CN110866410B - Multilingual conversion method, multilingual conversion device, computer device, and storage medium - Google Patents
Multilingual conversion method, multilingual conversion device, computer device, and storage medium Download PDFInfo
- Publication number
- CN110866410B CN110866410B CN201911117209.5A CN201911117209A CN110866410B CN 110866410 B CN110866410 B CN 110866410B CN 201911117209 A CN201911117209 A CN 201911117209A CN 110866410 B CN110866410 B CN 110866410B
- Authority
- CN
- China
- Prior art keywords
- language
- sender
- search result
- condition
- search
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/033—Voice editing, e.g. manipulating the voice of the synthesiser
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/033—Voice editing, e.g. manipulating the voice of the synthesiser
- G10L13/0335—Pitch control
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to a multi-language conversion method, a device, a computer device and a storage medium, wherein the method comprises the steps of obtaining voice information and receiving language set by a receiver; identifying the voice information to obtain a language to be converted; integrating the language to be converted and the receiving language set by the receiver to obtain a first retrieval condition; searching in a first database to obtain a first search result; judging whether the first search result is successful in matching; if not, setting a rated number, and integrating the rated number with the first search condition to obtain a second search condition; searching in a second database to obtain a second search result; judging whether the second search result is successful in matching; if not, calling a translation program to translate the language to be translated to obtain target language characters; acquiring tone, pitch and loudness to obtain conditions to be integrated; according to the condition to be integrated, performing voice conversion on the target language words to obtain a target language; and transmitted to the receiving side. The invention improves the language conversion efficiency and the accuracy.
Description
Technical Field
The present invention relates to a computer, and more particularly, to a multilingual conversion method, apparatus, computer device, and storage medium.
Background
With the rapid development of society, people want to see the world outside, but the languages of each place are different, so that the situations of language failure and difficult communication are caused; still others have failed to use the body language for physical reasons, but are desirous of communicating with the outside world.
In the prior art, a user is required to query individual words in the whole sentence to be translated by utilizing a dictionary; alternatively, the entire statement to be translated is translated using a machine translation tool. However, by means of individual word translation, the resulting translation result may be a plurality of different results, requiring the user to analyze and identify the target word most conforming to the context from the plurality of translation results; through the whole sentence translation mode, the obtained translation result may have the problems of incorrect word sequence or sentence pattern, etc., the final result is required to be determined through analysis by a user, and whether individual words are translated or whole sentences are translated, the final result is limited by a database of the user, and once words or sentences which are not in the database of the user occur, accurate conversion cannot be performed.
Therefore, a new method is needed to be designed, so that the language conversion efficiency and the accuracy are improved, and different user requirements are met.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a multi-language conversion method, a multi-language conversion device, a multi-language conversion computer device and a multi-language conversion storage medium.
In order to achieve the above purpose, the present invention adopts the following technical scheme: a multi-language conversion method comprising:
acquiring voice information from a sender and a receiving language set by a receiver;
identifying the voice information of the sender to obtain a language to be converted;
integrating the language to be converted and a receiving language set by a receiver to obtain a first retrieval condition;
searching in a first database according to the first search condition to obtain a first search result;
judging whether the first search result is successfully matched;
if the first search result is not successfully matched, setting a rated number, and integrating the rated number with the first search condition to obtain a second search condition;
searching in the second database according to the second search condition to obtain a second search result;
judging whether the second search result is successfully matched;
if the second search result is not successfully matched, a translation program is called to translate the language to be converted so as to obtain target language characters;
acquiring tone, pitch and loudness set by a sender to obtain conditions to be integrated;
performing voice conversion on the target language words according to the condition to be integrated to obtain target voice;
and sending the target voice to a receiver.
The further technical scheme is as follows: the first database includes a sender-customized language library.
The further technical scheme is as follows: the judging whether the first search result is successful in matching comprises the following steps:
if the first search result is successfully matched, acquiring the characters which are in the first database and accord with the first search condition to obtain target language characters, and entering the tone, the tone and the loudness which are set by the acquisition sender to obtain the condition to be integrated.
The further technical scheme is as follows: the judging whether the second search result is successful in matching comprises the following steps:
and if the second search result is successfully matched, acquiring the characters with the good score not smaller than the good score specified number and the highest good score to acquire target language characters, and entering the tone, the tone and the loudness set by the acquisition sender to acquire the condition to be integrated.
