CN108509428B - Earphone translation method and system - Google Patents

Earphone translation method and system Download PDF

Info

Publication number
CN108509428B
CN108509428B CN201810162977.1A CN201810162977A CN108509428B CN 108509428 B CN108509428 B CN 108509428B CN 201810162977 A CN201810162977 A CN 201810162977A CN 108509428 B CN108509428 B CN 108509428B
Authority
CN
China
Prior art keywords
earphone
audio
storage box
translation
wireless connection
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
Application number
CN201810162977.1A
Other languages
Chinese (zh)
Other versions
CN108509428A (en
Inventor
李建明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Boomtech Industrial Co ltd
Original Assignee
Shenzhen Boomtech Industrial Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Boomtech Industrial Co ltd filed Critical Shenzhen Boomtech Industrial Co ltd
Priority to CN201810162977.1A priority Critical patent/CN108509428B/en
Publication of CN108509428A publication Critical patent/CN108509428A/en
Application granted granted Critical
Publication of CN108509428B publication Critical patent/CN108509428B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/42—Data-driven translation
    • G06F40/45—Example-based machine translation; Alignment
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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 TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
    • H04R1/1033—Cables or cables storage, e.g. cable reels
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
    • H04R1/1083—Reduction of ambient noise
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
    • H04R1/1091—Details not provided for in groups H04R1/1008 - H04R1/1083
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W76/00—Connection management
    • H04W76/10—Connection setup
    • H04W76/11—Allocation or use of connection identifiers
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • G10L2021/02161—Number of inputs available containing the signal or the noise to be suppressed
    • G10L2021/02163—Only one microphone
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2420/00—Details of connection covered by H04R, not provided for in its groups
    • H04R2420/07—Applications of wireless loudspeakers or wireless microphones
    • 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
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Acoustics & Sound (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Machine Translation (AREA)
  • Circuit For Audible Band Transducer (AREA)

Abstract

The embodiment of the invention discloses an earphone translation method, which is characterized by being applied to an earphone system comprising a first earphone, a second earphone and an earphone storage box, wherein the translation method comprises the following steps: the first earphone is wirelessly connected with the second earphone and the earphone storage box; the second earphone receives the main control command and initiates a main control application to the first earphone; the first earphone receives the main control application and forwards the main control application to the earphone storage box; the earphone storage box is disconnected from the wireless connection with the first earphone, and the wireless connection with the second earphone is established; the second earphone acquires a first audio and sends the first audio to the earphone storage box; the earphone storage box receives the first audio, obtains a second audio obtained by translating the first audio according to the first audio, and sends the second audio to a second earphone; and the second earphone is connected with the second audio and sends the second audio to the first earphone for playing. By adopting the method and the device, the translation efficiency among different languages can be improved.

