CN114554238A - Live broadcast voice simultaneous transmission method, device, medium and electronic equipment - Google Patents
Live broadcast voice simultaneous transmission method, device, medium and electronic equipment Download PDFInfo
- Publication number
- CN114554238A CN114554238A CN202210167850.5A CN202210167850A CN114554238A CN 114554238 A CN114554238 A CN 114554238A CN 202210167850 A CN202210167850 A CN 202210167850A CN 114554238 A CN114554238 A CN 114554238A
- Authority
- CN
- China
- Prior art keywords
- target
- text
- voice
- texts
- original
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
- H04N21/234336—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by media transcoding, e.g. video is transformed into a slideshow of still pictures or audio is converted into text
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
- H04N21/440236—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display by media transcoding, e.g. video is transformed into a slideshow of still pictures, audio is converted into text
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/278—Subtitling
Abstract
The present disclosure relates to a live voice simultaneous transmission method, device, medium, and electronic apparatus, including: acquiring target language and original audio stream data; the method comprises the steps of performing clauses on original audio stream data, and synchronously identifying original subtitle texts corresponding to clause voices; translating the original caption texts respectively corresponding to the clause voices into target caption texts, and synthesizing target voices corresponding to the clause voices according to the target caption texts; and taking the target voice as target audio stream data to form live data after synchronous transmission. Therefore, when the caption text obtained by recognizing the original audio stream data is translated in the process of synchronous transmission, the caption text is not input into the translation engine word by word, but the original audio stream data is processed in a sentence division way in the stage of voice recognition, so that the translation request issued to the downstream comprises complete sentences, the translation effect of a translated text is ensured, and the problem of poor listening effect of the synthesized voice in the background technology is solved.
Description
Technical Field
The present disclosure relates to the field of live broadcasting, and in particular, to a live voice simultaneous transmission method, apparatus, medium, and electronic device.
Background
At present, in a live broadcast simultaneous transmission scenario, a method for translating a primitive speech in a live broadcast into a speech of another language is generally based on a processing link of "automatic speech recognition — machine translation — machine speech synthesis", where each step in the link is performed word by word, that is, speech recognition obtains a word, and then the word is input to a downstream translation module to translate the word to obtain a translation text corresponding to the word, and then the speech of the other language corresponding to the word is synthesized according to the translation text. Because the recognition of the original text is performed word by word, the machine translation engine is positioned at the downstream of the original text recognition engine, and the received translation request is broken and often not a complete sentence, the speech effect heard by the translation can be poor due to the fact that the translation is connected to the speech synthesis engine. Such as: the speaker's original words are "home good, happy to Shanghai! "the translated text is respectively submitted to the translation engine in recognition," big, home, good, happy, welcome, coming, Shanghai "and" the synthesized speech is also listened to because the translation engine translates the original text word by word.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In a first aspect, the present disclosure provides a live voice simultaneous transmission method, where the method includes:
acquiring target language and original audio stream data, wherein the original audio stream data is obtained by decoding direct broadcast data;
the original audio stream data is divided into sentences, and original caption texts corresponding to the speech of each sentence are synchronously identified;
translating the original caption texts respectively corresponding to the clause voices into target caption texts, and synthesizing target voices corresponding to the clause voices according to the target caption texts, wherein the target caption texts are texts in the target languages;
and taking the target voice as target audio stream data to form live data after simultaneous transmission.
In a second aspect, the present disclosure provides a live voice simultaneous transmission apparatus, the apparatus comprising:
the acquisition module is used for acquiring target language and original audio stream data, wherein the original audio stream data is obtained by decoding direct broadcast data;
the sentence dividing module is used for dividing sentences of the original audio stream data and synchronously identifying original caption texts corresponding to the speech of each sentence;
the synchronous transmission module is used for translating the original caption texts corresponding to the clause voices into target caption texts and synthesizing target voices corresponding to the clause voices according to the target caption texts, wherein the target caption texts are texts in the target languages;
and the processing module is used for taking the target voice as target audio stream data to form live data after simultaneous transmission.
In a third aspect, the present disclosure provides a computer-readable medium having stored thereon a computer program which, when executed by a processing apparatus, performs the steps of the method described in the embodiments in the first aspect.
In a fourth aspect, the present disclosure provides an electronic device comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method described in the embodiments in the first aspect.
By the technical scheme, in the process of simultaneous transmission, when the caption text obtained by identifying the original audio stream data is translated, the caption text is not input into the translation engine word by word, but the original audio stream data is subjected to clause processing in the stage of voice identification, so that the translation request received by a downstream translation module is ensured to be a complete clause, the translation effect of a translated text is ensured, and the problem of poor listening effect of the synthesized voice in the background technology is solved.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale. In the drawings:
fig. 1 is a flowchart illustrating a live voice simulcast method according to an exemplary embodiment of the present disclosure.
Fig. 2 is a flowchart illustrating a live voice simulcast method according to yet another exemplary embodiment of the present disclosure.
Fig. 3 is a flowchart illustrating a live voice simulcast method according to yet another exemplary embodiment of the present disclosure.
Fig. 4 is a block diagram illustrating a structure of a live voice simultaneous transmission apparatus according to an exemplary embodiment of the present disclosure.
Fig. 5 is a block diagram illustrating a structure of a live voice simultaneous transmission apparatus according to still another exemplary embodiment of the present disclosure.
FIG. 6 shows a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
Fig. 1 is a flowchart illustrating a live voice simulcast method according to an exemplary embodiment of the present disclosure. As shown in fig. 1, the method includes steps 101 to 104.