The further technical scheme is as follows: before the voice information from the sender and the receiving language set by the receiver are obtained, the method further comprises the following steps:
judging whether the sender is in a dormant state or not;
if the sender is in a dormant state, waking up the sender by adopting a voice wake-up technology to obtain a wake-up result;
judging whether the wake-up is successful or not according to the wake-up result;
if the wake-up is successful, entering the receiving language set by the receiving party and acquiring the voice information from the transmitting party;
if the sender is not in the dormant state, entering the receiving language set by the receiver and acquiring the voice information from the sender.
The invention also provides a multilingual conversion device comprising:
an acquisition unit configured to acquire voice information from a sender and a reception language set by a receiver;
the recognition unit is used for recognizing the voice information of the sender to obtain a language to be converted;
a first search condition obtaining unit, configured to integrate the language to be converted and a receiving language set by a receiving party, so as to obtain a first search condition;
the first search unit is used for searching in the first database according to the first search condition so as to obtain a first search result;
a first judging unit, configured to judge whether the first search result is successful in matching;
the second search condition acquisition unit is used for setting a rated number if the first search result is not successfully matched, and integrating the rated number with the first search condition to obtain a second search condition;
the second search unit is used for searching in the second database according to the second search condition so as to obtain a second search result;
a second judging unit, configured to judge whether the second search result is successful in matching;
the translation unit is used for calling a translation program to translate the language to be converted if the second search result is not successfully matched, so as to obtain target language characters;
the to-be-integrated condition acquisition unit is used for acquiring tone, tone and loudness set by a sender to obtain to-be-integrated conditions;
the voice conversion unit is used for converting the voice of the target language words according to the condition to be integrated so as to obtain target voice;
and the sending unit is used for sending the target voice to a receiver.
The further technical scheme is as follows: further comprises:
and the first text acquisition unit is used for acquiring the text which accords with the search condition in the first database if the first search result is successfully matched so as to obtain the target language text, and entering the tone, the tone and the loudness which are set by the acquisition sender so as to obtain the condition to be integrated.
The further technical scheme is as follows: further comprises:
and the second text acquisition unit is used for acquiring the text with the good score not smaller than the good score specified number and the highest good score if the second search result is successfully matched to obtain the target language text, and entering the tone, the tone and the loudness set by the acquisition sender to obtain the condition to be integrated.
The invention also provides a computer device which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the method when executing the computer program.
The present invention also provides a storage medium storing a computer program which, when executed by a processor, performs the above-described method.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the voice information sent by the sender is converted to form the language to be converted, and the first database, the second database and the third translation tool are called to carry out multiparty conversion according to the received language set by the receiver, so that the accuracy of the language conversion is improved, and the voice which can be received by the receiver is translated according to tone, tone and loudness, so that the language conversion efficiency and accuracy are improved, and different user requirements are met.
The invention is further described below with reference to the drawings and specific embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an application scenario of a multilingual conversion method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a multi-language conversion method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a multi-language conversion method according to another embodiment of the present invention;
FIG. 4 is a schematic block diagram of a multi-language conversion device according to an embodiment of the present invention;
FIG. 5 is a schematic block diagram of a multi-language conversion device according to another embodiment of the present invention;
fig. 6 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of a multi-language conversion method according to an embodiment of the present invention. Fig. 2 is a schematic flow chart of a multi-language conversion method according to an embodiment of the present invention. The multi-language conversion method is applied to a server, the server performs data interaction with a sender and a receiver, wherein the sender and the receiver are terminals, and the server performs language conversion according to contents sent and received by the sender and the receiver, converts one language into another language and presents the converted contents in a voice mode.
Fig. 2 is a flow chart of a multi-language conversion method according to an embodiment of the invention. As shown in fig. 2, the method includes the following steps S110 to S240.
S110, acquiring voice information from a sender and receiving language set by a receiver.
In this embodiment, an APP is provided on the interface of the sender, so that the user may send voice information by using the terminal of the sender, and the receiving language set by the receiver refers to the voice type received by the receiver, such as english, chinese, and the like.
S120, identifying the voice information of the sender to obtain the language to be converted.
In this embodiment, the language to be converted refers to text information after conversion of voice information sent by the sender.
