33 results about "Translation language" patented technology

The invention relates to the technical field of artificial intelligence, and discloses a Bluetooth communication intelligent speech translation method and system based on multi-mode enhancement, and the method comprises the steps: collecting a multi-channel audio signal through a built-in multi-microphone array of a Bluetooth device, carrying out the dynamic direction self-adaptive beam forming of the multi-channel audio signal, and carrying out the self-adaptive beam forming of the multi-channel audio signal; extracting a Mel spectrogram feature of the direction enhancement signal, identifying lip regions of a plurality of candidate speakers in each frame of real-time speaking video captured by a camera, performing time sequence convolution on the lip regions to obtain a lip movement time sequence embedded vector, calculating a correlation score with the Mel spectrogram feature, separating the direction enhancement signal, and obtaining a lip movement time sequence embedded vector; and performing text transcription and conversion on the high-confidence separation voice to obtain a translation language text, and sending the synthesized target translation voice to a preset mobile terminal through the Bluetooth device to obtain a target translation result. According to the method, the real-time performance and accuracy of speech translation are improved in a multi-person scene, far-field speech, noise interference and accent difference.

The present disclosure provides a method for translating a game, an electronic device, and a non-transitory computer-readable storage medium. The method include: establishing, by a proxy server, a communication connection between a client and a game server through the proxy server, wherein the proxy server communicates with the game server for the game; receiving, by the proxy server, game data from the game server, where the game data is sent by the game server in response to an active request or actively pushed by the game server; determining, by the proxy server, language resource data contained in the game data; and translating, by the proxy server, the language resource data according to a predetermined automation service, and returning translated language resource data to the client, so that the client loads the translated language resource data.

1. Name of the designed product: translation machine. 2. Use of the designed product: for translating languages. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

1. The name of the design product: graphical user interface (AI translation) of real-time translation application of electronic device. 2. The use of the design product: for an electronic device. 3. The design points of the design product: the graphical user interface content displayed by the electronic device. 4. The picture or photo that best indicates the design points: front view. 5. The use of the graphical user interface: for providing AI translation. 6. The human-computer interaction mode of the graphical user interface: clicking, staying, and sliding the relevant function buttons on the screen. 7. The change state description of the graphical user interface: the front view is the main interface of the real-time translation application, the AI translation module in the front view includes earphone mode, external speaker mode, and face-to-face translation, clicking the earphone mode of the AI translation module in the front view enters the interface change state diagram 1; clicking the button at the bottom of the interface change state diagram 1 to start collecting voice, after single collection is completed, it is converted into interface change state diagram 2; clicking the translation language selection button at the top center of the interface change state diagram 2 enters the interface change state diagram 3 for user to select the recording language; clicking the translation language in the interface change state diagram 3 enters the interface change state diagram 4 for user to select the translation language; wherein, “XXXX” in the front view shows the connected earphone model, “AAAAAAAA” shows the MAC address, and the area covered by the gray translucent mask is the variable content picture; “ZZZ” in the interface change state diagram 2 is the text content to be translated by voice recognition, “YYY” is the translated text content, and clicking the clear button at the upper right corner of the interface change state diagram 2 can clear the text content in the interface.

1. Name of the designed product: translation machine. 2. Use of the designed product: for translating languages. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

The invention discloses a text information processing method and device, equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring text information, a first mapping table and a second mapping table, wherein the text information is used for indicating character contents needing to be rendered by an application program; searching in the first mapping table on the basis of the text information to obtain a first text identifier, wherein the first mapping table comprises at least two development language key value pairs which take the text content of the development language of the application program as keywords and take the text identifier as a data item; a first translation text is searched in the second mapping table based on the first text identifier, the second mapping table comprises at least two translation language key value pairs with the text identifier as a keyword and text content of a translation language as a data item, and the translation language is different from the development language; and rendering and displaying the character content of the first translated text.

Embodiments of the invention provide a speech translation method and device, a readable storage medium and a program product. The method comprises the steps of determining a source language corresponding to a to-be-processed speech; generating a translation speech and a translation text of a translation language; the translated speech and the speech to be processed have the same acoustic characteristics; the translation language is determined by a user or a use environment; and displaying the translated speech and the translated text. And the information transmission efficiency in the cross-language interaction scene is improved.

The invention relates to a term evaluation-based language model precise translation method and device. Relates to the technical field of translation. The method comprises the steps of obtaining a target domain term set and a domain corpus, and extracting a target sentence containing a target term to generate a reference translation; replacing the target terms with candidate lexical elements in a candidate lexical element set to generate disturbance sentences and obtain disturbance translations; carrying out statistics on probability distribution of candidate lexical elements which enable the disturbance translation and the reference translation to achieve term-level semantic matching; and calculating term translation entropy based on the candidate lexical element probability distribution. Fusing the term translation entropy into the training, decoding and / or data enhancement process of the translation language model; or selecting a target translation language model with high domain term adaptability to execute the translation task by using the term translation uncertainty reflected by the term translation entropy. According to the method, the uncertainty of the model on term translation is identified, so that the model is guided to more accurately translate or select a language model more adaptive to terms, and the term translation accuracy and consistency are improved.