In step 101, a target language and original audio stream data are obtained, where the original audio stream data is obtained by decoding live data.
The live data may be live data including a video stream and an audio stream, or may be live data including only an audio stream, and in the case that the live data is live data including a video stream and an audio stream, decoding the live data into original video stream data and original audio stream data may be implemented by any audio decoder.
The live data can be obtained from any live equipment or server, can be real-time live data or recorded and broadcast data, and whether the original live data is generated in real time or not is not limited in the disclosure, so long as the live data comprises audio stream data and needs to be transmitted simultaneously. In the case that the live data is not live in real time, the original audio stream data may be obtained by simulating live streaming instead of obtaining the entire complete original audio stream data.
The target language can be obtained by the user through inputting in advance. Or, the user may also change the target language during the process of performing the co-transmission processing on the original audio stream data, and the original audio stream data acquired after the target language is changed may be co-transmitted according to the changed target language.
In step 102, the original audio stream data is sentence-divided, and the original caption text corresponding to each sentence voice is synchronously recognized.
The method for segmenting the original audio stream data can be realized by the existing speech recognition technology, for example, whether the segmentation can be performed at the position can be judged by judging whether inter-sentence pause occurs in the recognized sentence on the time axis. The present disclosure does not limit the specific method of clauses.
In step 103, the original caption text corresponding to each clause voice is translated into a target caption text, and a target voice corresponding to the clause voice is synthesized according to the target caption text, where the target caption text is a text of the target language.
In step 104, the target voice is taken as target audio stream data to form live data after synchronous transmission.
Through sentence division, complete sentences in the original audio stream data can be obtained at the stage of voice recognition, the original caption text corresponding to each complete sentence is used as an original caption text, the original caption text corresponding to one complete sentence is translated to obtain a target caption text, and then the whole sentence is subjected to voice synthesis, so that the semantics of each character in one complete sentence can be considered in the synthesis process of the target voice, and more reasonable and accurate target voice can be obtained.
For example, if the original audio stream data includes the aforementioned "big family good" in the process of performing speech recognition on the original audio stream data, it is popular to Shanghai! After the original audio stream data is identified to obtain the "great family" in the example of the voice, the audio stream data including the voice "great family" can be determined to be used as a clause through a clause method, then the whole original caption text "great family" corresponding to the clause is translated to obtain the "Everyone is welcoding", and then the whole translation is subjected to voice synthesis through a voice synthesis module.
If, in the process of performing speech recognition on the original audio stream data in a word-by-word concurrent transmission manner described in the background art, the occurrence process of the recognized text is "-big-good", and the occurrence process of the translation is correspondingly "-big-all-Hello every one", performing speech synthesis on such a translation will affect the listening effect of the synthesized speech to a certain extent, affect the understanding of the user on the live content,
by the technical scheme, in the process of simultaneous transmission, when the caption text obtained by identifying the original audio stream data is translated, the caption text is not input into the translation engine word by word, but the original audio stream data is subjected to clause processing in the stage of voice identification, so that the translation request received by a downstream translation module is ensured to be a complete clause, the translation effect of a translated text is ensured, and the problem of poor listening effect of the synthesized voice in the background technology is solved.
In addition, in the process of simultaneous transmission, the problem that the audio length of the translated text after voice synthesis is different from the audio length of the original text often occurs, so that the voice of the translated text is staggered from the original text, and the live broadcast effect is affected. To address this issue, the present disclosure also provides a method as shown in fig. 2.
Fig. 2 is a flowchart illustrating a live voice simulcast method according to yet another exemplary embodiment of the present disclosure. As shown in fig. 2, the method further includes steps 201 to 206.
In step 201, a translation text obtained by translating the original subtitle text corresponding to each clause voice is obtained.
In step 202, sentence duration corresponding to the sentence dividing voice is determined according to a time axis where the sentence dividing voice is located, and a phoneme numerical range corresponding to the sentence dividing duration is determined.
In step 203, the actual number of phonemes in the translated text is calculated.
In step 204, determining whether the actual number of phonemes is within the phoneme numerical range, if yes, going to step 205, and if no, going to step 206;
in step 205, that is, in the case where it is determined that the actual number of phonemes is within the phoneme numerical range, the translated text is regarded as the target subtitle text, and a target speech corresponding to the sentence dividing speech is synthesized from the target subtitle text.
That is, in the process of translating and synthesizing a speech, the phoneme numerical range is determined according to the sentence duration corresponding to the sentence speech in the time axis of the original audio stream data, the actual number of phonemes in the translated text obtained through translation is calculated, and only when the actual number of phonemes meets the condition that the actual number of phonemes is within the phoneme numerical range, the translated text is directly determined as the target subtitle text to synthesize the target speech.
The phoneme numerical range may be obtained in advance through training or calculation, and the number of phonemes that can be included in the target subtitle text corresponding to the target speech is the minimum and the maximum when the duration of the synthesized target speech is consistent with the sentence duration. The actual number of phonemes is directly calculated from the translated text. If the actual phoneme number of the translation text is within the phoneme numerical range allowed by the sentence duration of the sentence voice corresponding to the translation text in the time axis of the original audio stream data, the audio length corresponding to the target voice synthesized from the translation text is consistent with the audio length corresponding to the sentence voice, and the situation that the translation voice and the original voice are staggered does not occur.
In step 206, that is, in the case where it is determined that the actual number of phonemes is not within the phoneme numerical range, the translated text is adjusted according to the size relationship between the actual number of phonemes and the phoneme numerical range and a preset text adjustment rule.