Description

Earphone translation method and system
Technical Field
The invention relates to the field of wireless communication, in particular to an earphone translation method and system.
Background
Today, with rapid development of science and technology, people are increasingly open in communication, and in the process of tourism, entertainment and academic communication, not only information is more and more globalized, but also languages are more and more diversified, so that language communication barriers are common. How to conveniently and quickly provide translation contents for two communication parties with language barrier, and realize barrier-free communication between the two parties is a considerable problem.
In the existing translation method, a large amount of human resources are consumed for manually obtaining translation results, resources are not easy to store, and the translation results cannot be reused, and the problems of time and labor consumption for voice acquisition and low translation efficiency exist when the translation results are obtained by a common terminal.
Disclosure of Invention
In view of this, embodiments of the present invention provide an earphone translation method and system, which enable a user to quickly obtain a desired translated voice or text message, facilitate communication among users of different languages, and improve translation efficiency.
In order to solve the above technical problem, a first aspect of the embodiments of the present invention provides an earphone translation method, which is applied to an earphone system including a first earphone, a second earphone and an earphone storage box, and includes:
when the first earphone and the second earphone are taken out of the earphone containing box, triggering the first earphone to establish wireless connection with the second earphone, and establishing wireless connection between the first earphone and the earphone containing box;
the second earphone receives a main control instruction and initiates a main control application to the first earphone;
the first earphone receives the main control application and forwards the main control application to the earphone storage box;
the earphone storage box is disconnected from the wireless connection with the first earphone, and the wireless connection with the second earphone is established;
the second earphone acquires a first audio and sends the first audio to the earphone storage box;
the earphone storage box receives the first audio, obtains a second audio obtained by translating the first audio according to the first audio, and sends the second audio to a second earphone;
and the second earphone receives the second audio and sends the second audio to the first earphone for playing.
Optionally, the acquiring, by the second headset, the first audio includes:
acquiring a first audio from a terminal which establishes wireless connection with the second earphone; or
Picking up a main voice close to a target sound source;
whether a noise reduction mode is started is detected, if so, the method comprises the following steps:
picking up auxiliary voices far away from a target sound source;
and filtering the noise in the main voice according to the auxiliary voice to obtain a first audio.
Optionally, the detecting whether to turn on the noise reduction mode includes:
the second earphone receives a noise reduction instruction and starts a noise reduction mode; or:
the earphone storage box receives noise reduction operation and sends the noise reduction instruction to the second earphone, and the second earphone starts a noise reduction mode.
Optionally, the acquiring, by the second headset, the first audio includes:
and acquiring a first audio from the terminal which establishes wireless connection with the second earphone.
Optionally, the receiving, by the earphone receiver, the first audio, and the obtaining of the second audio after the first audio is translated includes:
sending the first audio to a cloud server, and receiving a second audio obtained by translating the first audio from the cloud server; or:
and translating the first audio according to a translation engine and a corpus local to the earphone storage box to obtain a second audio.
Optionally, the receiving of the earphone receiving box receives the first audio, and further includes after acquiring the second audio after the first audio is translated:
acquiring a first word corresponding to the first audio and a second word corresponding to the second audio from a cloud server; or
Acquiring first characters corresponding to the first audio and second characters corresponding to the second audio through a character acquisition module of the earphone storage box;
and displaying the first characters and the second characters.
Optionally, the translating the first audio according to a translation engine and a corpus local to the earphone storage box to obtain a second audio includes:
when first audio is received, confirming that the earphone storage box stores the first audio in advance;
and acquiring a second audio which is stored corresponding to the first audio.
Optionally, when the first audio is received, before searching whether the first audio is pre-stored in the earphone storage box, the method includes:
receiving a modification instruction of the first character, obtaining the modified first character, and obtaining a second audio translated by the first audio according to the modified first character and the first audio;
and correspondingly storing the first audio and the second audio in an earphone storage box.
Optionally, the receiving, by the second headphone, the second audio and sending the second audio to the first headphone for playing further includes:
and the second earphone plays the second audio.
Accordingly, a second aspect of the embodiments of the present invention provides an earphone translation system, which includes a first earphone, a second earphone and an earphone storage box, wherein:
the first earphone comprises a first wireless communication module and a first loudspeaker, the first wireless communication module is used for establishing wireless connection with the second earphone and the earphone storage box, and the first loudspeaker is used for playing audio received by the first wireless communication module;
the second earphone comprises a second wireless communication module, a second control module, a second processor and a second voice acquisition module, the second wireless communication module is used for establishing wireless connection with the first earphone, the second control module is used for receiving master control operation, the second processor generates a master control instruction according to the master control operation and enables the second wireless communication module to send a master control application to the first earphone, the first wireless communication module is disconnected from the wireless connection with the earphone containing box, and the second wireless communication module is established with the earphone containing box in a wireless connection mode; the second voice acquisition module is used for acquiring a first audio, and the second wireless communication module is also used for sending the first audio to the earphone storage box, receiving a second audio obtained by translating the first audio, and sending the second audio to the first earphone for playing;
the earphone containing box comprises a first earphone seat, a second earphone seat, a box body wireless communication module and a translation module, wherein the first earphone seat is used for placing a first earphone, the second earphone seat is used for placing a second earphone, and the box body wireless communication module is used for establishing wireless connection with the first earphone or the second earphone and receiving a first audio frequency sent by the second earphone; the translation module is used for acquiring a second audio corresponding to the translated first audio; the box body wireless communication module is also used for sending the second audio to the second earphone.
Optionally, the second earphone is used for connecting with a terminal and acquiring a first audio from the terminal; or:
the second voice acquisition module comprises a main microphone and an auxiliary microphone, wherein:
the primary microphone is used for picking up primary voice close to a target sound source;
the auxiliary microphone is used for picking up auxiliary voice far away from a target sound source;
the second processor is used for filtering noise in the main voice according to the auxiliary voice to obtain a first audio frequency.
Optionally, the second control module is further configured to receive a noise reduction operation, and the second processor is further configured to generate a noise reduction instruction according to the noise reduction operation; or:
the earphone storage box comprises a box body control module and a processor, wherein the box body control module is used for receiving noise reduction operation, and the processor generates a noise reduction instruction according to the noise reduction operation and sends the noise reduction instruction to the second earphone.
Optionally, the earphone storage box is connected with the cloud server, and receives a second audio obtained by translating the first audio from the cloud server; or:
the translation module comprises a local translation engine and a corpus, and is used for translating the first audio to obtain a second audio obtained by translating the first audio.
Optionally, the earphone storage box is configured to obtain, from a cloud server, first characters corresponding to the first audio and second characters corresponding to the second audio; or
The earphone storage box comprises a character acquisition module which is used for acquiring first characters corresponding to the first audio frequency and second characters corresponding to the second audio frequency according to the first audio frequency;
the earphone receiver includes the display screen, is used for right first characters with the second characters are shown.
Optionally, the earphone storage box includes a memory and a search module, where the memory is used to correspondingly store the first audio and a second audio obtained by translating the first audio;
the searching module is used for searching and acquiring the first audio and the second audio corresponding to the first audio which are pre-stored in the memory when the first audio is received.
Optionally, the display screen is configured to receive a modification instruction of the user on the first text, to obtain a modified first text, and the translation module is configured to obtain a second audio translated by the first audio according to the modified first text and the first audio.
Optionally, the second earphone is further configured to play the second audio.
The embodiment of the invention has the following beneficial effects:
in the earphone translation system comprising a first earphone, a second earphone and an earphone storage box, the first earphone and the second earphone are triggered to be in wireless connection, then one earphone, for example, the first earphone receives a main control command to become a main earphone and establish wireless connection with the earphone storage box, and the connection method enables only the main earphone in the two earphones to be in direct communication with the earphone storage box, so that the signal transmission target in the system is very clear and no occupation or series transmission exists; then first pronunciation that first earphone received needs translation, and send first pronunciation for the earphone receiver, translation module in the earphone receiver turns over first pronunciation locally or transmits to the high in the clouds and carries out the translation, obtain the second pronunciation after the translation, send for first earphone, first earphone receives the second pronunciation, and forward to first earphone and play, at this translation in-process, earphone translation system can directly translate the pronunciation received, the user only need wear the earphone and just can carry out the dialogue of same language and need not spend extra time and obtain the translation result, high convenience and fast, the translation efficiency has been promoted.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a possible earphone translation system provided by an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for interpreting an earphone according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for reducing noise in a translation process according to an embodiment of the present invention;
FIG. 4 is a flowchart illustration of a method for improving translation quality according to an embodiment of the present invention;
fig. 5 is a flowchart illustrating a specific earphone translation method according to an embodiment of the present invention;
fig. 6 is a block diagram of a headset translation system according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a possible headset translating system in an embodiment of the present invention: fig. 7 (a) is a schematic view of a second earphone placed in an earphone storage box, and fig. 7 (B) is a schematic view of a first earphone structure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "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.
In order to better understand the technical solution of the present application, a brief description is provided below for an application of an embodiment of the related art. Referring to fig. 1, fig. 1 is a schematic diagram of a possible earphone translation system 10 according to an embodiment of the present invention, which includes an earphone storage box formed by a first earphone storage box portion 101 and a second earphone storage box portion 102, and a first earphone 103 and a second earphone 104. In this system, the second earphone housing part 102 is used for housing the first earphone 103 and the second earphone 104, and the inner space formed by the second earphone housing part 102 is used for housing the first earphone housing part 101. And the earphone storage box is also used for acquiring the translated audio and sending the translated audio to the first earphone 103 or the second earphone 104 for playing. In the process, as the earphone storage box and the left second earphone need to be wirelessly connected, the connection relationship and the data transmission relationship between the earphone storage box and the left second earphone are a part worth researching, and in addition, how the earphone translation system obtains the audio to be translated and the translation result corresponding to the audio is another key problem to be solved.
An embodiment of the present application provides an improved solution for the above problem, please refer to fig. 2, and fig. 2 is a schematic flow chart of an earphone translation method according to an embodiment of the present invention, as shown in fig. 2, the earphone translation method includes:
s201, the first earphone and the second earphone establish wireless connection according to the triggering instruction.
Specifically, when the first earphone and the second earphone are taken out of the earphone accommodating box, the first earphone is triggered to be wirelessly connected with the second earphone.
In an alternative embodiment, when the first earphone and the second earphone are placed in the earphone containing box, the two earphones comprise contacts capable of being connected with the earphone containing box, and when the earphones are connected with the contacts of the earphone containing box, the earphone containing box can charge the two earphones. At this time, the two earphones are in a charging state or a power-off state, and wireless connection or wireless transmission cannot be carried out. When the two earphones are taken out from the storage box, the two earphones are in the power-on state and the wireless network signals are normal, and wireless connection can be carried out. Optionally, the first earphone and the second earphone are triggered to perform wireless connection, the first earphone and the second earphone are automatically triggered to perform connection after being taken out from the earphone storage box, or the first earphone and/or the second earphone receive a connection instruction of a user, then the earphone receiving the instruction sends a connection application to the other earphone according to a connection protocol of the earphone, and the other earphone identifies a connectable opposite earphone according to the connection protocol in the earphone, so that the first earphone and the second earphone are finally and successfully established wireless connection. The connection instruction initiated by the user to the earphone can be realized through functional keys, touch control, rhythmic knocking and the like, and the wireless connection can comprise connection modes such as Bluetooth, wifi, z I gbee or NB-I OT and the like. After the first earphone and the second earphone establish a wireless connection, S202 is performed.
S202, the first earphone and the earphone storage box are in wireless connection according to the triggering instruction.
Specifically, in the earphone translation system according to the embodiment of the present invention, there are a master earphone capable of establishing wireless connection with an earphone storage case and performing wireless communication, and a slave earphone incapable of establishing wireless connection with the earphone storage case.
In an alternative embodiment, the first earphone is the main earphone by default, so the first earphone needs to establish a wireless connection with the earphone storage box for subsequent wireless communication transmission. When first earphone was placed in the earphone receiver, unable initiation wireless connection, when first earphone took out from the earphone receiver, automatic trigger first earphone initiated the connection application to the earphone receiver, and the earphone receiver carries out authentication to first earphone according to both built-in agreements, and the back of passing the authentication agrees to establish wireless connection with first earphone.
S203, the second earphone receives the main control instruction and initiates a main control application to the first earphone.
Specifically, when a user wants to replace the second earphone as the main earphone to establish wireless connection with the mobile phone storage box, a main control instruction needs to be sent to the second earphone. Optionally, the method of sending the main control instruction includes key operation, touch control, rhythmic tapping operation, and the like. And after receiving the main control command, the second earphone sends a main control application to the first earphone, and the first earphone receives the main control application sent by the second earphone. S204 is performed.
S204, the first earphone forwards the main control application to the earphone containing box.
Specifically, since the second earphone cannot directly communicate with the earphone storage box as a slave earphone, the main control application of the second earphone needs to be forwarded to the earphone storage box through the first earphone. The second earphone applies for the master control authority, the original main earphone, namely the first earphone and the earphone storage box simultaneously apply for the master control authority, the first earphone forwards the master control application of the second earphone to the earphone storage box, and the master control application that the first earphone passes through the second earphone is indicated.
S205, the earphone storage box is disconnected from the wireless connection with the first earphone, and the wireless connection with the second earphone is established.
Specifically, the earphone receiver receives a main control application of a second earphone forwarded by a first earphone, the wireless connection with the first earphone is disconnected, then the wireless connection application is initiatively initiated to the second earphone, and the second earphone passes through the wireless connection application and the wireless connection is established with the earphone receiver.
In an alternative embodiment, in the process of S203-S205, only one operation received by the earphone is translated, that is, the main control operation received by the second earphone, and the subsequent process of switching the earphone connected to the earphone storage box from the first earphone to the second earphone is performed automatically without manual operation. And this process has accomplished the master-slave authority switching process of two earphones in the earphone translation system, by first earphone connection earphone receiver, for acquiescence main earphone, the second earphone is the earphone from, switches into the second earphone and connects the earphone receiver for main earphone, and first earphone is from the earphone. S206 is performed.
S206, the second earphone acquires the first audio and sends the first audio to the earphone containing box.
In an alternative embodiment, the second headphone acquires the first audio, i.e. the audio to be translated, and the method includes two methods: firstly, a microphone is arranged on a second earphone, and the microphone picks up audio to be translated; secondly, the earphone is connected with the terminal, and receives the audio data sent by the terminal to obtain the audio needing to be translated. The first method is generally used to pick up the voice uttered by the user, and the application scenario includes talking with different language objects, bilingual learning, etc., and the second method is generally used to obtain a piece of existing audio that needs to be translated, and the application scenario includes watching a movie, a tv show, or bilingual cross-learning. Optionally, noise is likely to exist in the audio picked up by the microphone, so that noise reduction processing needs to be performed on the picked-up audio, where the noise reduction method includes setting a master microphone and a slave microphone, and the master voice picked up by the master microphone is subjected to noise reduction processing according to the slave voice picked up by the slave microphone, and the specific method is shown in the embodiment corresponding to fig. 3.