1. The name of the design product: podcast transcription graphical user interface for electronic device. 2. The use of the design product: for an electronic device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best indicates the design points: design 3 interface change state diagram. 5. Design 3 is designated as the basic design. 6. The use of the graphical user interface: to display the transcription function of the podcast. 7. Other circumstances that need to be explained are described in the drawings: in design 1 main view, the audio recording automatically jumps to design 1 interface change state diagram, and the middle of design 1 interface change state diagram displays the recorded text content; clicking the button at the bottom of design 1 main view or design 1 interface change state diagram can switch between pausing and continuing recording; clicking the right upper corner of the interface can switch the language displayed in the middle of the interface; clicking the "subtitle translation" in the left lower corner of the interface or clicking the floating window on the right side of the interface can display the audio recording content in the middle of the interface in two languages; the change states of design 2 and design 3 are the same as those of design 1; after clicking "subtitle translation" in the left lower corner of design 4 main view and selecting the translation language, or clicking the floating window on the right side of design 4 main view, and then clicking the start button at the bottom of design 4 main view, design 4 interface change state diagram is obtained, and the middle of the interface of design 4 interface change state diagram displays the recorded audio in two languages. 8. Other circumstances that need to be explained are described in the drawings: "XX" in each view represents a word or character.

A method of translating content may include receiving an image file of a translation target related to an episode of content based on a first language, extracting text corresponding to the first language from the image file, and providing a translation editor for the image file so that a translated version of the episode is generated on the basis of a second language using the image file. The translation editor may include a first area in which the image file of the translation target is output, and a second area for receiving a translated language in the second language for the extracted text as input. In response to a control command for image capturing, at least a portion of the output image file is received through the first area, an input window for receiving a translated language for the captured image as input is generated in the second area.

1. Name of the product in this design: AI original audio translation and subtitle module for video playback graphical user interface of electronic device. 2. Application of this design: This design is intended for use in an electronic device. 3. The key design features of this product are the graphical user interface portion for which protection is sought. 4. The picture or photo that best illustrates the key design points: Design 1 front view. 5. Design 1 is designated as the basic design. 6. Uses of the graphical user interface: Overall use: video playback interaction; Local use: to realize the functions of video AI original sound translation and dubbing, and subtitle language switching and display through changes in user operation. 7. Other situations requiring explanation are illustrated in the diagrams: This design protects the AI ​​original audio translation and subtitle module; Design 1: Clicking the "Original Audio Translation and Subtitle" option in the lower right corner of the main view of Design 1 expands the list on the side of the interface, as shown in Figure 1 of the Design 1 change state. The original audio translation and subtitle languages ​​can be selected separately. The list can be slid vertically, as shown in Figure 2 of the Design 1 change state; Design 2: Clicking the "Original Audio Translation and Subtitle" option in the lower right corner of the main view of Design 2, as shown in Figure 1 of the Design 2 change state, allows the selection of the original audio translation and subtitle languages. The list can be slid vertically, as shown in Figure 2 of the Design 2 change state; Design 3: If the currently playing video does not have original audio translation, as shown in the main view of Design 3, the lower right corner entry displays the "Subtitle" option. Clicking this option expands the list on the side of the interface, as shown in the Figure 3 change state, allowing the selection of the desired language option; Design 4: Design 4 is another display interface for the subtitle module. Click the "Subtitle" option in the lower right corner of the main view of Design 4. As shown in the change state diagram of Design 4, you can select the desired language option. Design 5: If the currently playing video only has original audio translation, as shown in the main view of Design 5, the lower right corner entry will display the "Original Audio Translation (AI)" option. Clicking this option will expand the list on the side of the interface, as shown in the change state diagram of Design 5, allowing you to switch the original audio translation language. The usage state reference diagrams are renderings of the user interface. The main view of Design 1 and change state diagrams 1-2 correspond to usage state reference diagrams 1-3 of Design 1, the main view of Design 2 and change state diagrams 1-2 correspond to usage state reference diagrams 1-3 of Design 2, the main view of Design 3 and change state diagrams correspond to usage state reference diagrams 1-2 of Design 3, the main view of Design 4 and change state diagrams correspond to usage state reference diagrams 1-2 of Design 4, and the main view of Design 5 and change state diagrams correspond to usage state reference diagrams 1-2 of Design 5.