In step 207, it is determined whether the actual number of phonemes in the adjusted translated text is within the phoneme numerical range, if so, the process goes to step 208, and if not, the process goes to step 206 to continue the adjustment.
In step 208, that is, in the case where it is determined that the actual number of phonemes in the adjusted translated text is within the phoneme numerical range, the adjusted translated text is used as the target caption text, and the target speech corresponding to the sentence dividing speech is synthesized according to the target caption text.
When the actual number of phonemes of the translated text is not within the phoneme numerical range allowed by the sentence duration of the sentence voice corresponding to the translated text in the time axis of the original audio stream data, it is characterized that the audio length corresponding to the target voice obtained by directly synthesizing the translated text is inconsistent with the audio length corresponding to the sentence voice, and the translated text voice and the original text voice are staggered. Therefore, at this time, a certain adjustment needs to be performed on the translation text or the speech synthesized by the translation text to ensure that the final target speech is consistent with the audio duration of the clause speech. And step 204 to step 208 show a scheme of adjusting the translated text so that the actual phoneme number of the adjusted translated text is within the phoneme numerical range.
The method for adjusting the translated text may be performed according to a preset text adjustment rule, as shown in step 206. For example, when the actual number of phonemes in the translated text is less than the minimum value of the phoneme numerical range, a text which does not affect the actual semantics of the translated text may be added to the translated text according to semantics, a chinese translated text may be, for example, "kaki", "o", and the like, and an english translated text may include, for example, "hum."; when the actual number of phonemes in the translated text is greater than the maximum value of the phoneme numerical range, the part of text which does not influence the semantics in the translated text can be deleted.
After the translated text is adjusted according to the preset text adjustment rule, a determination may be further made as to whether the actual number of phonemes in the adjusted translated text is within the phoneme numerical range, so as to ensure that the actual number of phonemes in the translated text is within the phoneme numerical range before the target subtitle text is determined to synthesize the target speech.
In addition, if the number of actual phonemes in the adjusted translated text does not meet the condition that the number of actual phonemes in the translated text is within the phoneme numerical range after the adjustment of the preset text adjustment rule for the preset threshold number of times is performed on the translated text, the translated text or the synthesized speech corresponding to the translated text can be further processed in other manners, so that the time length of the speech after the co-transmission is aligned with the sentence dividing time length before the co-transmission. A specific way may be, for example, the method shown in fig. 3.
Fig. 3 is a flowchart illustrating a live audio simulcast method according to yet another exemplary embodiment of the present disclosure. As shown in fig. 3, the method further comprises step 301 and step 302.
In step 301, a plurality of candidate texts translated from the original subtitle text corresponding to each clause speech are obtained.
In step 302, the candidate text with the highest priority among the plurality of candidate texts is determined as the translated text.
That is, the translated text obtained by translating the original subtitle text corresponding to the clause speech may be obtained by determining the priority from a plurality of candidate texts. The candidate text may also be a plurality of texts with a higher matching degree with the original subtitle text corresponding to the clause speech, among a plurality of texts obtained by translating the original subtitle text corresponding to the clause speech, and the priority of the candidate text may also be determined according to the matching degree of the candidate text with the original subtitle text corresponding to the clause speech, where the higher the matching degree is, the higher the priority is.
In step 303, it is determined whether the adjustment frequency of the translated text reaches a preset threshold frequency, if yes, the process goes to step 304, and if not, the process returns to step 206 to adjust the translated text again.
In step 304, that is, under the condition that the actual number of phonemes is not within the phoneme numerical range and the adjustment number of times of the translated text reaches a preset threshold number of times, sequentially determining the candidate texts as the translated text according to the priority.
In the case that the actual number of phonemes is not within the phoneme numerical range, the translated text may be replaced from the candidate text according to the priority order by the step in step 303. For example, after the candidate text with the highest priority among the candidate texts is taken as the translated text, it is determined that the actual number of phonemes of the translated text is not within the phoneme numerical range, the candidate text with the highest priority among the candidate texts is taken as the translated text, the actual number of phonemes of the translated text is calculated again, and the determination whether the actual number of factors of the translated text is within the phoneme numerical range is performed again.
In step 305, it is determined whether the actual number of factors of the translated text is within the phoneme numerical range, and if so, the process may directly return to step 205 to use the translated text as a target caption text and synthesize a target voice corresponding to the sentence-dividing voice according to the target caption text. If not, go to step 306.
In step 306, it is determined whether all of the candidate texts have been traversed, if yes, the process goes to step 307, and if not, the process returns to step 304, and the candidate texts that have not been determined as translation texts are determined as translation texts according to priority.
That is, the process of determining the translated texts from the candidate texts according to the step 304 sequentially according to the priorities is performed until the actual phoneme number of the translated text is within the phoneme number range or the candidate texts are traversed.
If the actual number of phonemes of the translated text is determined to be within the phoneme numerical range, the step 205 may be directly returned to, where the translated text whose actual number of phonemes meets the condition is used as the target caption text, and the target speech corresponding to the sentence dividing speech is synthesized according to the target caption text.
If a plurality of candidate texts have been traversed and no translated text satisfying the phoneme numerical range condition is determined yet, the sequential determination of the candidate texts is not repeated, and the target speech may be obtained by a method shown in step 307 and step 308, for example.
In step 307, that is, in the case that all of the candidate texts have been traversed, and the actual number of phonemes of the translated text is not within the phoneme numerical range, the candidate text with the highest priority in the candidate texts is determined as the target subtitle text.