In this embodiment, a voice recognition technology is specifically used to recognize the voice information input by the sender, and convert the voice information into text information.
S130, integrating the language to be converted and the receiving language set by the receiving party to obtain a first retrieval condition.
In this embodiment, the first search condition refers to a band conversion language that needs to be converted and a reception language set by the receiving side.
And S140, searching in the first database according to the first search condition to obtain a first search result.
In this embodiment, the first search result refers to a result obtained by searching in the first database according to the first search condition, whether the search is successful or not.
In this embodiment, the first database includes a sender-customized language library.
S150, judging whether the first search result is successful in matching.
In this embodiment, firstly, the first database is searched, and when the first database is not successfully searched, the second database is entered for searching again, so as to improve the accuracy of the whole language conversion.
And S160, if the first search result is successfully matched, acquiring characters which are in the first database and accord with the first search condition so as to obtain target language characters, and entering the step S220.
In this embodiment, the target language text refers to a language that can be received by the receiving party after the language to be converted is converted.
S170, if the first search result is not successfully matched, setting a rated number, and integrating the rated number with the first search condition to obtain a second search condition.
In the present embodiment, the second search condition refers to a condition including a set good score specifying number and the first search condition integrated together, that is, a condition that the first search condition must be satisfied and the good score specifying number must be satisfied.
And S180, searching in a second database according to the second search condition to obtain a second search result.
In this embodiment, the second database refers to a global public repository. The general public library refers to a database in which the general public participates in translation, and specifically users using the system globally participate in translation, and when participating, the users only need to select a primary language, input original language characters, target language and input target language characters, and the satisfaction degree is voted by the public. Such as: you get, translate into English; chinese: hello, english: hello; chinese: hello, english: hi; for the mass public pool of the whole people, on one hand, in order to reduce the storage amount of data, on the other hand, in order to avoid that some users maliciously submit irrelevant data, the system can automatically screen at regular intervals and process the data with low ticket number.
Of course, the user-defined language library refers to a database formed by user-defined translation, so that in order to facilitate the user to translate a set of communication rule library, the system searches the library first when performing text conversion, and if the user does not invoke a translation tool, the system directly performs speech synthesis.
In this embodiment, the second search result refers to a result obtained by searching in the second database according to the second search condition, whether the search is successful or not.
S190, judging whether the second search result is successful in matching;
and S200, if the second search result is successfully matched, acquiring characters with the good score not smaller than the good score specified number and the highest good score to acquire target language characters, and entering the step S220.
The score of each matched data must be greater than the score of 100, so that human malicious translation can be prevented as much as possible, and the score of the matched target language words must be greater than 100 to be selected for use, and then a piece of information with the highest score and the score greater than the score of 100 is acquired as the target language words.
S210, if the second search result is not matched successfully, a translation program is called to translate the language to be converted so as to obtain the target language characters.
And recognizing the voice information of the sender into voice to be converted by calling a translation module or using a third translation tool according to the received language set by the receiver, and translating the voice information into the received text.
S220, acquiring tone, pitch and loudness set by a sender to obtain conditions to be integrated.
In this embodiment, the condition to be integrated refers to a condition required for converting the target language text into the voice.
For obtaining the tone color set by the sender, the user firstly collects the tone color of the user when using the system, so as to ensure that the receiver can distinguish the other party and achieve the purpose of real co-sound barrier-free voice communication. The tone and the loudness are the tone and the loudness of the synthesized sound which can be set by the user in a self-defined way, and the system can be set by default.
S230, performing voice conversion on the target language words according to the condition to be integrated so as to obtain target voice.
In this embodiment, the target speech is a sound that is synthesized into the translated text, the extracted tone, the set tone and the loudness by a speech synthesis technology and can be understood by the receiver.
S240, the target voice is sent to a receiver.
In the whole process, a big data retrieval matching technology is adopted in the process of retrieving the first database and the second database, and a large amount of data is generated in a translation providing mechanism by the whole people, so that the data is stored in a sub-table sub-base mode, and a distributed multi-thread mode is needed to search when the matching data is searched.
In the whole process, in order to ensure the speed of data processing and to ensure the high availability and the normal operation of the server, a high-performance cluster server can be adopted, and a high-quality network is used, so that the delay of sending data is reduced.