1. Name of the designed product: translation machine. 2. Use of the designed product: for translating languages. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

1. The name of the design product: translation homepage graphical user interface for electronic device. 2. The use of the design product: an electronic device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best indicates the design points: front view. 5. The use of the graphical user interface: for displaying translation language switching and translation function details information. 6. The change state description of the graphical user interface: the language switching bar is above the main view interface, clicking the language switching bar can select different languages, the translation function control is below the language switching bar, clicking any translation function control enters the corresponding translation function page, the history control is in the upper right corner of the main view interface, clicking the history control enters the history translation page. 7. Other circumstances that need to be explained: "XX" in each view represents text or characters.

The invention relates to a low-resource language translation model obtaining method and device and electronic equipment. The method comprises the following steps: acquiring a plurality of test language pairs under a target translation language pair; performing target language translation processing on the input hybrid expert model by using the plurality of test languages to obtain selected statistical frequencies corresponding to a plurality of target expert networks in the hybrid expert model in the translation processing and target selected probabilities corresponding to the frequencies in the selected statistical frequencies; according to the selected statistical frequency and the target selected probability corresponding to each frequency, determining associated information of each of the plurality of target expert networks and the target translation language pair; cutting the plurality of target expert networks based on the associated information to obtain a cut initial translation model; and according to the training language pair of the target translation language pair, training the initial translation model to obtain a low-resource language translation model for translating the target translation language pair. A low-resource language translation model which is light in weight and good in translation effect can be obtained.

Whether or not a translated text corresponds to the character's mouth movements is appropriately evaluated. At least one processor (11) generates a similarity degree indicating a similarity of the character's mouth movements, based on the character's mouth shape corresponding to each of phonemes (33a through 33c) included in a pre-translation phoneme sequence (33) and on the character's mouth shape corresponding to each of phonemes (34a through 34e, 35a, and 35b) included in post-translation phoneme sequences (34 and 35).

Various embodiments of the present disclosure are directed to an inflight entertainment computer server. The IFE computer server includes at least one network interface, at least one processor connected to communicate through the at least one network interface with video display units and / or personal electronic devices, and at least one memory. The at least one memory including a language conversion module operative to translate an announcement including digitized speech and / or text from a first language to an available set of translated languages; a passenger preferred language module operative to identify a set of passenger preferred languages based on information obtained for passengers onboard the aircraft; and an announcement distribution module operative to receive the announcement in the first language generated by a crew member or by a controller, and process the announcement in the first language through the language conversion module to output a set of translated announcements.

Embodiments of the present application disclose a conference information processing method and device, a terminal and a computer readable storage medium. The method comprises: monitoring a language type of online conference voice data in a target conference; when it is determined that a language type of first real-time voice information in the online conference voice data is a target language type, generating first text corresponding to the first real-time voice information, and displaying the first text on a conference interface; when it is determined that a language type of second real-time voice information in the online conference voice data is a language type to be translated, performing target language type text conversion processing on the second real-time voice information to obtain second text, and displaying the second text on the conference interface. Thus, the technical problem of weak visibility of information transmission in the process of online video conference is solved.

A method for utilizing contextual data in generating machine translations. The method includes receiving a translation request including an initial prompt received via a user interface. The initial prompt includes a first language passage and a translation instruction. The initial prompt also includes a context data signal received via a context data source. The method further includes generating a context instruction based on the context data signal and generating a modified prompt including the initial prompt and the context instruction. The method further includes sending the modified prompt to a neural machine translation (NMT) model to process the modified prompt and receiving a second language translation passage as a response to the modified prompt. The second translation language passage being a second language translation of the first language passage translated according to the translation instruction and the context instruction.

This invention discloses a call translation method, apparatus, device, and storage medium, applied to a translation server, and specifically discloses: receiving a media stream anchoring instruction from a voice application server; acquiring a conversational media stream based on the media stream anchoring instruction, and monitoring the conversational media stream in real time to identify the current language information in the conversational media stream; the current language information includes the current language type of the speech in the conversational media stream; matching the current language type with a preset translation language list in a synchronous translation service; when the matching result indicates that the current language type is inconsistent with the target language type, and the current language type belongs to the source language type in the translation language list, translating the speech in the conversational media stream according to the mapping relationship in the translation language list, generating a translated conversational media stream, and sending the translated conversational media stream to the user terminal.

Embodiments of the present application disclose a language translation library updating method and device, equipment and a storage medium. The method comprises: obtaining to-be-translated content in a preset format table, the to-be-translated content comprising to-be-translated text and a corresponding translation language, wherein the to-be-translated text comprises at least one to-be-translated term; if a translation result corresponding to the to-be-translated term translation text does not exist in a language translation library, outputting a target translation result of the to-be-translated term translation text based on the translation language, and creating an added translation term of the language translation library based on the target translation result; and updating the language translation library based on the added translation term, to obtain an updated language translation library. Embodiments of the present application can update the language translation library according to the added translation term, optimize the translation capability of the language translation library, improve the translation efficiency, and improve the diversity of business types of the language translation library.