In step 308, an intermediate voice is synthesized according to the target caption text, the speed of the intermediate voice is adjusted according to the sentence dividing duration corresponding to the sentence dividing voice, so that the duration corresponding to the speed-adjusted intermediate voice is consistent with the sentence dividing duration, and the speed-adjusted intermediate voice is determined as the target voice corresponding to the sentence dividing voice.
Or, under the condition that the candidate texts are traversed and the actual number of phonemes of the translated text is not within the phoneme numerical range, the current translated text can be directly used as the target subtitle text to synthesize the voice to obtain the intermediate voice, and the speed of the synthesized intermediate voice is regulated according to the clause duration corresponding to the clause voice, so as to ensure that the target voice obtained after the speed regulation can be aligned with the clause voice on the time axis.
In addition, the method for determining the translated text by traversing a plurality of candidate texts to ensure that the final target speech is consistent with the sentence dividing duration shown in fig. 3 and the method for adjusting the translated text according to the preset text adjustment rule to ensure that the final target speech is consistent with the sentence dividing duration shown in fig. 2 do not have a fixed sequential execution order between the two methods. In the actual simultaneous transmission process, if the actual phoneme number is not in the phoneme numerical range, the translation text can be directly adjusted according to the preset text adjustment rule, searching for a translation text meeting the requirement in a mode of sequentially determining the translation text according to the priority in a plurality of candidate texts under the condition of being incapable of being adjusted, finally ensuring that the time length of the voice after the simultaneous transmission is consistent with the sentence division time length in the original audio stream data in a mode of regulating the speed of the synthesized voice under the condition of being incapable of being adjusted, or searching for a translation text meeting the requirement in a mode of sequentially determining the translation text according to the priority in a plurality of candidate texts, and adjusting the translated text according to the preset text adjustment rule under the condition that the translation text cannot be adjusted, and finally ensuring that the time length of the speech after the simultaneous transmission can be consistent with the sentence dividing time length in the original audio stream data in a synthesized speech speed regulation mode under the condition that the translation text cannot be adjusted. Alternatively, the concurrent transmission may be achieved only by a preset text adjustment rule or only by prioritized candidate texts.
In one possible embodiment, the method further comprises: acquiring an original language; the sentence dividing of the original audio stream data and the synchronous recognition of the original caption text corresponding to each sentence voice comprise: and carrying out sentence division on the original audio stream data, and synchronously identifying original caption texts corresponding to the sentence voice according to the original language. That is, before performing speech recognition on the original audio stream data, the original language corresponding to the original audio stream data may be determined by user input, so as to facilitate the speech recognition.
In a possible implementation manner, the process of synthesizing the target subtitle text by using the voice may also be performed according to audio data such as a target tone, a target volume, a target tone, and the like, where the target tone, the target volume, and the target tone may be determined by the user input mode together with the target language, so that the user can select the language, tone, volume, and tone of the voice to be synthesized by the user.
In a possible implementation manner, according to the setting of the user, the determined original subtitle text and/or target subtitle text can be displayed in the live broadcast picture as the subtitle under the condition that the subtitle display requirement exists.
Fig. 4 is a block diagram illustrating a structure of a live voice simultaneous transmission apparatus according to an exemplary embodiment of the present disclosure. As shown in fig. 4, the apparatus includes: an obtaining module 10, configured to obtain target language and original audio stream data, where the original audio stream data is obtained by decoding live broadcast data; a sentence dividing module 20, configured to divide sentences of the original audio stream data, and synchronously identify an original subtitle text corresponding to each sentence voice; the simultaneous transmission module 30 is configured to translate the original subtitle text corresponding to each clause voice into a target subtitle text, and synthesize a target voice corresponding to the clause voice according to the target subtitle text, where the target subtitle text is a text of the target language; and the processing module 40 is configured to use the target voice as target audio stream data to form live data after synchronous transmission.
By the technical scheme, in the process of simultaneous transmission, when the caption text obtained by identifying the original audio stream data is translated, the caption text is not input into the translation engine word by word, but the original audio stream data is subjected to clause processing in the stage of voice identification, so that the translation request received by a downstream translation module is ensured to be a complete clause, the translation effect of a translated text is ensured, and the problem of poor listening effect of the synthesized voice in the background technology is solved.
Fig. 5 is a block diagram illustrating a structure of a live voice simultaneous transmission apparatus according to still another exemplary embodiment of the present disclosure. As shown in fig. 5, the peer-to-peer module 30 includes: the obtaining sub-module 301 is configured to obtain a translation text obtained by translating the original subtitle text corresponding to each clause voice; the determining submodule 302 is configured to determine a sentence division duration corresponding to the sentence division voice according to a time axis in which the sentence division voice is located, and determine a phoneme numerical range corresponding to the sentence division duration; a calculating module 303, configured to calculate an actual number of phonemes in the translated text; the first synthesizing sub-module 304, if the actual number of phonemes is within the phoneme numerical range, uses the translated text as the target subtitle text, and synthesizes target speech corresponding to the sentence-dividing speech according to the target subtitle text.
In a possible implementation, as shown in fig. 5, the peer-to-peer module 30 further includes: a second synthesis sub-module 305, configured to, if the actual number of phonemes is not within the phoneme numerical range, adjust the translated text according to a size relationship between the actual number of phonemes and the phoneme numerical range and a preset text adjustment rule; and if the actual phoneme number in the adjusted translation text is within the phoneme numerical range, taking the adjusted translation text as the target caption text, and synthesizing the target voice corresponding to the sentence dividing voice according to the target caption text.