After obtaining the first audio that needs the translation, the user makes it send first audio for the earphone receiver with the operation second earphone.
S207, the earphone containing box obtains a second audio obtained by translating the first audio according to the first audio, and sends the second audio to a second earphone.
In an alternative embodiment, the earphone containing box obtains the first audio according to the first audio, and the translated second audio includes two meanings: firstly, the earphone storage box comprises a local translation engine and a semantic library, and can be used for directly translating the received first audio locally to obtain a translated second audio; and secondly, the earphone storage box is connected with the cloud server, after the earphone storage box receives the first audio needing to be translated, the first audio is sent to the cloud server for translation, and then the second audio obtained by translating the first audio is obtained from the cloud server. The first method can enable the earphone translation system to obtain translation results quickly, translation efficiency is improved, the second method can reduce storage and load pressure of an earphone storage box, and design complexity of earphone storage is reduced.
In an alternative embodiment, after the first audio is sent to the earphone storage box, the language type of the translation needs to be set, for example, the second earphone language type is set to "chinese", the first earphone language type is set to "english", which indicates that the first audio received from the second earphone needs to be recognized as chinese, and the translated second audio is english and sent to the first earphone. Correspondingly, chinese-French, chinese-Japanese, english-Japanese and the like can be set to represent the inter-translation of the corresponding language types. This process can improve the efficiency of recognition of the first audio and obtain a target language type that meets the demand.
In an optional embodiment, after receiving the first audio, the earphone storage box may obtain the first text after the speech recognition according to the first audio, and after obtaining the second audio obtained by translating the first audio, may obtain the second text after the speech recognition according to the second audio. And the user can modify the first characters, so that the identification result of the first audio is more accurate. This process will be described in detail in the corresponding embodiment of fig. 4.
After the second audio obtained by translating the first audio is obtained, the earphone storage box sends the second audio to a second earphone through wireless transmission. S208 is performed.
And S208, the second earphone sends the second audio to the first earphone for playing.
In an optional embodiment, the second audio obtained by translating the first audio through the earphone storage box is received by the second earphone and sent to the first earphone, and the second audio is played by the loudspeaker of the first earphone. To this end, the headset translation system completes the whole translation process, including: a second earphone (main earphone) receives the first audio and sends the first audio to an earphone storage box; the earphone storage box obtains a second audio after the first audio is translated according to the first audio and sends the second audio to a second earphone; the second earphone transmitting the second audio to the first earphone (slave earphone); the first earphone plays the second audio.
Optionally, after receiving the second audio, the second earphone may also play the second audio through a microphone disposed on the second earphone, in addition to sending the second audio to the first earphone for playing, so that the user can hear the audio corresponding to the translated audio sent by the user.
In an alternative embodiment, the first headset may also initiate a master control application, and establish a wireless connection with the headset storage box, so that the master-slave control authority of the headset system is translated and switched, and then the translation process of S206-S208 is completed.
In the embodiment of the invention, only the main earphone can establish wireless connection and wireless transmission with the earphone storage box by distinguishing the main earphone from the auxiliary earphone, so that channel crossing and signal interference can be avoided in the process of sending data between the earphone and the earphone storage box, and the accuracy rate of receiving data is improved; in addition, the main earphone is used for receiving the audio needing to be translated, the efficiency of acquiring the audio needing to be translated is improved, the audio needing to be translated is sent to the storage box to acquire the translation result, and the efficiency of acquiring the translation result is improved.
Referring to fig. 3, fig. 3 is a schematic flow chart of a noise reduction method in a translation process according to an embodiment of the present invention, and as shown in fig. 3, the noise reduction method includes:
s301, picking up the main voice close to the target sound source.
In an alternative embodiment, two microphones are provided for the second earpiece (primary earpiece): the microphone system comprises a main microphone and an auxiliary microphone, wherein the main microphone is used for picking up main voice. The sound picked up by the microphone of the earphone comes from the speaking sound of the user, so the target sound source is the mouth of the user, and the sound close to the target sound source is the mouth close to the user. If the side where the speaker is located is the front side of the earphone, and the side opposite to the speaker is the back side of the earphone, when the user wears the earphone, the front side of the earphone is closer to the mouth of the user, and the back side of the earphone is farther from the mouth of the user, so that the main microphone can be arranged on the front side of the earphone, the auxiliary microphone is arranged on the back side of the earphone, and the sound picked up by the main microphone is the main voice.
S302, whether the noise reduction mode is started or not is detected.
Specifically, the noise reduction mode is turned on, that is, the received voice needs to be subjected to noise reduction processing by default.
In an alternative embodiment, the method for turning on the noise reduction mode of the second headphone includes two methods: the second earphone directly receives noise reduction operation of a user and starts a noise reduction mode according to the noise reduction operation, wherein the noise reduction operation comprises key operation, touch operation or knocking operation and the like; and secondly, the earphone storage box receives the noise reduction operation of the user, then the noise reduction instruction is sent to the second earphone through wireless connection, the second earphone starts the noise reduction mode according to the received noise reduction instruction, and the noise reduction operation of the earphone storage box is the same as that of the second earphone.
And S303, picking up the auxiliary voice far away from the target sound source.
In an alternative embodiment, if the second headphone does not receive the noise reduction instruction, the second headphone only needs to pick up the primary voice, and if the second headphone receives the noise reduction instruction, the second headphone also needs to pick up the secondary voice.
S304, filtering the noise in the main voice according to the auxiliary voice to obtain a first audio.
In an optional embodiment, the content of the main speech includes effective sound and environmental sound emitted by the user, the content of the auxiliary speech also includes effective sound and environmental sound emitted by the user, the main speech and the auxiliary speech are different in that the effective sound in the main speech has a larger volume than the effective sound in the auxiliary speech, the content is more and clearer, the main speech is filtered according to the content of the auxiliary speech, the environmental noise in the main speech can be filtered, and the remaining sound with excellent tone quality is the first audio meeting the requirement.
Optionally, according to the contents of S301 to S304, another feasible solution exists, that is, the primary microphone is disposed on the second earphone, and the secondary microphone is disposed on the earphone storage box, and the subsequent process is not changed, so that the ambient noise in the primary voice can be effectively filtered out, and the first audio is obtained.
In the embodiment of the invention, the main microphone and the auxiliary microphone are arranged on the earphone to pick up the corresponding main voice and the auxiliary voice, and then the noise reduction processing is carried out on the main voice according to the content of the auxiliary voice, so that the environmental noise in the picked-up audio can be effectively filtered, and the audio quality of the audio needing to be translated is improved.
Referring to fig. 4, fig. 4 is a schematic view illustrating a flow chart of a method for improving translation quality according to an embodiment of the present invention, where as shown in the figure, the method for improving translation quality includes:
s401, the earphone containing box receives first audio.
In an alternative embodiment, the earphone storage box receives a first audio sent by a second earphone (a main earphone), wherein the first audio is a target audio needing to be translated.
S402, acquiring a first character corresponding to the first audio and displaying the first character.
In an optional embodiment, the first audio needs to be subjected to speech recognition, and a first text corresponding to the first audio is obtained. In this process, can set up the speech recognition engine at the characters acquisition module of earphone receiver, directly acquire first characters, also can send first audio frequency to the high in the clouds server and carry out speech recognition and obtain first characters.
And S403, searching whether the first audio is stored in the earphone storage box in advance.