According to the multi-language conversion method, the voice information sent by the sender is converted to form the language to be converted, the multi-language conversion is carried out in the first database, the second database and the third translation tool according to the received language set by the receiver, so that the accuracy of the language conversion is improved, the voice which can be received by the receiver is translated according to tone, tone and loudness, the language conversion efficiency and accuracy are improved, and different user requirements are met.
Fig. 3 is a flow chart of a multi-language conversion method according to another embodiment of the invention. As shown in fig. 3, the multilingual conversion method of the present embodiment includes steps S310 to S470. Steps S340 to S470 are similar to steps S110 to S240 in the above embodiment, and are not described herein. Steps S310 to S330 added in the present embodiment are described in detail below.
S310, judging whether the sender is in a dormant state or not;
s320, if the sender is in a dormant state, waking up the sender by adopting a voice wake-up technology to obtain a wake-up result;
s330, judging whether the wake-up is successful according to the wake-up result;
if the wake-up is successful, the step S340 is entered;
if the sender is not in the sleep state, the step S340 is entered.
The sender is set as a background running state in a standby state, and when voice input is recognized as a wake-up instruction by the server, the sender is automatically waken up and voice prompt is carried out, for example: the voice chat system is activated, please select the sending object or the receiving party, and continue to carry out voice prompt: the recipients that you choose are. At this time, the sender may input the ID number or the nickname of the receiver (both the ID and the nickname are unique), for example: 10000000 or Zhang three, after the server receives the instruction, according to the default language set by the sender, the voice recognition is performed to convert into characters, then the server automatically searches and retrieves the friend library of the sender, if there is the friend, the voice prompt is performed, such as: "established connection with Zhang san, please talk about the bar"; if the friend is not searched, performing voice prompt, and continuing voice prompt when the friend is not searched: the receiver selected by you is until the friend is found, but if the server waits for 30s to not receive the voice information yet, the sender is automatically put in a dormant state, and if the sender is used again, the sender needs to wake up again. Under the condition that the friends are searched, the sender can send voice messages to the friends at any time, and after the sender finishes speaking a sentence, if the server does not receive the voice messages again after 3 seconds, the voice messages are automatically sent. If the message is not sent again to the friend in 5 minutes from the time interval of the last message sending, automatically disconnecting the dialogue connection with Zhang III, and enabling the sender to be in a dormant state; if friends need to be switched, inputting a friend switching instruction by voice, and switching friends. When the server receives the voice information of the sender, firstly, the voice information set by the receiver is acquired, then the voice information is compared with the voice set by the sender, if the voice information is the same, the voice information is directly sent, if the voice information is different, the voice information is sent to the voice information processing module, the voice information is processed into the voice information of the voice set by the receiver, and then the voice information is automatically sent to the receiver.
Under the interface operation state, the sender and the receiver have two use modes, one is the same as that under the standby state, and a voice selection friend mode can also be used, and only one friend can communicate under the mode. One is that the sender manually selects friends, the voice information is input by pressing a voice input button, and when the voice information is input for the time, the voice information can be automatically sent by loosening the button. After receiving the voice message, the server performs language comparison or enters a language processing module, and the processed target voice is sent. After the receiver receives the information, the system can judge whether to play the voice information according to whether to automatically play the voice information set by the receiver.
When the sender is in a standby awakening state, voice chat is carried out by adopting a single channel, at the moment, only one friend can be connected in a conversation mode, and if the friends are to be switched, a voice command is input again to switch the friends. The chat performed by the sender using the interface adopts multiple channels, so that a plurality of friends can be manually selected to simultaneously chat.
Fig. 4 is a schematic block diagram of a multi-language conversion device 300 according to an embodiment of the present invention. As shown in fig. 4, the present invention further provides a multi-language conversion device 300 corresponding to the above multi-language conversion method. The multi-language conversion apparatus 300 includes a unit for performing the above-described multi-language conversion method, and may be configured in a server.