In a possible implementation, as shown in fig. 5, the obtaining sub-module 301 is further configured to: obtaining a plurality of candidate texts obtained by translating the original subtitle texts respectively corresponding to the clause voices; determining a candidate text with the highest priority among the plurality of candidate texts as the translated text.
In a possible implementation, as shown in fig. 5, the peer-to-peer module 30 further includes: a third synthesis sub-module 306, configured to determine, according to the priority, the candidate texts as the translated texts in sequence if the actual number of phonemes is not within the phoneme numerical range until the actual number of phonemes of the translated text is within the phoneme numerical range or all the candidate texts have been traversed.
In a possible implementation, as shown in fig. 5, the peer-to-peer module 30 further includes: a fourth synthesis sub-module 307, configured to determine, if all of the candidate texts have been traversed, and the actual number of phonemes of the translated text is not within the phoneme numerical range, a candidate text with a highest priority in the candidate texts as the target subtitle text; and synthesizing intermediate voice according to the target caption text, regulating the speed of the intermediate voice according to the sentence dividing duration corresponding to the sentence dividing voice so as to enable the duration corresponding to the speed-regulated intermediate voice to be consistent with the sentence dividing duration, and determining the speed-regulated intermediate voice as the target voice corresponding to the sentence dividing voice.
In a possible implementation, the obtaining module 10 is further configured to: acquiring an original language; the sentence segmentation module 20 is further configured to: and carrying out clauses on the original audio stream data, and synchronously identifying original caption texts corresponding to the clause voices according to the original languages.
Referring now to FIG. 6, a block diagram of an electronic device 600 suitable for use in implementing embodiments of the present disclosure is shown. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, magnetic tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring target language and original audio stream data, wherein the original audio stream data is obtained by decoding direct broadcast data; the original audio stream data is divided into sentences, and original caption texts corresponding to the speech of each sentence are synchronously identified; translating the original caption texts respectively corresponding to the clause voices into target caption texts, and synthesizing target voices corresponding to the clause voices according to the target caption texts, wherein the target caption texts are texts in the target languages; and taking the target voice as target audio stream data to form live data after simultaneous transmission.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Here, the name of the module does not constitute a limitation to the module itself in some cases, and for example, the acquisition module may also be described as a "module that acquires target language and original audio stream data".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Example 1 provides, in accordance with one or more embodiments of the present disclosure, a live voice simulcast method, the method comprising: acquiring target language and original audio stream data, wherein the original audio stream data is obtained by decoding direct broadcast data; the original audio stream data is divided into sentences, and original caption texts corresponding to the speech of each sentence are synchronously identified; translating the original caption texts respectively corresponding to the clause voices into target caption texts, and synthesizing target voices corresponding to the clause voices according to the target caption texts, wherein the target caption texts are texts in the target languages; and taking the target voice as target audio stream data to form live data after simultaneous transmission.
Example 2 provides the method of example 1, wherein translating the original subtitle text corresponding to each of the clause voices into a target subtitle text, and synthesizing a target voice corresponding to the clause voice from the target subtitle text comprises: obtaining translation texts obtained by translating the original caption texts respectively corresponding to the clause voices; determining sentence dividing duration corresponding to the sentence dividing voice according to a time axis of the sentence dividing voice, and determining a phoneme numerical range corresponding to the sentence dividing duration; calculating the actual number of phonemes in the translated text; and if the actual phoneme number is within the phoneme numerical range, taking the translated text as the target caption text, and synthesizing the target voice corresponding to the sentence dividing voice according to the target caption text.
Example 3 provides the method of example 2, wherein translating the original subtitle text corresponding to each of the clause voices into a target subtitle text, and synthesizing a target voice corresponding to the clause voice from the target subtitle text further comprises: if the actual phoneme number is not in the phoneme numerical range, adjusting the translated text according to the size relation between the actual phoneme number and the phoneme numerical range and a preset text adjustment rule; and if the actual phoneme number in the adjusted translation text is within the phoneme numerical range, taking the adjusted translation text as the target caption text, and synthesizing the target voice corresponding to the sentence dividing voice according to the target caption text.
Example 4 provides the method of example 2, and the obtaining translated texts translated from the original subtitle texts corresponding to the clause voices respectively includes: obtaining a plurality of candidate texts obtained by translating the original subtitle texts respectively corresponding to the clause voices; determining a candidate text with the highest priority among the plurality of candidate texts as the translated text.
Example 5 provides the method of example 4, wherein translating the original subtitle text corresponding to each of the clause voices into a target subtitle text, and synthesizing a target voice corresponding to the clause voice from the target subtitle text further comprises: and if the actual phoneme number is not in the phoneme numerical range, sequentially determining the candidate texts as the translated texts according to the priority until the actual phoneme number of the translated texts is in the phoneme numerical range or the candidate texts are traversed and ended.
Example 6 provides the method of example 5, wherein translating the original subtitle text corresponding to each of the clause voices into a target subtitle text, and synthesizing a target voice corresponding to the clause voice from the target subtitle text further comprises: if the candidate texts are traversed and the actual phoneme number of the translated text is not in the phoneme numerical range, determining the candidate text with the highest priority in the candidate texts as the target subtitle text; and synthesizing intermediate voice according to the target caption text, regulating the speed of the intermediate voice according to the sentence dividing duration corresponding to the sentence dividing voice so as to enable the duration corresponding to the speed-regulated intermediate voice to be consistent with the sentence dividing duration, and determining the speed-regulated intermediate voice as the target voice corresponding to the sentence dividing voice.