1. Name of the designed product: translation machine. 2. Use of the designed product: for translating languages. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

The invention relates to the technical field of speech recognition, and discloses an intelligent selection method and system of an AI speech translation model. The method comprises the following steps: obtaining translation task information to perform natural language processing, extracting a translation language pair and a keyword feature vector of a professional field to which the translation language pair belongs, and obtaining a demand vector embedding representation; querying a model library based on the representation, and matching a preliminary candidate model set through vector cosine similarity; extracting performance indexes of each model, and selecting an alternative optimal model through weighted calculation; if the evaluation of the model in a specific task scene is lower than a threshold value, iteratively comparing the suboptimal model, and determining an adjusted optimal model; the model is used for processing voice input, and final translation content is generated through recognition, translation and terminology post-processing correction; and finally, updating model library metadata according to a translation result and demand matching degree feedback, and optimizing a subsequent matching mechanism. According to the method, efficient and accurate dynamic selection and continuous optimization of the model under complex translation requirements can be realized.

A method of providing content translation that includes transmitting, by a management server, a translation target manuscript for an episode of content created based on a first language to a translation server; providing, by the translation server, the translation target manuscript to a first terminal, and receiving, from the first terminal, translated language corresponding to a second language, where the second language is different from the first language; generating, by the translation server, a translation file for the translation target manuscript using the received translated language; providing, by the translation server, the translation file to a second terminal; and receiving, from the second terminal, an image file corresponding to the episode, which is translated into the second language using the translation file.

1. Name of the designed product: translation machine. 2. Use of the designed product: for translating languages. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

Embodiments of the present disclosure disclose a code multilingualization method, device, equipment, storage medium and program product, wherein the code multilingualization method comprises: determining a code variable capable of being recognized by a current code running environment; the code variable comprises original language text in source code and translated language text of the original language text in multiple languages; based on target original language text to be processed, the code variable and language identification, determining a to-be-replaced variable corresponding to the target original language text; replacing the target original language text in the source code with the to-be-replaced variable to obtain multilingual source code; the to-be-replaced variable is used to adjust the translated language text corresponding to the target original language text based on the language identification. In this way, the multilingual switching of the original language text in the source code can be intelligently realized, the operation is simple, and the applicability is strong.

The invention discloses a translation method based on intelligent glasses, relates to the technical field of real-time translation of glasses, and is used for solving the problem that the actual use experience is affected due to the fact that translation content is not matched with the attention degree of a user. Judging whether to start a translation analysis system according to the recognition result and the native language of the user; monitoring the residence time of the user and the static duration of eyeballs by the system to generate translation characteristic values; judging whether to execute translation according to the distance variation between the user and the article; collecting target state data within the set translation time; and calculating a shallow time proofreading proportion in combination with a translation language length, and finally generating translation shallow time, thereby realizing intelligent recognition of translation requirements and dynamic adjustment of translation duration.

To provide a system in which a user uses a portable terminal to utilize an interpretation service using tripartite telephone conversation.SOLUTION: A tripartite interpretation system 100 comprises: an interpretation application 20 that is activated by a QR code (R) 10, which is displayed on a pamphlet 11 together with information on a language capable of being interpreted, being read by a portable terminal 21 and displays information on a plurality of languages capable of being interpreted; and a customer dealing database 30 in which information for an interpreter to determine whether or not to reject telephone conversation is stored. When a language to which interpretation is desired is selected, the interpretation application 20 originates a call with information on the pamphlet 11 attached using an IP telephone to a predetermined interpretation center. In the interpretation center, an interpreter of the language selected by a user responds to an incoming call and originates a call to a provider of the pamphlet 11 when it is determined not to reject telephone conversation, to establish tripartite telephone conversation among the user, the interpreter, and the provider.SELECTED DRAWING: Figure 2

The application provides a script translation method, device, equipment, medium and program product. The method comprises the following steps: determining prior knowledge corresponding to a first script from a preset script library in response to a translation requirement, so as to obtain a prompt word template; inputting the prompt word template into a target translation model to obtain a script translation result of the first script in a target translation language; displaying a visual preview interface according to the script translation result and first display information; in the case that an adjustment instruction of the visual preview interface is detected, updating the script translation result and / or updating the display position of the script translation result on a target display screen in response to the adjustment instruction, to obtain target script translation content corresponding to the first script, and the display effect of the target script translation content is adapted to the target display screen. The scheme can reduce the possibility that the translated text exceeds the original text display range, reduce the situation that the page information display is incomplete, and improve the display effect of the function page.