Specifically, referring to fig. 4, the multi-language conversion device 300 includes:
an obtaining unit 304, configured to obtain voice information from a sender and a receiving language set by a receiver;
a recognition unit 305, configured to recognize the voice information of the sender to obtain a language to be converted;
a first search condition obtaining unit 306, configured to integrate the language to be converted and a receiving language set by the receiving party, so as to obtain a first search condition;
a first search unit 307, configured to perform a search in the first database according to the first search condition, so as to obtain a first search result;
a first judging unit 308, configured to judge whether the first search result is successful in matching;
a second search condition obtaining unit 309, configured to set a specified number if the first search result is not successfully matched, and integrate with the first search condition to obtain a second search condition;
a second search unit 310, configured to search in a second database according to a second search condition, so as to obtain a second search result;
a second judging unit 311, configured to judge whether the second search result is successful in matching;
a translation unit 312, configured to invoke a translation program to translate the language to be translated to obtain a target language text if the second search result is not matched successfully;
a condition to be integrated obtaining unit 313, configured to obtain the tone, the pitch and the loudness set by the sender, so as to obtain a condition to be integrated;
a voice conversion unit 314, configured to perform voice conversion on the target language text according to the condition to be integrated, so as to obtain target voice;
a sending unit 315, configured to send the target voice to a receiving party.
In an embodiment, further comprising:
and the first text obtaining unit 316 is configured to obtain the text that matches the search condition in the first database if the first search result is successfully matched, so as to obtain the target language text, and enter the tone, the pitch and the loudness set by the obtaining sender, so as to obtain the condition to be integrated.
In an embodiment, further comprising:
and a second text obtaining unit 317, configured to obtain a text with a score not less than the score specified by the score and the highest score if the second search result is successfully matched, so as to obtain a target language text, and enter the tone, the pitch and the loudness set by the sender to obtain the condition to be integrated.
Fig. 5 is a schematic block diagram of a multi-language conversion device 300 according to another embodiment of the present invention. As shown in fig. 5, the multilingual conversion apparatus 300 of the present embodiment is added with a state judgment unit 301, a wake-up unit 302, and a wake-up judgment unit 303 on the basis of the above embodiments.
A state judging unit 301, configured to judge whether the sender is in a sleep state; if the sender is not in the dormant state, entering the receiving language set by the receiver and acquiring the voice information from the sender.
A wake-up unit 302, configured to wake up the sender by using a voice wake-up technology if the sender is in a sleep state, so as to obtain a wake-up result;
a wake-up judging unit 303, configured to judge whether wake-up is successful according to a wake-up result; if the wake-up is successful, entering the receiving language set by the receiving party and acquiring the voice information from the transmitting party.
It should be noted that, as will be clearly understood by those skilled in the art, the specific implementation process of the multi-language conversion device 300 and each unit may refer to the corresponding description in the foregoing method embodiments, and for convenience and brevity of description, the description is omitted here.
The above-described multilingual conversion apparatus 300 may be implemented in the form of a computer program which can be run on a computer device as shown in fig. 6.
Referring to fig. 6, fig. 6 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server, and the server may be a stand-alone server or may be a server cluster formed by a plurality of servers.
With reference to FIG. 6, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a multi-language conversion method.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the execution of a computer program 5032 in the non-volatile storage medium 503, which computer program 5032, when executed by the processor 502, causes the processor 502 to perform a multi-language conversion method.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of a portion of the architecture in connection with the present application and is not intended to limit the computer device 500 to which the present application is applied, and that a particular computer device 500 may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to execute a computer program 5032 stored in a memory to implement the steps of:
acquiring voice information from a sender and a receiving language set by a receiver; identifying the voice information of the sender to obtain a language to be converted; integrating the language to be converted and a receiving language set by a receiver to obtain a first retrieval condition; searching in a first database according to the first search condition to obtain a first search result; judging whether the first search result is successfully matched; if the first search result is not successfully matched, setting a rated number, and integrating the rated number with the first search condition to obtain a second search condition; searching in the second database according to the second search condition to obtain a second search result; judging whether the second search result is successfully matched; if the second search result is not successfully matched, a translation program is called to translate the language to be converted so as to obtain target language characters; acquiring tone, pitch and loudness set by a sender to obtain conditions to be integrated; performing voice conversion on the target language words according to the condition to be integrated to obtain target voice; and sending the target voice to a receiver.
The first database comprises a sender custom language library.
In one embodiment, when the step of determining whether the first search result is a match success is implemented by the processor 502, the following steps are specifically implemented:
if the first search result is successfully matched, acquiring the characters which are in the first database and accord with the first search condition to obtain target language characters, and entering the tone, the tone and the loudness which are set by the acquisition sender to obtain the condition to be integrated.
In one embodiment, when the step of determining whether the second search result is a match success is implemented by the processor 502, the following steps are specifically implemented:
and if the second search result is successfully matched, acquiring the characters with the good score not smaller than the good score specified number and the highest good score to acquire target language characters, and entering the tone, the tone and the loudness set by the acquisition sender to acquire the condition to be integrated.
In one embodiment, before implementing the step of acquiring the voice information from the sender and the receiving language set by the receiver, the processor 502 further implements the following steps:
judging whether the sender is in a dormant state or not;
if the sender is in a dormant state, waking up the sender by adopting a voice wake-up technology to obtain a wake-up result;
judging whether the wake-up is successful or not according to the wake-up result;
if the wake-up is successful, entering the receiving language set by the receiving party and acquiring the voice information from the transmitting party;
if the sender is not in the dormant state, entering the receiving language set by the receiver and acquiring the voice information from the sender.
It should be appreciated that in embodiments of the present application, the processor 502 may be a central processing unit (CentralProcessing Unit, CPU), the processor 502 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Those skilled in the art will appreciate that all or part of the flow in a method embodying the above described embodiments may be accomplished by computer programs instructing the relevant hardware. The computer program comprises program instructions, and the computer program can be stored in a storage medium, which is a computer readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer readable storage medium. The storage medium stores a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring voice information from a sender and a receiving language set by a receiver; identifying the voice information of the sender to obtain a language to be converted; integrating the language to be converted and a receiving language set by a receiver to obtain a first retrieval condition; searching in a first database according to the first search condition to obtain a first search result; judging whether the first search result is successfully matched; if the first search result is not successfully matched, setting a rated number, and integrating the rated number with the first search condition to obtain a second search condition; searching in the second database according to the second search condition to obtain a second search result; judging whether the second search result is successfully matched; if the second search result is not successfully matched, a translation program is called to translate the language to be converted so as to obtain target language characters; acquiring tone, pitch and loudness set by a sender to obtain conditions to be integrated; performing voice conversion on the target language words according to the condition to be integrated to obtain target voice; and sending the target voice to a receiver.
The first database comprises a sender custom language library.
In one embodiment, when the processor executes the computer program to implement the step of determining whether the first search result is a match success, the method specifically includes the following steps:
if the first search result is successfully matched, acquiring the characters which are in the first database and accord with the first search condition to obtain target language characters, and entering the tone, the tone and the loudness which are set by the acquisition sender to obtain the condition to be integrated.
In one embodiment, when the processor executes the computer program to implement the step of determining whether the second search result is a match success, the method specifically includes the following steps:
and if the second search result is successfully matched, acquiring the characters with the good score not smaller than the good score specified number and the highest good score to acquire target language characters, and entering the tone, the tone and the loudness set by the acquisition sender to acquire the condition to be integrated.
In one embodiment, before executing the computer program to implement the step of obtaining the voice information from the sender and the receiving language set by the receiver, the processor further implements the following steps:
judging whether the sender is in a dormant state or not; if the sender is in a dormant state, waking up the sender by adopting a voice wake-up technology to obtain a wake-up result; judging whether the wake-up is successful or not according to the wake-up result; if the wake-up is successful, entering the receiving language set by the receiving party and acquiring the voice information from the transmitting party; if the sender is not in the dormant state, entering the receiving language set by the receiver and acquiring the voice information from the sender.
The storage medium may be a U-disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, or other various computer-readable storage media that can store program codes.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be combined, divided and deleted according to actual needs. In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The integrated unit may be stored in a storage medium if implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a terminal, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A method of multilingual conversion comprising:
acquiring voice information from a sender and a receiving language set by a receiver;
identifying the voice information of the sender to obtain a language to be converted;
integrating the language to be converted and a receiving language set by a receiver to obtain a first retrieval condition;
searching in a first database according to the first search condition to obtain a first search result;
judging whether the first search result is successfully matched;
if the first search result is not successfully matched, setting a rated number, and integrating the rated number with the first search condition to obtain a second search condition;
searching in the second database according to the second search condition to obtain a second search result;
judging whether the second search result is successfully matched;
if the second search result is not successfully matched, a translation program is called to translate the language to be converted so as to obtain target language characters;
acquiring tone, pitch and loudness set by a sender to obtain conditions to be integrated;
performing voice conversion on the target language words according to the condition to be integrated to obtain target voice;
and sending the target voice to a receiver.
2. The method of claim 1, wherein the first database comprises a sender-custom language library.
3. The method of claim 1, wherein the determining whether the first search result is successful in matching comprises:
if the first search result is successfully matched, acquiring the characters which are in the first database and accord with the first search condition to obtain target language characters, and entering the tone, the tone and the loudness which are set by the acquisition sender to obtain the condition to be integrated.
4. The method of claim 1, wherein the determining whether the second search result is successful in matching comprises:
and if the second search result is successfully matched, acquiring the characters with the good score not smaller than the good score specified number and the highest good score to acquire target language characters, and entering the tone, the tone and the loudness set by the acquisition sender to acquire the condition to be integrated.
5. The multi-language conversion method according to claim 1, wherein before the voice information from the sender and the receiving language set by the receiver are acquired, further comprising:
judging whether the sender is in a dormant state or not;
if the sender is in a dormant state, waking up the sender by adopting a voice wake-up technology to obtain a wake-up result;
judging whether the wake-up is successful or not according to the wake-up result;
if the wake-up is successful, entering the receiving language set by the receiving party and acquiring the voice information from the transmitting party;
if the sender is not in the dormant state, entering the receiving language set by the receiver and acquiring the voice information from the sender.
6. A multilingual conversion apparatus comprising:
an acquisition unit configured to acquire voice information from a sender and a reception language set by a receiver;
the recognition unit is used for recognizing the voice information of the sender to obtain a language to be converted;
a first search condition obtaining unit, configured to integrate the language to be converted and a receiving language set by a receiving party, so as to obtain a first search condition;
the first search unit is used for searching in the first database according to the first search condition so as to obtain a first search result;
a first judging unit, configured to judge whether the first search result is successful in matching;
the second search condition acquisition unit is used for setting a rated number if the first search result is not successfully matched, and integrating the rated number with the first search condition to obtain a second search condition;
the second search unit is used for searching in the second database according to the second search condition so as to obtain a second search result;
a second judging unit, configured to judge whether the second search result is successful in matching;
the translation unit is used for calling a translation program to translate the language to be converted if the second search result is not successfully matched, so as to obtain target language characters;
the to-be-integrated condition acquisition unit is used for acquiring tone, tone and loudness set by a sender to obtain to-be-integrated conditions;
the voice conversion unit is used for converting the voice of the target language words according to the condition to be integrated so as to obtain target voice;
and the sending unit is used for sending the target voice to a receiver.
7. The multi-language conversion device of claim 6, further comprising:
and the first text acquisition unit is used for acquiring the text which accords with the search condition in the first database if the first search result is successfully matched so as to obtain the target language text, and entering the tone, the tone and the loudness which are set by the acquisition sender so as to obtain the condition to be integrated.
8. The multilingual conversion apparatus of claim 7 further comprising:
and the second text acquisition unit is used for acquiring the text with the good score not smaller than the good score specified number and the highest good score if the second search result is successfully matched to obtain the target language text, and entering the tone, the tone and the loudness set by the acquisition sender to obtain the condition to be integrated.
9. A computer device, characterized in that it comprises a memory on which a computer program is stored and a processor which, when executing the computer program, implements the method according to any of claims 1-5.
10. A storage medium storing a computer program which, when executed by a processor, performs the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911117209.5A CN110866410B (en) | 2019-11-15 | 2019-11-15 | Multilingual conversion method, multilingual conversion device, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911117209.5A CN110866410B (en) | 2019-11-15 | 2019-11-15 | Multilingual conversion method, multilingual conversion device, computer device, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110866410A CN110866410A (en) | 2020-03-06 |
| CN110866410B true CN110866410B (en) | 2023-07-25 |
Family
ID=69654428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911117209.5A Active CN110866410B (en) | 2019-11-15 | 2019-11-15 | Multilingual conversion method, multilingual conversion device, computer device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866410B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112447179A (en) * | 2019-08-29 | 2021-03-05 | 中国移动通信有限公司研究院 | Voice interaction method, device, equipment and computer readable storage medium |
| CN111739531B (en) * | 2020-06-11 | 2022-08-09 | 浙江沁园水处理科技有限公司 | Voice control method |
| WO2022140966A1 (en) * | 2020-12-28 | 2022-07-07 | 深圳市优必选科技股份有限公司 | Cross-language voice conversion method, computer device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503195A (en) * | 2016-11-02 | 2017-03-15 | 四川译宝联科技有限公司 | A kind of translation word stocks search method and system based on search engine |
| CN107220243A (en) * | 2017-05-31 | 2017-09-29 | 陈振 | A kind of Database Interactive translation system |
| CN107301176A (en) * | 2017-06-30 | 2017-10-27 | 广东欧珀移动通信有限公司 | A kind of interpretation method, device and storage medium, electronic equipment |
| CN109960813A (en) * | 2019-03-18 | 2019-07-02 | 维沃移动通信有限公司 | A kind of interpretation method, mobile terminal and computer readable storage medium |
| CN110232107A (en) * | 2019-05-08 | 2019-09-13 | 深圳市小满科技有限公司 | A kind of product data acquisition methods |
| CN110444198A (en) * | 2019-07-03 | 2019-11-12 | 平安科技（深圳）有限公司 | Search method, device, computer equipment and storage medium |
-
2019
- 2019-11-15 CN CN201911117209.5A patent/CN110866410B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503195A (en) * | 2016-11-02 | 2017-03-15 | 四川译宝联科技有限公司 | A kind of translation word stocks search method and system based on search engine |
| CN107220243A (en) * | 2017-05-31 | 2017-09-29 | 陈振 | A kind of Database Interactive translation system |
| CN107301176A (en) * | 2017-06-30 | 2017-10-27 | 广东欧珀移动通信有限公司 | A kind of interpretation method, device and storage medium, electronic equipment |
| CN109960813A (en) * | 2019-03-18 | 2019-07-02 | 维沃移动通信有限公司 | A kind of interpretation method, mobile terminal and computer readable storage medium |
| CN110232107A (en) * | 2019-05-08 | 2019-09-13 | 深圳市小满科技有限公司 | A kind of product data acquisition methods |
| CN110444198A (en) * | 2019-07-03 | 2019-11-12 | 平安科技（深圳）有限公司 | Search method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110866410A (en) | 2020-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866410B (en) | Multilingual conversion method, multilingual conversion device, computer device, and storage medium | |
| EP2959476B1 (en) | Recognizing accented speech | |
| US10599645B2 (en) | Bidirectional probabilistic natural language rewriting and selection | |
| KR101683944B1 (en) | Speech translation system, control apparatus and control method | |
| US20190164064A1 (en) | Question and answer interaction method and device, and computer readable storage medium | |
| CN112262430A (en) | Automatically determining language for speech recognition of a spoken utterance received via an automated assistant interface | |
| US11295092B2 (en) | Automatic post-editing model for neural machine translation | |
| CN110164435A (en) | Audio recognition method, device, equipment and computer readable storage medium | |
| WO2017016104A1 (en) | Question-answer information processing method and apparatus, storage medium, and device | |
| WO2014159473A2 (en) | Automatic supplementation of word correction dictionaries | |
| CN1704958A (en) | Information transmission system and information transmission method | |
| CN109074354A (en) | Show the method and terminal device of candidate item | |
| CN103853703A (en) | Information processing method and electronic equipment | |
| CN106713111B (en) | Processing method for adding friends, terminal and server | |
| CN109782997B (en) | Data processing method, device and storage medium | |
| CN108595406B (en) | User state reminding method and device, electronic equipment and storage medium | |
| CN109582775B (en) | Information input method, device, computer equipment and storage medium | |
| CN110956958A (en) | Searching method, searching device, terminal equipment and storage medium | |
| CN113643684B (en) | Speech synthesis method, device, electronic equipment and storage medium | |
| CA3131060C (en) | Speech analysis system | |
| CN109725798B (en) | Intelligent role switching method and related device | |
| WO2022213943A1 (en) | Message sending method, message sending apparatus, electronic device, and storage medium | |
| US11895269B2 (en) | Determination and visual display of spoken menus for calls | |
| US20190279623A1 (en) | Method for speech recognition dictation and correction by spelling input, system and storage medium | |
| JP2021082125A (en) | Dialogue device |
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 |