In an optional embodiment, the storage module is included in the earphone storage box, and can correspondingly store the received audio needing to be translated and the translation result thereof, so that the stored content can be directly called when the same voice is received in the subsequent process. Optionally, before storing the audio to be translated and the translation result thereof, a storage condition may be further set, for example, when the same audio N (N is an integer greater than 0) is received for more than several times, it is described that the audio to be translated is a common term, and the audio to be translated may be stored. And the audio which is received for less than N times and needs to be translated is not stored, so that the consumption of the storage space of the earphone storage box can be reduced. If the first audio is found to be stored in the earphone storage box in advance, S408 is executed, otherwise S404 is executed.
S404, sending the first audio and the first characters to a cloud server, and obtaining a second audio obtained by translating the first audio.
In an optional embodiment, according to S403, the first audio is not stored in the earphone storage box, so that the first audio and the corresponding first text thereof need to be sent to a cloud server that establishes a wireless connection with the earphone storage box, and the cloud server translates the first audio to obtain a second audio after the first audio is translated. Before sending the first audio to the cloud server, a language type, such as "chinese-english," may also be set, indicating that chinese of the first audio is translated into english of the second audio. After the second audio is obtained, S405 is performed.
S405, obtaining second characters corresponding to the second audio and displaying the second characters.
In an alternative embodiment, the second audio is subjected to speech recognition to obtain the corresponding second text. This identification process can be realized through high in the clouds server, and the earphone receiver receives the second characters that the second audio frequency corresponds, also can realize the discernment to the second audio frequency through the built-in speech recognition engine of earphone receiver characters acquisition module. Simultaneously, the earphone receiver also can show the second characters.
S406, correspondingly storing the first audio and the second audio.
In an optional embodiment, assuming that the first audio already meets the storage condition of the earphone storage box, the earphone storage box correspondingly stores the first audio and the translated second audio, so that when the earphone storage box receives the first audio with the same content next time, a corresponding instruction is executed.
S407, receiving a modification instruction of the first character to obtain the modified first character.
In an optional embodiment, the first audio corresponding to the first text is the user's speaking voice picked up by the second earphone, in the process of identifying the first audio, the identification result may be inaccurate due to problems such as noise, pronunciation or mismatch of corresponding language types, and the user corrects the first text according to the display result on the earphone storage box to obtain the corrected first text. Because the recognition result of the first audio is modified and the translation result is different, S404-S406 need to be repeated, the first audio and the modified first text are sent to the cloud server again for translation, the previous translation result is updated, the second text corresponding to the second audio and the second audio obtained by translating the new first audio is obtained, the first audio and the new second audio are correspondingly stored, and the previously stored related content of the first audio is replaced.
S408, acquiring a second audio which is stored correspondingly to the first audio.
In an optional embodiment, according to S403, it can be known that the first audio is found to be already stored in the earphone storage box, and then the translation content of the first audio can be obtained only by acquiring the second audio stored corresponding to the first audio, so that the translation process is completed.
And S409, acquiring second characters corresponding to a second audio and displaying the second characters.
The process is the same as S405, and is not described in detail here.
In the embodiment of the invention, the earphone storage box receives the pre-translation audio, performs voice recognition on the pre-translation audio to obtain pre-translation characters, and searches whether the earphone storage box stores the pre-translation audio in advance, if so, directly obtains a translation result corresponding to the pre-translation audio from the earphone storage box; and if not, sending the pre-translation audio and the corresponding pre-translation characters to the cloud server together to obtain a translation result, and then obtaining and displaying the characters corresponding to the translation result according to the translation result. And if the correction of the user on the pre-translation characters is received, re-acquiring the translation result from the cloud server according to the corrected pre-translation characters and the corrected pre-translation voice. In the process, the translation efficiency is improved by storing the translation result through the earphone storage box, and the translation accuracy of the earphone translation system is improved by receiving the modification of the characters before translation.
Referring to fig. 5, fig. 5 is a flowchart illustrating a specific earphone translation method according to an embodiment of the present invention, and as shown in fig. 5, the translation method includes:
s501, the first earphone and the second earphone establish wireless connection according to the triggering instruction.
In the embodiment of the invention, when the first earphone and the second earphone are taken out of the earphone containing box, the two earphones are triggered to establish wireless connection.
S502, the first earphone and the earphone storage box are in wireless connection according to the triggering instruction.
In the embodiment of the invention, the first earphone is the default main earphone, and when the first earphone is taken out of the earphone containing box, the first earphone is triggered to establish wireless connection with the earphone containing box.
S503, the first earphone receives the first audio needing to be translated from the terminal.
In the embodiment of the invention, the first earphone establishes wireless connection with the terminal, and acquires the first audio needing to be translated from the terminal.
S504, the first earphone sends the first audio to an earphone storage box for translation.
In the embodiment of the invention, the first earphone sends the first audio to the earphone containing box through wireless transmission, and the earphone containing box translates the first audio.
S505, the earphone storage box obtains the translated second audio of the first audio from the local, and displays the first characters and the second characters corresponding to the first audio and the second audio.
In the embodiment of the invention, the earphone storage box comprises a local translation engine, a corpus and a local voice recognition engine, and can directly translate a first audio to obtain a second audio obtained by translating the first audio, and obtain a first character corresponding to the first audio and a second character corresponding to the second audio according to the local voice recognition engine. The earphone receiver still includes the display screen, can show first characters and second characters. As shown in table 1:
TABLE 1 textual-to-translation Table
A first earphone: chinese character A second earphone: english language
And (delta): do you ask you for you to be a U.S.? Hello！Are you from America？
Where "Δ" represents the audio received by the headphones that needs to be interpreted. The language types corresponding to the first earphone and the second earphone can be changed.
S506, the first earphone acquires second audio from the earphone storage box, plays the second audio, and sends the second audio to the second earphone for playing.
In the embodiment of the invention, the first earphone plays the second audio after obtaining the second audio from the earphone storage box, and simultaneously sends the second audio to the second earphone for playing, so that both sides can hear the translated sentences.
And S507, the second earphone receives the main control instruction and initiates a main control application to the first earphone.
In the embodiment of the present invention, when a user of a second headset wants to initiate a session to a user of a first headset, the second headset needs to obtain a master control permission first, so that the user of the second headset operates a master control key on the second headset, and the second headset receives a master control instruction and initiates a master control application to the first headset.
S508, the first earphone forwards the main control application to the earphone containing box.
In the embodiment of the invention, only the first earphone is in wireless connection with the earphone containing box, so that the main control application of the second earphone needs the first earphone to be forwarded to the earphone containing box.
S509, the earphone containing box is disconnected from the first earphone, and wireless connection with the second earphone is established.
In the embodiment of the invention, the earphone containing box is disconnected from the wireless connection with the first earphone, the wireless connection with the second earphone is established, and the second earphone obtains the master control authority and can be directly communicated with the earphone containing box.
S510, the second earphone picks up audio, and noise reduction processing is carried out on the audio to obtain third audio.
This process has been described in detail in the embodiment corresponding to fig. 3, and is not described herein again.
And S511, the second earphone sends the third audio to the earphone containing box.
And S512, the earphone storage box obtains third characters according to the third audio and displays the third characters.
In the embodiment of the invention, the earphone storage box obtains the third characters corresponding to the third audio through the local character obtaining module, and the display screen of the earphone storage box displays the third characters.
S513, the earphone storage box sends the third audio and the third characters to the cloud server for translation, and obtains a fourth audio obtained by translating the third audio and fourth characters corresponding to the fourth audio. As shown in table 2:
table 2 original text-translation comparison table after switching master earphone and slave earphone
Figure BDA0001583574890000151
And S514, the earphone storage box receives the modification of the third characters, sends the modified third characters and the modified third audio to the cloud server, obtains a new translated fourth audio of the third audio and fourth characters corresponding to the fourth audio, and displays the fourth characters.
In the embodiment of the invention, when performing voice recognition on the received third audio, the earphone storage box has a fault, and the "Australia" is recognized as the "Australia", so that the user corresponding to the second earphone modifies the third text, and sends the modified third text and the third audio to the cloud server, and a new translated fourth audio of the third audio and a fourth text corresponding to the fourth audio are obtained. As shown in table 3:
TABLE 3 modified textual-to-translation look-up tables
Figure BDA0001583574890000152
And S515, correspondingly storing the third audio and the fourth audio by the earphone storage box, and sending the fourth audio to the second earphone.
In the embodiment of the invention, since the user modifies the third text, it is stated that the recognition of the third audio by the text acquisition module needs to be improved, and in order to effectively prevent the situation that the recognition is inaccurate after the third audio is received next time, and needs to be changed and translated again, the earphone storage box correspondingly stores the third audio and the fourth audio, so that when the third audio is received next time, the translated fourth audio can be directly called. Simultaneously, the earphone receiver sends the fourth audio to the second earphone.
And S516, the second earphone plays the fourth audio and sends the fourth audio to the first earphone for playing.
The second earphone plays the fourth audio, so that a user corresponding to the second earphone hears a translation result of the sound made by the user, and language learning is facilitated. The first earphone plays the fourth audio, so that a user corresponding to the first earphone can communicate with people of different language types in real time.
In the embodiment of the invention, the switching process of the master earphone and the slave earphone in the earphone system and the process of receiving the audio to be translated by the master earphone and transmitting the audio to be translated to the earphone storage box for translation are described in detail, so that the problems of signal interference and cross-channel transmission which may occur to the two earphones in the conversation process initiated by a user are avoided. In the process of translating the audio needing to be translated by the earphone containing box, the correction of the words corresponding to the audio needing to be translated by the user is received, the translation result is obtained again according to the corrected words and the audio needing to be translated, and the translation accuracy is improved. And finally, the audio to be translated and the translation result obtained again are correspondingly stored, so that when the same pre-translation audio is received again, the stored result is directly called to obtain the translation result, and the translation efficiency is improved.
Referring to fig. 6, fig. 6 is a block diagram of a headset interpreting system according to an embodiment of the present invention, as shown in fig. 6, the headset interpreting system includes a first headset 61, a second headset 62 and a headset accommodating box 63, the first headset 61 includes a first wireless communication module 610 and a first speaker 611, the first wireless communication module 610 is used for establishing a wireless connection with the second headset 62 and the headset accommodating box 63, and the first speaker 611 is used for playing audio received by the first wireless communication module. The second earphone 62 comprises a second wireless communication module 620, a second control module 623, a second processor 624 and a second voice acquisition module 622, wherein the second wireless communication module 620 is used for establishing wireless connection with the first earphone 61, the second control module 623 is used for receiving a main control instruction, so that the second wireless communication module 620 sends a main control application to the first earphone 61, the first wireless communication module 610 disconnects the wireless connection with the earphone storage box 63, and the second wireless communication module 620 establishes wireless connection with the earphone storage box 62; the second voice acquiring module 622 is configured to acquire a first audio, and the second wireless communication module 620 is further configured to send the first audio to the earphone storage box 63, receive a second audio obtained by translating the first audio, and send the second audio to the first earphone 61 for playing. The earphone storage box 63 comprises a first earphone seat 630, a second earphone seat 631, a box wireless communication module 632 and a translation module 633, the first earphone seat 630 is used for placing a first earphone 61, the second earphone seat 631 is used for placing a second earphone 62, and the box wireless communication module 632 is used for establishing wireless connection with the first earphone 61 or the second earphone 62 and receiving a first audio sent by the second earphone 62; the translation module 633 is configured to obtain a second audio corresponding to the translated first audio; the cartridge wireless communication module 632 is further configured to send the second audio to the second earpiece 62.
Optionally, the second earphone 62 is further configured to establish a wireless connection with the terminal 80 and obtain the first audio from the terminal 80; or:
the second earpiece comprises a primary microphone 6221 and a secondary microphone 6222, wherein:
the primary microphone 6221 is used to pick up a primary voice close to a target sound source;
the auxiliary microphone 6222 is used to pick up auxiliary voice far from a target sound source;
the second processor 624 is configured to filter noise in the main speech according to the auxiliary speech to obtain a first audio. Optionally, the second control module 623 is further configured to receive a noise reduction operation, and the second processor 624 is further configured to generate a noise reduction instruction according to the noise reduction operation; or:
the earphone storage box comprises a box body control module 634 and a processor 639, wherein the box body control module 634 is used for receiving noise reduction operation, and the processor 639 generates a noise reduction instruction according to the noise reduction operation and sends the noise reduction instruction to the second earphone.
Optionally, the headset storage box is connected to the cloud server 70, and receives a second audio obtained by translating the first audio from the cloud server; or:
the translation module 633 comprises a local translation engine 6331 and a corpus 6332, and is configured to translate the first audio to obtain a second audio obtained by translating the first audio.
Optionally, the earphone storage box 63 is configured to obtain first words corresponding to the first audio and second words corresponding to the second audio from the cloud server 70; or
The earphone storage box 63 includes a text acquisition module 635, configured to identify the first audio to obtain first text, and identify the second audio to obtain second text;
earphone receiver 63 includes display screen 636 for right first characters with the second characters are shown.
Optionally, the headset storage box includes a memory 637 and a search module 638, the memory 637 is used for correspondingly storing the first audio and the second audio obtained by translating the first audio;
the searching module 638 is configured to search and obtain the first audio and the corresponding second audio pre-stored in the memory 637 when the first audio is received.
Optionally, the display screen 636 is configured to receive a modification instruction of the first text from a user, to obtain a modified first text, and the translation module 633 is configured to obtain a second audio translated by the first audio according to the modified first text and the first audio.
Optionally, the second earphone 62 is further configured to play the second audio.
In addition, because first earphone and second earphone can all initiate the main control application and obtain the main control authority, so its function sets up the same, only when the connection/disconnection state is different with the earphone receiver, the task of being responsible for is different, so the functional module of first earphone and second earphone is identical.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an earphone translation system according to an embodiment of the present invention, where (a) in fig. 7 is a schematic diagram of a second earphone placed in an earphone storage box, and (B) in fig. 7 is a schematic diagram of a first earphone structure, as shown in the figure, the earphone translation system includes an earphone storage box 900, a first earphone 901, and a second earphone 902, the earphone storage box 900 includes a box of a first storage box portion 905 and a box drawer of a second storage box portion 906, and the drawer box 906 can be placed in a space formed by the box 905 and can also be pulled out. The box drawer 906 further comprises a first earphone seat 903 and a second earphone seat 904, wherein the first earphone seat 903 is used for placing a first earphone 901, the second earphone seat 904 is used for placing a second earphone 902, the second earphone seat comprises a first contact point 911, the second earphone 902 comprises a second contact point 912, when the second earphone is placed on the second earphone seat, the first contact point 911 contacts with the second contact point 912, a battery in the second earphone stops supplying power for each functional module of the first earphone, and the earphone storage box can charge the battery of the second earphone.
In addition, after the second headphone is taken out, the main microphone 910, the sub microphone 909, and the second speaker 913 are included in the second headphone 902, and the display 907 and the function keys 908 are included in the headphone storage case 900. The headset translation system is used for implementing the methods corresponding to fig. 2 to 5, and also includes all the functions described in fig. 6.
The earphone translation system in the embodiment allocates different authorities by setting different connection states for the first earphone and the second earphone, so that occupation or cross-channel transmission in the communication process is prevented, and the communication quality is improved; in addition, the earphone is used for collecting audio, the earphone storage box is used for receiving the audio and obtaining a translation result corresponding to the audio, so that a user can realize real-time conversation and communication of different language types, convenience and rapidness are realized, and the translation efficiency is improved.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.