Example 7 provides a method of example 1, the method further comprising, in accordance with one or more embodiments of the present disclosure: acquiring an original language; the sentence dividing of the original audio stream data and the synchronous recognition of the original caption text corresponding to each sentence voice comprise: and carrying out clauses on the original audio stream data, and synchronously identifying original caption texts corresponding to the clause voices according to the original languages.
Example 8 provides, in accordance with one or more embodiments of the present disclosure, a live speech simultaneous transmission apparatus, comprising: the acquisition module is used for acquiring target language and original audio stream data, wherein the original audio stream data is obtained by decoding direct broadcast data; the sentence dividing module is used for dividing sentences of the original audio stream data and synchronously identifying original caption texts corresponding to the speech of each sentence; the synchronous transmission module is used for translating the original caption texts corresponding to the clause voices into target caption texts and synthesizing target voices corresponding to the clause voices according to the target caption texts, wherein the target caption texts are texts in the target languages; and the processing module is used for taking the target voice as target audio stream data to form live data after simultaneous transmission.
Example 9 provides a computer readable medium having stored thereon a computer program that, when executed by a processing apparatus, performs the steps of the method of any of examples 1-7, in accordance with one or more embodiments of the present disclosure.
Example 10 provides, in accordance with one or more embodiments of the present disclosure, an electronic device comprising: a storage device having a computer program stored thereon; processing means for executing the computer program in the storage means to carry out the steps of the method of any of examples 1-7.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims (10)
1. A live voice simultaneous transmission method is characterized by comprising the following steps:
acquiring target language and original audio stream data, wherein the original audio stream data is obtained by decoding direct broadcast data;
the original audio stream data is divided into sentences, and original caption texts corresponding to the speech of each sentence are synchronously identified;
translating the original caption texts respectively corresponding to the clause voices into target caption texts, and synthesizing target voices corresponding to the clause voices according to the target caption texts, wherein the target caption texts are texts in the target languages;
and taking the target voice as target audio stream data to form live data after simultaneous transmission.
2. The method of claim 1, wherein translating the original caption text corresponding to each of the clause voices into a target caption text, and synthesizing a target voice corresponding to the clause voice according to the target caption text comprises:
obtaining translation texts obtained by translating the original caption texts respectively corresponding to the clause voices;
determining sentence dividing duration corresponding to the sentence dividing voice according to a time axis of the sentence dividing voice, and determining a phoneme numerical range corresponding to the sentence dividing duration;
calculating the actual number of phonemes in the translated text;
and if the actual phoneme number is within the phoneme numerical range, taking the translated text as the target caption text, and synthesizing the target voice corresponding to the sentence dividing voice according to the target caption text.
3. The method of claim 2, wherein translating the original caption text corresponding to each of the clause voices into a target caption text and synthesizing a target voice corresponding to the clause voice according to the target caption text further comprises:
if the actual phoneme number is not in the phoneme numerical range, adjusting the translated text according to the size relation between the actual phoneme number and the phoneme numerical range and a preset text adjustment rule;
and if the actual phoneme number in the adjusted translation text is within the phoneme numerical range, taking the adjusted translation text as the target caption text, and synthesizing the target voice corresponding to the sentence dividing voice according to the target caption text.
4. The method according to claim 2, wherein the obtaining of the translated text translated from the original subtitle text corresponding to each clause speech comprises:
obtaining a plurality of candidate texts obtained by translating the original subtitle texts respectively corresponding to the clause voices;
determining a candidate text with the highest priority among the plurality of candidate texts as the translated text.
5. The method of claim 4, wherein translating the original caption text corresponding to each of the clause voices into a target caption text and synthesizing a target voice corresponding to the clause voice according to the target caption text further comprises:
and if the actual phoneme number is not in the phoneme numerical range, sequentially determining the candidate texts as the translated texts according to the priority until the actual phoneme number of the translated texts is in the phoneme numerical range or the candidate texts are traversed and ended.
6. The method of claim 5, wherein translating the original caption text corresponding to each of the clause voices into a target caption text and synthesizing a target voice corresponding to the clause voice according to the target caption text further comprises:
if the candidate texts are traversed and the actual phoneme number of the translated text is not in the phoneme numerical range, determining the candidate text with the highest priority in the candidate texts as the target subtitle text;
and synthesizing intermediate voice according to the target caption text, regulating the speed of the intermediate voice according to the sentence dividing duration corresponding to the sentence dividing voice so as to enable the duration corresponding to the speed-regulated intermediate voice to be consistent with the sentence dividing duration, and determining the speed-regulated intermediate voice as the target voice corresponding to the sentence dividing voice.
7. The method of claim 1, further comprising: acquiring an original language;
the sentence dividing of the original audio stream data and the synchronous recognition of the original caption text corresponding to each sentence voice comprise:
and carrying out clauses on the original audio stream data, and synchronously identifying original caption texts corresponding to the clause voices according to the original languages.
8. A live speech simultaneous transmission apparatus, the apparatus comprising:
the acquisition module is used for acquiring target language and original audio stream data, wherein the original audio stream data is obtained by decoding direct broadcast data;
the sentence dividing module is used for dividing sentences of the original audio stream data and synchronously identifying original caption texts corresponding to the speech of each sentence;
the synchronous transmission module is used for translating the original caption texts corresponding to the clause voices into target caption texts and synthesizing target voices corresponding to the clause voices according to the target caption texts, wherein the target caption texts are texts in the target languages;
and the processing module is used for taking the target voice as target audio stream data to form live data after simultaneous transmission.
