second target sentence in the target baby book matching the second key text content, the first target sentence and the second target sentence being continuous sentences in the target baby book; The first translation unit is specifically configured to take the first target sentence as first translated text content of the first audio data, and take the second target sentence as second translated text content of the third audio data; The playing unit is further configured to play fourth audio data corresponding to the second translated text content.
3. The translation machine of claim 1, wherein, The machine further comprises: The collection unit is configured to collect image information of the infant, identify whether the image information indicates that the infant is reading a book, extract book feature information or a book name from the image information when the image information indicates that the infant is reading a book, search for a reading book currently read by the infant in a network based on the book feature information or the book name, obtain an electronic book corresponding to the reading book, and store the electronic book in the book library.
4. The translation machine of claim 3, wherein, The collection unit is further configured to collect a set of audio data of the infant during reading of the reading book, and a book image corresponding to each audio data in the set of audio data in the reading book, establish a mapping relationship between the audio data and the book image, and store the mapping relationship in the book library, wherein the book image corresponding to each audio data in the reading book is a current image of the reading book displayed in the image information when the infant outputs the audio data. The second identification unit is specifically configured to: convert the first key audio feature into first key text content, search for a target infant book including the first key text content in a pre-obtained book library based on the first key text content, identify a candidate sentence in the target infant book that matches the first key text content, and extract a book page image of the target infant book including the candidate sentence; and match the book page image with a target book image, and when the book page image matches the target book image, the candidate sentence is taken as the first target sentence; wherein the target book image is a book image that has a mapping relationship with historical audio data that matches the first audio data in the set of audio data, and is extracted based on the mapping relationship.
5. The translation machine according to any one of claims 1 to 3, wherein, The translation machine further includes: A third collection unit is configured to collect fifth audio data of the infant, the fifth audio data including M pieces of audio data before the first audio data and N pieces of audio data after the first audio data, M and N being positive integers. A fourth identification unit is configured to identify a speech rate of the fifth audio data and the first audio data, and compare the speech rate with a preset speech rate threshold. A second translation unit is configured to extract M key audio features of the M pieces of audio data, convert the M key audio features into M key text contents, identify M target sentences in the target infant book that match the M key text contents based on the M key text contents, and take the M target sentences as translated text contents of the M pieces of audio data; and when the speech rate reaches the preset speech rate threshold, identify N target sentences continuous with the first target sentence in the target infant book, and take the N target sentences as translated text contents of the N pieces of audio data. The playing unit is further configured to play audio data corresponding to the translated text content of the M pieces of audio data, and play audio data corresponding to the translated text content of the N pieces of audio data.
6. A method of translation, characterized by, Comprise: Collecting first audio data of a young child; Identifying a first key audio feature in the first audio data, the first key audio feature being an audio feature that can accurately identify text content, and the first audio data having audio features that cannot identify text content; Converting the first key audio feature into first key text content, and based on the first key text content, searching for a target young child book including the first key text content in a pre-acquired book library, and identifying a first target sentence in the target young child book that matches the first key text content; Taking the first target sentence as first translated text content of the first audio data; Playing second audio data corresponding to the first translated text content; The method further comprises: Detecting whether the current environment meets the young child audio translation condition, wherein the young child audio translation condition comprises: The current location does not belong to the pre-recorded residence location of the young child; The current environment includes personnel other than the pre-recorded associated family members of the young child; The method further comprises: When the current environment meets the young child audio translation condition, collecting first audio data of a young child.
7. The method of claim 6, wherein, The method further comprises: Collecting third audio data of the young child, the third audio data being audio data that is continuous with the first audio data and has a pause interval; Identifying a second key audio feature in the third audio data, the second key audio feature being an audio feature that can accurately identify text content, and the second audio data having audio features that cannot identify text content; The method further comprises: Converting the first key audio feature into first key text content, and based on the first key text content, searching for a target young child book including the first key text content in a pre-acquired book library, and identifying a first target sentence in the target young child book that matches the first key text content; The method further comprises: Converting the first key audio feature into first key text content, and based on the first key text content, searching for a target young child book including the first key text content in a pre-acquired book library, and identifying a first target sentence in the target young child book that matches the first key text content; The method further comprises: Taking the first target sentence as first translated text content of the first audio data, and taking the second target sentence as second translated text content of the third audio data.
8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program, when executed by the processor, implements the steps in the translation method of any of claims 6-7.
Citation Information
Patent Citations
Electronic book obtaining method and device
CN106294552A
Method of generating book database for reading evaluation
US20220189333A1