Claims (9)

1. A headset translation method is applied to a headset system comprising a first headset, a second headset and a headset storage box, and comprises the following steps:
when the first earphone and the second earphone are taken out of the earphone containing box, triggering the first earphone to establish wireless connection with the second earphone, and establishing wireless connection between the first earphone and the earphone containing box;
the second earphone receives a main control instruction and initiates a main control application to the first earphone;
the first earphone receives the main control application and forwards the main control application to the earphone storage box;
the earphone storage box is disconnected from the wireless connection with the first earphone, and the wireless connection with the second earphone is established;
the second earphone acquires a first audio and sends the first audio to the earphone storage box;
the earphone storage box receives the first audio, acquires a second audio obtained by translating the first audio according to the first audio, and sends the second audio to a second earphone;
acquiring first characters corresponding to the first audio and second characters corresponding to the second audio from a cloud server; or acquiring first characters corresponding to the first audio and second characters corresponding to the second audio through a character acquisition module of the earphone storage box;
displaying the first characters and the second characters;
and the second earphone receives the second audio and sends the second audio to the first earphone for playing.
2. The method of claim 1, wherein the second earpiece acquiring first audio comprises:
acquiring a first audio from a terminal which establishes wireless connection with the second earphone; or
Picking up a main voice close to a target sound source;
detecting whether a noise reduction mode is started, if so:
picking up auxiliary voices far away from a target sound source;
and filtering the noise in the main voice according to the auxiliary voice to obtain a first audio.
3. The method of claim 2, wherein detecting whether to turn on a noise reduction mode comprises, prior to:
the second earphone receives the noise reduction operation and starts a noise reduction mode; or:
the earphone storage box receives the noise reduction operation, generates a noise reduction instruction and sends the noise reduction instruction to the second earphone, and the second earphone starts a noise reduction mode.
4. The method of claim 1, wherein the headphone receiver receives the first audio, and wherein obtaining the first audio translated into a second audio comprises:
sending the first audio to a cloud server, and receiving a second audio obtained by translating the first audio from the cloud server; or:
and translating the first audio according to a translation engine and a corpus local to the earphone storage box to obtain a second audio.
5. The method of claim 1, wherein translating the first audio according to a translation engine and corpus local to a headset receiver, and obtaining a second audio further comprises:
when first audio is received, confirming that the earphone storage box stores the first audio in advance;
and acquiring a second audio which is stored corresponding to the first audio.
6. The method of claim 5, wherein searching whether the headphone receiver pre-stores the first audio when the first audio is received comprises:
receiving a modification instruction of the first character, obtaining the modified first character, and obtaining a second audio translated by the first audio according to the modified first character and the first audio;
and correspondingly storing the first audio and the second audio in an earphone storage box.
7. The method of any of claims 1-6, wherein the second earpiece receiving the second audio and sending it to the first earpiece for playback further comprises:
the second earphone plays the second audio.
8. The earphone translation system is characterized by comprising a first earphone, a second earphone and an earphone storage box;
the first earphone comprises a first wireless communication module and a first loudspeaker, the first wireless communication module is used for establishing wireless connection with the second earphone and the earphone storage box, and the first loudspeaker is used for playing audio received by the first wireless communication module;
the second earphone comprises a second wireless communication module, a second control module, a second processor and a second voice acquisition module, the second wireless communication module is used for establishing wireless connection with the first earphone, the second control module is used for receiving master control operation, the second processor generates a master control instruction according to the master control operation and enables the second wireless communication module to send a master control application to the first earphone, the first wireless communication module is disconnected from the wireless connection with the earphone containing box, and the second wireless communication module is established with the earphone containing box in a wireless connection mode; the second voice acquisition module is used for acquiring a first audio, and the second wireless communication module is also used for sending the first audio to the earphone storage box, receiving a second audio obtained by translating the first audio, and sending the second audio to the first earphone for playing;
the earphone containing box comprises a first earphone seat, a second earphone seat, a box body wireless communication module and a translation module, wherein the first earphone seat is used for placing a first earphone, the second earphone seat is used for placing a second earphone, and the box body wireless communication module is used for establishing wireless connection with the first earphone or the second earphone and receiving a first audio frequency sent by the second earphone; the translation module is used for acquiring a second audio corresponding to the translated first audio; the box body wireless communication module is also used for sending the second audio to the second earphone;
the earphone receiver receives the first audio frequency, still includes after obtaining the second audio frequency after the first audio frequency translation:
acquiring first characters corresponding to the first audio and second characters corresponding to the second audio from a cloud server; or acquiring first characters corresponding to the first audio and second characters corresponding to the second audio through a character acquisition module of the earphone storage box;
and displaying the first characters and the second characters.
9. The headset translation system of claim 8 wherein the second headset is configured to establish a wireless connection with the terminal and obtain the first audio from the terminal; or:
the second voice acquisition module comprises a main microphone and an auxiliary microphone, wherein:
the primary microphone is used for picking up primary voice close to a target sound source;
the second processor is used for detecting whether the second earphone is started to be in the noise reduction mode;
the auxiliary microphone is used for picking up auxiliary voice far away from a target sound source under the condition that the second earphone is determined to be in the noise reduction mode;
the second processor is used for filtering noise in the main voice according to the auxiliary voice to obtain a first audio frequency.
CN201810162977.1A 2018-02-26 2018-02-26 Earphone translation method and system Active CN108509428B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810162977.1A CN108509428B (en) 2018-02-26 2018-02-26 Earphone translation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810162977.1A CN108509428B (en) 2018-02-26 2018-02-26 Earphone translation method and system

Publications (2)

Publication Number Publication Date
CN108509428A CN108509428A (en) 2018-09-07
CN108509428B true CN108509428B (en) 2023-04-18

Family

ID=63375756

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810162977.1A Active CN108509428B (en) 2018-02-26 2018-02-26 Earphone translation method and system

Country Status (1)

Country Link
CN (1) CN108509428B (en)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110913503A (en) * 2018-09-17 2020-03-24 泰凌微电子（上海）有限公司 Wireless earphone signal transmission method and wireless earphone
CN112119641B (en) 2018-09-20 2022-04-22 华为技术有限公司 Method and device for realizing automatic translation through multiple TWS (time and frequency) earphones connected in forwarding mode
CN111276135B (en) * 2018-12-03 2023-06-20 华为终端有限公司 Network voice recognition method, network service interaction method and intelligent earphone
CN110232919A (en) * 2019-06-19 2019-09-13 北京智合大方科技有限公司 Real-time voice stream extracts and speech recognition system and method
CN111031439A (en) * 2019-12-27 2020-04-17 深圳春沐源控股有限公司 Earphone box
CN111836149A (en) * 2020-03-20 2020-10-27 东莞讯滔电子有限公司 Wireless earphone device and using method of wireless earphone box
CN111696554B (en) * 2020-06-05 2022-04-26 北京搜狗科技发展有限公司 Translation method and device, earphone and earphone storage device
CN111739538B (en) * 2020-06-05 2022-04-26 北京搜狗科技发展有限公司 Translation method and device, earphone and server
CN111741394A (en) * 2020-06-05 2020-10-02 北京搜狗科技发展有限公司 Data processing method and device and readable medium
CN111696552B (en) * 2020-06-05 2023-09-22 北京搜狗科技发展有限公司 Translation method, translation device and earphone
CN111862940A (en) * 2020-07-15 2020-10-30 百度在线网络技术（北京）有限公司 Earphone-based translation method, device, system, equipment and storage medium
CN112235676B (en) * 2020-09-30 2023-04-14 上海闻泰电子科技有限公司 Audio system with noise reduction function, control method and storage medium
CN112506331A (en) * 2020-12-11 2021-03-16 北京搜狗科技发展有限公司 Data processing method and earphone accommodating device
CN113286218B (en) * 2021-04-23 2022-12-20 北京搜狗智能科技有限公司 Translation method and device and earphone equipment

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105187969A (en) * 2015-09-21 2015-12-23 深圳市冠旭电子有限公司 Earphone used for simultaneous translation
CN205140247U (en) * 2015-11-20 2016-04-06 李晓丽 Multifunctional english teaching plate
RU2016138166A (en) * 2016-09-26 2017-01-10 Владимир Анатольевич Ефремов A method for automatically translating oral speech from one language to another and a device for its implementation
CN206236080U (en) * 2016-12-01 2017-06-09 南京君子游信息技术有限公司 Face-to-face translator
CN106851450A (en) * 2016-12-26 2017-06-13 歌尔科技有限公司 A kind of wireless headset pair and electronic equipment
CN106919562A (en) * 2017-04-28 2017-07-04 深圳市大乘科技股份有限公司 A kind of real-time translation system, method and device
CN107333201A (en) * 2017-07-24 2017-11-07 歌尔科技有限公司 One kind translation earphone storage box, wireless translation earphone and wireless translation system
CN107333200A (en) * 2017-07-24 2017-11-07 歌尔科技有限公司 One kind translation earphone storage box, wireless translation earphone and wireless translation system
CN107506353A (en) * 2017-10-17 2017-12-22 深圳市沃特沃德股份有限公司 Translate box and translation system
CN107708006A (en) * 2017-08-23 2018-02-16 广东思派康电子科技有限公司 Computer-readable recording medium, real-time translation system

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105187969A (en) * 2015-09-21 2015-12-23 深圳市冠旭电子有限公司 Earphone used for simultaneous translation
CN205140247U (en) * 2015-11-20 2016-04-06 李晓丽 Multifunctional english teaching plate
RU2016138166A (en) * 2016-09-26 2017-01-10 Владимир Анатольевич Ефремов A method for automatically translating oral speech from one language to another and a device for its implementation
CN206236080U (en) * 2016-12-01 2017-06-09 南京君子游信息技术有限公司 Face-to-face translator
CN106851450A (en) * 2016-12-26 2017-06-13 歌尔科技有限公司 A kind of wireless headset pair and electronic equipment
CN106919562A (en) * 2017-04-28 2017-07-04 深圳市大乘科技股份有限公司 A kind of real-time translation system, method and device
CN107333201A (en) * 2017-07-24 2017-11-07 歌尔科技有限公司 One kind translation earphone storage box, wireless translation earphone and wireless translation system
CN107333200A (en) * 2017-07-24 2017-11-07 歌尔科技有限公司 One kind translation earphone storage box, wireless translation earphone and wireless translation system
CN107708006A (en) * 2017-08-23 2018-02-16 广东思派康电子科技有限公司 Computer-readable recording medium, real-time translation system
CN107506353A (en) * 2017-10-17 2017-12-22 深圳市沃特沃德股份有限公司 Translate box and translation system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
孔征 .新闻直播演播室音频系统的特点.《 现代电视技术》.2005,44-46. *

Also Published As

Publication number Publication date
CN108509428A (en) 2018-09-07

Similar Documents

Publication Publication Date Title
CN108509428B (en) Earphone translation method and system
CN108280067B (en) Earphone translation method and system
CN108564949B (en) Wrist strap type AI voice interaction device and system
US20180324296A1 (en) Transcription of communications through a device
CN112770214B (en) Earphone control method and device and earphone
CN106210365B (en) Videoconference method for regulation of sound volume and system
CN109379490B (en) Audio playing method and device, electronic equipment and computer readable medium
US11489351B2 (en) Wireless earphone device and method for using the same
CN102340730A (en) Method for playing multi-channel stereo by matching multiple mobile phones
CN110708615A (en) Intercommunication system and intercommunication method realized based on TWS earphone
CN106445453A (en) Method and device for switching audio output paths
WO2021244159A1 (en) Translation method and apparatus, earphone, and earphone storage apparatus
CN103324459A (en) Method and system for implementing USB (universal serial bus) headset devices
CN111556439A (en) Terminal connection control method, terminal and computer storage medium
CN105281811A (en) Voice data transmission processing method and terminal
US20060044120A1 (en) Car audio system and method combining with MP3 player
US20190132895A1 (en) Multi-connection device and multi-connection method
US20240147128A1 (en) Mode control method, device for bluetooth headset, and computer readable storage medium
WO2021244135A1 (en) Translation method and apparatus, and headset
CN112866855A (en) Hearing aid method and system, earphone charging box and storage medium
CN111739538B (en) Translation method and device, earphone and server
CN100559805C (en) Mobile terminals and the message output method that is used for this terminal
CN113905128B (en) Call reminding method and terminal
CN111694539B (en) Method, device and medium for switching between earphone and loudspeaker
CN112380880A (en) Translation method and translation 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