9. A computer-readable medium, on which a computer program is stored, characterized in that the program, when being executed by processing means, carries out the steps of the method of any one of claims 1 to 7.
10. An electronic device, comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210167850.5A CN114554238B (en) | 2022-02-23 | 2022-02-23 | Live broadcast voice simultaneous transmission method, device, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210167850.5A CN114554238B (en) | 2022-02-23 | 2022-02-23 | Live broadcast voice simultaneous transmission method, device, medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114554238A true CN114554238A (en) | 2022-05-27 |
| CN114554238B CN114554238B (en) | 2023-08-11 |
Family
ID=81677638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210167850.5A Active CN114554238B (en) | 2022-02-23 | 2022-02-23 | Live broadcast voice simultaneous transmission method, device, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114554238B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115002502A (en) * | 2022-07-29 | 2022-09-02 | 广州市千钧网络科技有限公司 | Data processing method and server |
| CN116471436A (en) * | 2023-04-12 | 2023-07-21 | 央视国际网络有限公司 | Information processing method and device, storage medium and electronic equipment |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990047559A (en) * | 1997-12-04 | 1999-07-05 | 전주범 | Voice translation display control method of VSI tape |
| US20060074690A1 (en) * | 2004-09-29 | 2006-04-06 | Inventec Corporation | Speech displaying system and method |
| US20130268259A1 (en) * | 2012-04-04 | 2013-10-10 | Electronics And Telecommunications Research Institute | Translation apparatus and method thereof |
| CN103854648A (en) * | 2012-12-08 | 2014-06-11 | 上海能感物联网有限公司 | Chinese and foreign language voiced image data bidirectional reversible voice converting and subtitle labeling method |
| US20160021334A1 (en) * | 2013-03-11 | 2016-01-21 | Video Dubber Ltd. | Method, Apparatus and System For Regenerating Voice Intonation In Automatically Dubbed Videos |
| CN105704579A (en) * | 2014-11-27 | 2016-06-22 | 南京苏宁软件技术有限公司 | Real-time automatic caption translation method during media playing and system |
| CN106791913A (en) * | 2016-12-30 | 2017-05-31 | 深圳市九洲电器有限公司 | Digital television program simultaneous interpretation output intent and system |
| US20180075023A1 (en) * | 2016-09-09 | 2018-03-15 | Electronics And Telecommunications Research Institute | Device and method of simultaneous interpretation based on real-time extraction of interpretation unit |
| CN108401192A (en) * | 2018-04-25 | 2018-08-14 | 腾讯科技（深圳）有限公司 | Video stream processing method, device, computer equipment and storage medium |
| CN108566558A (en) * | 2018-04-24 | 2018-09-21 | 腾讯科技（深圳）有限公司 | Video stream processing method, device, computer equipment and storage medium |
| CN207993005U (en) * | 2018-04-03 | 2018-10-19 | 中译语通科技股份有限公司 | A kind of multi-lingual simultaneous interpretation translation terminal control mechanism based on news conference scene |
| CN110164420A (en) * | 2018-08-02 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of method and device of the method for speech recognition, voice punctuate |
| CN110381388A (en) * | 2018-11-14 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of method for generating captions and device based on artificial intelligence |
| JP2020178262A (en) * | 2019-04-19 | 2020-10-29 | 日本放送協会 | Live subtitle shaping processing device and program |
| CN111955013A (en) * | 2018-04-04 | 2020-11-17 | 诺基私人有限公司 | Method and system for facilitating interactions during real-time streaming events |
| CN112601102A (en) * | 2020-12-11 | 2021-04-02 | 北京有竹居网络技术有限公司 | Method and device for determining simultaneous interpretation of subtitles, electronic equipment and storage medium |
| JP2021090172A (en) * | 2019-12-05 | 2021-06-10 | 讀賣テレビ放送株式会社 | Caption data generation device, content distribution system, video reproduction device, program, and caption data generation method |
| CN113343675A (en) * | 2021-06-30 | 2021-09-03 | 北京搜狗科技发展有限公司 | Subtitle generating method and device for generating subtitles |
| CN113660432A (en) * | 2021-08-17 | 2021-11-16 | 安徽听见科技有限公司 | Translation subtitle production method and device, electronic equipment and storage medium |
| CN113889113A (en) * | 2021-11-10 | 2022-01-04 | 北京有竹居网络技术有限公司 | Sentence dividing method and device, storage medium and electronic equipment |
| KR102351408B1 (en) * | 2021-03-26 | 2022-01-14 | 이광선 | service method of automatically generating translated subtitles of video contents |
| CN114040255A (en) * | 2021-10-28 | 2022-02-11 | 上海网达软件股份有限公司 | Live caption generating method, system, equipment and storage medium |
-
2022
- 2022-02-23 CN CN202210167850.5A patent/CN114554238B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990047559A (en) * | 1997-12-04 | 1999-07-05 | 전주범 | Voice translation display control method of VSI tape |
| US20060074690A1 (en) * | 2004-09-29 | 2006-04-06 | Inventec Corporation | Speech displaying system and method |
| US20130268259A1 (en) * | 2012-04-04 | 2013-10-10 | Electronics And Telecommunications Research Institute | Translation apparatus and method thereof |
| CN103854648A (en) * | 2012-12-08 | 2014-06-11 | 上海能感物联网有限公司 | Chinese and foreign language voiced image data bidirectional reversible voice converting and subtitle labeling method |
| US20160021334A1 (en) * | 2013-03-11 | 2016-01-21 | Video Dubber Ltd. | Method, Apparatus and System For Regenerating Voice Intonation In Automatically Dubbed Videos |
| CN105704579A (en) * | 2014-11-27 | 2016-06-22 | 南京苏宁软件技术有限公司 | Real-time automatic caption translation method during media playing and system |
| US20180075023A1 (en) * | 2016-09-09 | 2018-03-15 | Electronics And Telecommunications Research Institute | Device and method of simultaneous interpretation based on real-time extraction of interpretation unit |
| CN106791913A (en) * | 2016-12-30 | 2017-05-31 | 深圳市九洲电器有限公司 | Digital television program simultaneous interpretation output intent and system |
| CN207993005U (en) * | 2018-04-03 | 2018-10-19 | 中译语通科技股份有限公司 | A kind of multi-lingual simultaneous interpretation translation terminal control mechanism based on news conference scene |
| CN111955013A (en) * | 2018-04-04 | 2020-11-17 | 诺基私人有限公司 | Method and system for facilitating interactions during real-time streaming events |
| CN108566558A (en) * | 2018-04-24 | 2018-09-21 | 腾讯科技（深圳）有限公司 | Video stream processing method, device, computer equipment and storage medium |
| CN108401192A (en) * | 2018-04-25 | 2018-08-14 | 腾讯科技（深圳）有限公司 | Video stream processing method, device, computer equipment and storage medium |
| CN110164420A (en) * | 2018-08-02 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of method and device of the method for speech recognition, voice punctuate |
| CN110381388A (en) * | 2018-11-14 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of method for generating captions and device based on artificial intelligence |
| JP2020178262A (en) * | 2019-04-19 | 2020-10-29 | 日本放送協会 | Live subtitle shaping processing device and program |
| JP2021090172A (en) * | 2019-12-05 | 2021-06-10 | 讀賣テレビ放送株式会社 | Caption data generation device, content distribution system, video reproduction device, program, and caption data generation method |
| CN112601102A (en) * | 2020-12-11 | 2021-04-02 | 北京有竹居网络技术有限公司 | Method and device for determining simultaneous interpretation of subtitles, electronic equipment and storage medium |
| KR102351408B1 (en) * | 2021-03-26 | 2022-01-14 | 이광선 | service method of automatically generating translated subtitles of video contents |
| CN113343675A (en) * | 2021-06-30 | 2021-09-03 | 北京搜狗科技发展有限公司 | Subtitle generating method and device for generating subtitles |
| CN113660432A (en) * | 2021-08-17 | 2021-11-16 | 安徽听见科技有限公司 | Translation subtitle production method and device, electronic equipment and storage medium |
| CN114040255A (en) * | 2021-10-28 | 2022-02-11 | 上海网达软件股份有限公司 | Live caption generating method, system, equipment and storage medium |
| CN113889113A (en) * | 2021-11-10 | 2022-01-04 | 北京有竹居网络技术有限公司 | Sentence dividing method and device, storage medium and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 刘和平: "对口译职业化+专业化趋势的思考:挑战与对策", 第十一届全国口译大会暨国际口译研讨会 * |
| 闫笑: "翻译功能对等理论指导下的俄语电影《他是龙》的翻译-从耳语同传至字幕翻译", 中外交流, no. 018 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115002502A (en) * | 2022-07-29 | 2022-09-02 | 广州市千钧网络科技有限公司 | Data processing method and server |
| CN116471436A (en) * | 2023-04-12 | 2023-07-21 | 央视国际网络有限公司 | Information processing method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114554238B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112231498A (en) | Interactive information processing method, device, equipment and medium | |
| CN114554238B (en) | Live broadcast voice simultaneous transmission method, device, medium and electronic equipment | |
| CN111368559A (en) | Voice translation method and device, electronic equipment and storage medium | |
| CN111986655B (en) | Audio content identification method, device, equipment and computer readable medium | |
| US20220215841A1 (en) | Information processing method, system, apparatus, electronic device and storage medium | |
| CN111883107B (en) | Speech synthesis and feature extraction model training method, device, medium and equipment | |
| CN111916053B (en) | Voice generation method, device, equipment and computer readable medium | |
| CN111753558B (en) | Video translation method and device, storage medium and electronic equipment | |
| CN113035199B (en) | Audio processing method, device, equipment and readable storage medium | |
| WO2023083142A1 (en) | Sentence segmentation method and apparatus, storage medium, and electronic device | |
| CN113257218B (en) | Speech synthesis method, device, electronic equipment and storage medium | |
| CN113886612A (en) | Multimedia browsing method, device, equipment and medium | |
| CN113571044A (en) | Voice information processing method and device and electronic equipment | |
| CN113207044A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN114765025A (en) | Method for generating and recognizing speech recognition model, device, medium and equipment | |
| CN114495901A (en) | Speech synthesis method, speech synthesis device, storage medium and electronic equipment | |
| CN111935541B (en) | Video correction method and device, readable medium and electronic equipment | |
| CN115967833A (en) | Video generation method, device and equipment meter storage medium | |
| CN112836476B (en) | Summary generation method, device, equipment and medium | |
| CN115171645A (en) | Dubbing method and device, electronic equipment and storage medium | |
| CN114429629A (en) | Image processing method and device, readable storage medium and electronic equipment | |
| CN113420723A (en) | Method and device for acquiring video hotspot, readable medium and electronic equipment | |
| CN114430491A (en) | Live broadcast-based data processing method and device | |
| CN111027332A (en) | Method and device for generating translation model | |
| CN112530472B (en) | Audio and text synchronization method and device, readable medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |