WO2019090532A1 - 语音翻译方法、系统、装置和翻译设备 - Google Patents

语音翻译方法、系统、装置和翻译设备 Download PDF

Info

Publication number
WO2019090532A1
WO2019090532A1 PCT/CN2017/110004 CN2017110004W WO2019090532A1 WO 2019090532 A1 WO2019090532 A1 WO 2019090532A1 CN 2017110004 W CN2017110004 W CN 2017110004W WO 2019090532 A1 WO2019090532 A1 WO 2019090532A1
Authority
WO
WIPO (PCT)
Prior art keywords
bluetooth
bluetooth headset
translation
voice information
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.)
Ceased
Application number
PCT/CN2017/110004
Other languages
English (en)
French (fr)
Inventor
张立新
郑勇
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 Water World Co Ltd
Original Assignee
Shenzhen Water World 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 Water World Co Ltd filed Critical Shenzhen Water World Co Ltd
Priority to PCT/CN2017/110004 priority Critical patent/WO2019090532A1/zh
Publication of WO2019090532A1 publication Critical patent/WO2019090532A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/40Processing or translation of natural language

Definitions

  • the present invention relates to the field of electronic technologies, and in particular, to a speech translation method, system, device, and translation device.
  • Two users who speak different languages can communicate with each other through translation equipment to achieve barrier-free communication.
  • the translation device alternately establishes a Bluetooth connection with two Bluetooth headsets, receives the original voice information through the Bluetooth connection and sends the translated voice information, thereby achieving a private conversation between the two users.
  • a primary object of the present invention is to provide a speech translation method, system, apparatus, and translation apparatus, which are intended to implement a multi-party conversational speech translation and extend the scope of application.
  • an embodiment of the present invention provides a voice translation method, where the method includes the following steps.
  • the first Bluetooth headset establishes a Bluetooth connection with the translation device, and sends the original voice information to the translation device
  • the translation device receives the original voice information, and performs translation processing on the original voice information
  • the translation device sends the translated voice information to the at least two second Bluetooth headsets through the FM transceiver
  • the second Bluetooth headset receives the translated voice information through an FM receiver and outputs the voice information.
  • the method further includes:
  • the translation device transmits the original phrase to the at least two second Bluetooth headsets through the FM transceiver;
  • the second Bluetooth headset receives the original voice information through the FM receiver.
  • An embodiment of the present invention further provides a voice translation method, where the method includes the following steps:
  • the method further includes: sending, by the FM transceiver, the original voice information to the at least two second Bluetooth headsets.
  • the method before the step of establishing a Bluetooth connection with the first Bluetooth headset, the method further includes:
  • the step of establishing a Bluetooth connection with the first Bluetooth headset includes:
  • the step of disconnecting the Bluetooth connection with the first Bluetooth headset comprises:
  • Embodiments of the present invention also provide a voice translation system, the system including a first Bluetooth headset, at least two second Bluetooth headsets, and a translation device, where:
  • the first Bluetooth headset is configured to establish a Bluetooth connection with the translation device, and send original voice information to the translation device;
  • the translation device is configured to receive the original voice information, and perform translation processing on the original voice information; when the Bluetooth connection is disconnected from the first Bluetooth headset, to the at least through the FM transceiver Two a second Bluetooth headset sends the translated voice information;
  • the second Bluetooth headset is configured to receive the translated voice information through an FM receiver and output the same.
  • the translation device is further configured to: after receiving the original voice information, send the original voice information to the at least two second Bluetooth headsets by using the FM transceiver;
  • the second Bluetooth headset is further configured to: receive the original voice information by using the FM receiver.
  • the translation device is further configured to:
  • Embodiments of the present invention also provide a voice translation apparatus, where the apparatus includes:
  • connection establishing module configured to establish a Bluetooth connection with the first Bluetooth headset
  • an information receiving module configured to receive original voice information sent by the first Bluetooth headset
  • a translation processing module configured to perform translation processing on the original voice information
  • the first sending module is configured to send the translated language first message to the at least two second Bluetooth headsets through the FM transceiver.
  • the device further includes a second sending module, where the second sending module is configured to:
  • the FM transceiver transmits the original voice information to the at least two second Bluetooth headsets.
  • the device further includes:
  • an FM transmission setup module configured to scan an idle channel through the FM transceiver and establish an FM transmission on the idle channel
  • the channel information transmission module is configured to establish a Bluetooth connection with the first Bluetooth headset and the at least two second Bluetooth headsets one by one, and send channel information of the FM transmission.
  • connection establishing module includes:
  • connection request receiving unit configured to receive a connection request of the first Bluetooth headset
  • connecting unit configured to establish a Bluetooth connection with the first Bluetooth headset according to the connection request.
  • connection breaker module includes:
  • a disconnect request receiving unit configured to receive a disconnect request of the first Bluetooth headset
  • the disconnect unit is configured to disconnect the Bluetooth connection with the first Bluetooth headset according to the disconnect request.
  • Embodiments of the present invention also provide a translation apparatus including a memory, a processor, and at least one application stored in the memory and configured to be executed by the processor, the application being configured It is used to perform the aforementioned speech translation method.
  • a voice translation method provided by an embodiment of the present invention adds an FM transceiver and an FM receiver to a translation device and a Bluetooth headset, so that the translation device can receive the original voice information through the Bluetooth connection, and The translated voice message is sent outside, and the Bluetooth headset can receive the translated voice information through the FM receiver. Since the translation device receives and transmits information using Bluetooth and FM respectively, and the FM transceiver can send information to multiple Bluetooth headsets simultaneously, multiple users can take turns to speak and translate the voice information of the speech to the group. Other users have realized the voice translation of multi-party conversations, which has expanded the application range of translation equipment and greatly improved the user experience.
  • FIG. 1 is a flow chart of a first embodiment of a speech translation method of the present invention
  • FIG. 2 is a block diagram showing an example of a translation apparatus for implementing a speech translation method according to an embodiment of the present invention
  • FIG. 3 is a block diagram showing an example of a Bluetooth headset that implements a voice translation method according to an embodiment of the present invention
  • FIG. 4 is a flow chart of a second embodiment of a speech translation method of the present invention.
  • FIG. 5 is a block diagram showing an embodiment of a speech translation system of the present invention.
  • FIG. 6 is a block diagram showing a first embodiment of a speech translation apparatus of the present invention.
  • connection establishment module of FIG. 6 is a schematic block diagram of the connection establishment module of FIG. 6;
  • connection breaker module of FIG. 6 is a schematic block diagram of the connection breaker module of FIG. 6;
  • FIG. 9 is a block diagram showing a second embodiment of a speech translation apparatus of the present invention.
  • FIG. 10 is a block diagram showing a third embodiment of a speech translation apparatus of the present invention.
  • the implementation, functional features, and advantages of the present invention will be further described with reference to the accompanying drawings.
  • a first embodiment of a speech translation method of the present invention includes the following steps: [0069] Sl1, a first Bluetooth headset establishes a Bluetooth connection with a translation device, and sends the original voice to the translation device. information.
  • the translation device receives the original voice information, and performs translation processing on the original voice information.
  • the translation device sends the translated voice information to the at least two second Bluetooth headsets through the FM transceiver.
  • the second Bluetooth headset receives the translated voice information through the FM receiver and outputs the voice information.
  • the first Bluetooth headset is a Bluetooth headset worn by a user who speaks, and the voice information of the user is collected and sent to the translation device;
  • the second Bluetooth headset is a Bluetooth headset worn by the user who listens, and the translation is received by the user.
  • the voice message sent by the device is output.
  • the Bluetooth headset worn by the user turns into the second Bluetooth headset; when the listening user starts to speak, the Bluetooth headset worn by the user changes to the first Bluetooth headset.
  • an FM (Fr e q uenC y Modulation) transceiver is added to the translation device, and an FM receiver is added to the first Bluetooth headset and the second Bluetooth headset.
  • the translation device can be a specialized translation machine, or it can be a terminal device such as a mobile phone, a tablet, or a personal computer.
  • an example of a translation device for implementing a speech translation method includes a processor and a Bluetooth unit, and an added FM transceiver, and the processor is respectively connected to the Bluetooth unit and the FM transceiver.
  • the Bluetooth unit and FM transceiver are controlled by the processor.
  • the Bluetooth unit communicates and communicates with the outside through a Bluetooth antenna, and the FM transceiver communicates with the outside through the FM antenna unit.
  • a Bluetooth headset (first Bluetooth headset) for implementing the voice translation method of the embodiment of the present invention
  • a second Bluetooth headset which includes a processing unit, and an FM receiver and a connect/disconnect button are added.
  • the processing unit is respectively connected to the FM receiver and the connection/break button, and the FM receiver communicates with the outside through the FM antenna.
  • the FM receiver is controlled by the processing unit to receive the demodulated audio signal and transmit it to the amplifier circuit of the earphone receiver.
  • the Connect/Shutdown button provides quick control of the Bluetooth connection's on and off, which is equivalent to the start and end of the talk.
  • the translation device performs channel synchronization with each Bluetooth headset. Specifically, the translation device automatically enters the receiving mode to scan the idle channel (or frequency) through the FM transceiver, and after scanning to the idle channel, enters the transmitting mode, establishes an FM transmission on the idle channel, and activates the FM transmitting function; Pairing with each user's Bluetooth headset (including the first Bluetooth headset and each second Bluetooth headset), establishing a Bluetooth connection, and transmitting FM channel information to each Bluetooth headset via a Bluetooth connection; each Bluetooth headset receives an FM transmission After the channel information, FM reception is established on the same channel as the FM transmission by the FM receiver, and the FM receiving function is activated. After the translation device completes the channel synchronization, it disconnects the Bluetooth connection with the last connected Bluetooth headset.
  • the FM transceiver and the FM receiver can adopt the commonly used frequency band of 65 ⁇ 115MHZ, and the advantages are that the chip is mature, easy to purchase, low in cost, and can take into consideration FM radio.
  • other FM receiving and transmitting chips of the VHF and UHF bands may also be used, which are not limited in the present invention.
  • the FM transceiver and the FM receiver can adopt the subsonic squelch technology, that is, the CT CSS (Continuous Tone Controlled Squelch System) to modulate the speech signal first. And demodulation, transmission and reception are set at the same subsonic squelch frequency.
  • CT CSS Continuous Tone Controlled Squelch System
  • step S11 when the speaker triggers the connection/break button of the Bluetooth headset that he is wearing, the Bluetooth headset transmits the connection request to the translation device as the first Bluetooth headset; the translation device according to the connection request The first Bluetooth headset establishes a Bluetooth connection; the first Bluetooth headset collects the user's voice information, and the collected original voice information is sent to the translation device through the Bluetooth connection.
  • connection between the translation device and the first Bluetooth headset may be other than the manner of the connection request, and other methods in the prior art may be used.
  • the translation device can first establish a paired Bluetooth headset as the first Bluetooth headset, first establishing a connection with it.
  • step S12 the translation device receives the original voice information sent by the first Bluetooth headset and performs recording, and performs translation processing on the original voice information.
  • the translation device can translate the original voice information locally , the original voice information can also be sent to the server for translation processing.
  • the translation process is an ongoing process in which the translation device receives the original voice message while translating it.
  • the translation device first transmits the original voice information to the voice recognition server, and the voice recognition server recognizes the original voice information as a character string of the first language and returns it to the translation device; the translation device receives the character string of the first language and transmits To the translation server, the translation server translates the string of the first language into a string of the second language and returns it to the translation device; the translation device receives the string of the second language and sends it to the composition server, which synthesizes the character of the second language The string speech is synthesized into a speech stream of the second language and returned to the translation device.
  • the translation device receives the voice code stream in the second language, and the voice code stream is the voice information after the translation process.
  • step S13 when the speaker finishes speaking, the connection/break button is triggered again to close the Bluetooth connection, the first Bluetooth headset sends a disconnect request to the translation device, and the translation device responds to the first Bluetooth according to the disconnect request. The headset is disconnected from the Bluetooth connection.
  • the user can also control the disconnection of the Bluetooth connection through a voice command, and the translation device receives the voice command and disconnects the Bluetooth connection with the first Bluetooth headset.
  • the voice command such as "Complete", "End” and other keywords, the speaker can say the aforementioned keyword at the end after the speech is completed.
  • the translation device determines that the above keyword is determined as a voice command at the end of the sentence, for example, if the voice message is not continuously received after the preset keyword is detected (eg, 2-5 seconds), then The decision receives the second instruction.
  • the translation device detects whether the first Bluetooth headset has stopped transmitting voice information, and when it detects that the first Bluetooth headset stops transmitting voice information, connects to the Bluetooth headset of the first Bluetooth headset. Specifically, the translation device determines whether the voice information sent by the first Bluetooth headset is not received after the preset time interval, and when the voice information sent by the first Bluetooth headset is not received within the preset time, the first Bluetooth headset is determined. The voice message has been stopped.
  • the preset time can be set to 2-5 seconds, of course. It can be adjusted according to actual needs.
  • step S14 after the first Bluetooth headset and the translation device are disconnected from the Bluetooth connection, the translation device completes the translation processing of the last part of the original voice information, and optionally, the entire voice can be combined with the translated language.
  • the audio information is checked and modified.
  • the translation device sends the translated voice information to all of the second Bluetooth headsets through the FM transceiver.
  • each second Bluetooth headset receives the translated voice information sent by the translation device through the FM receiver and outputs the voice translation of the user's speech.
  • the connection/break button of the Bluetooth headset worn by the user is triggered to make the Bluetooth headset establish a Bluetooth connection with the translation device as the first Bluetooth headset, and the above steps Sl l-S14 are repeated.
  • the translation device may translate the original voice information into one language or at least two languages according to actual conditions, and when translated into at least two languages, send the various languages sequentially through the FM transceiver. Voice messages, users who use different languages can hear their own language.
  • the translation device after receiving the original voice information sent by the first Bluetooth headset, the translation device sends the original voice information to each second Bluetooth headset through the FM transceiver, while the translation processing of the original voice information is performed. This allows the speaker to speak, other users can still hear the speaker's original sound, enhance the authenticity of the dialogue.
  • the voice translation method of the embodiment of the present invention adds an FM transceiver and an FM receiver to the translation device and the Bluetooth headset, so that the translation device can receive the original voice information through the Bluetooth connection, and send the translated voice through the FM transceiver.
  • the voice message, Bluetooth headset can receive the translated voice information through the FM receiver. Since the translation device receives and transmits information using Bluetooth and FM respectively, and the FM transceiver can send information to multiple Bluetooth headsets simultaneously, multiple users can take turns to speak and translate the voice information of the speech to the group. Other users have realized the voice translation of multi-party conversations, which has expanded the application range of translation equipment and greatly improved the user experience.
  • a second embodiment of a speech translation method of the present invention is proposed.
  • the method is applied to the foregoing translation apparatus, and includes the following steps:
  • the translation device receives the connection request sent by the first Bluetooth headset, and establishes a Bluetooth connection with the first Bluetooth headset according to the connection request.
  • connection between the translation device and the first Bluetooth headset may be other than the manner of the connection request, and other methods in the prior art may be used.
  • a translation device can be the first Establish a paired Bluetooth headset as the first Bluetooth headset to automatically establish a connection with it.
  • the translation device performs channel synchronization with each Bluetooth headset. Specifically, the translation device automatically enters the receiving mode to scan the idle channel (or frequency) through the FM transceiver, and after scanning to the idle channel, enters the transmitting mode, establishes an FM transmission on the idle channel, and activates the FM transmitting function; Pairing with each user's Bluetooth headset (including the first Bluetooth headset and each second Bluetooth headset), establishing a Bluetooth connection, and transmitting FM channel information to each Bluetooth headset through a Bluetooth connection, controlling each Bluetooth headset to receive via FM The FM reception is established on the same channel as the FM transmission, and the FM reception function is activated. After the translation device completes the channel synchronization, it disconnects the Bluetooth connection from the last connected Bluetooth headset.
  • the FM transceiver and the FM receiver can adopt the commonly used frequency band of 65 ⁇ 115MHZ, and the advantages are that the chip is mature, easy to purchase, low in cost, and can take into consideration FM radio.
  • other FM receiving and transmitting chips of the VHF and UHF bands may also be used, which are not limited in the present invention.
  • the FM transceiver and the FM receiver can adopt the subsonic squelch technology, that is, the CT CSS (Continuous Tone Controlled Squelch System) to modulate the speech signal first. And demodulation, transmission and reception are set at the same subsonic squelch frequency.
  • CT CSS Continuous Tone Controlled Squelch System
  • the translation device may process the original voice information locally, or may send the original voice information to a server for translation processing.
  • the translation process is an ongoing process in which the translation device receives the original speech information while translating it.
  • the translation device first transmits the original voice information to the voice recognition server, and the voice recognition server recognizes the original voice information as a character string of the first language and returns it to the translation device; the translation device receives the character string of the first language and transmits To the translation server, the translation server translates the string of the first language into a string of the second language and returns it to the translation device; the translation device receives the string of the second language and sends it to the composition server, which synthesizes the character of the second language The string speech is synthesized into a speech stream of the second language and returned to the translation device.
  • the translation device receives the voice code stream in the second language, and the voice code stream is the voice information after the translation process.
  • the translation device receives the disconnection request sent by the first Bluetooth headset, and disconnects the Bluetooth connection with the first Bluetooth headset according to the disconnection request.
  • the user can also control the disconnection of the Bluetooth connection through a voice command, and the translation device receives the voice command and disconnects the Bluetooth connection with the first Bluetooth headset.
  • the voice command such as "Complete", "End” and other keywords, the speaker can say the aforementioned keyword at the end after the speech is completed.
  • the translation device determines that the above keyword is determined as a voice command at the end of the sentence, for example, if the voice message is not continuously received after the preset keyword is detected (eg, 2-5 seconds), then The decision receives the second instruction.
  • the translation device detects whether the first Bluetooth headset has stopped transmitting voice information, and when it detects that the first Bluetooth headset stops transmitting voice information, connects to the Bluetooth headset of the first Bluetooth headset. Specifically, the translation device determines whether the voice information sent by the first Bluetooth headset is not received after the preset time interval, and when the voice information sent by the first Bluetooth headset is not received within the preset time, the first Bluetooth headset is determined. The voice message has been stopped.
  • the preset time can be set to 2-5 seconds, of course. It can be adjusted according to actual needs.
  • S25 Send the translated voice information to the at least two second Bluetooth headsets through the FM transceiver.
  • the translation device completes the translation processing of the last part of the original voice information, and optionally, the entire voice segment can be combined to correct the translated voice information.
  • the translation device sends the translated voice information to all of the second Bluetooth headsets via the FM transceiver.
  • the translation device may translate the original voice information into one language or at least two languages according to actual conditions, and when translated into at least two languages, send the various languages sequentially through the FM transceiver.
  • the voice information users who use different languages can hear their own language, and realize multi-party conversations of multi-language users.
  • the translation device After receiving the original voice information sent by the first Bluetooth headset, the translation device sends the original voice information to each second Bluetooth headset through the FM transceiver, while the translation processing of the original voice information is performed. Enable the speaker to speak, other users can still hear the speaker's original sound, enhance the dialogue Authenticity.
  • the voice translation method of the embodiment of the present invention by adding an FM transceiver to the translation device, so that the translation device can receive the original voice information sent by the Bluetooth headset through the Bluetooth connection, and send the translated voice information to the Bluetooth headset through the FM transceiver. receive. Since the translation device receives and transmits information using Bluetooth and FM respectively, and the FM transceiver can send information to multiple Bluetooth headsets simultaneously, multiple users can take turns to speak and translate the voice information of the speech to the group. Other users, thus realizing the voice translation of multi-party conversations, expanding the application range of translation equipment, greatly improving the user experience
  • a speech translation system of the present invention includes a first Bluetooth headset 200, at least two second Bluetooth headsets 300, and a translation device 100, wherein: the first Bluetooth headset 200 is set to Establishing a Bluetooth connection with the translation device 100 and transmitting the original voice information to the translation device 100; the translation device 100 is configured to receive the original voice information and perform translation processing on the original voice information; when the Bluetooth connection is disconnected from the first Bluetooth headset 200 Transmitting the translated voice information to the at least two second Bluetooth headsets 300 through the FM transceiver; the second Bluetooth headset 300 is configured to receive the translated voice information through the FM receiver
  • an FM transceiver is added to the translation device 100, and an FM receiver is added to the first Bluetooth headset 200 and the second Bluetooth headset 300.
  • the translation device 100 can be a dedicated translation machine or a terminal device such as a mobile phone, a tablet, or a personal computer.
  • the translation device 100 performs channel synchronization with each Bluetooth headset. Specifically, the translation device 100 automatically enters the receiving mode to scan the idle channel (or frequency) through the FM transceiver, enters the transmitting mode after scanning the idle channel, establishes the FM transmission on the idle channel, and activates the FM transmitting function; 100 pairs with each user's Bluetooth headset (including the first Bluetooth headset 200 and each of the second Bluetooth headsets 300), establish a Bluetooth connection, and transmit FM channel information to each Bluetooth headset through a Bluetooth connection; each Bluetooth headset After receiving the channel information of the FM transmission, the FM receiver establishes FM reception on the same channel as the FM transmission, and activates the FM receiving function. After the translation device 100 completes the channel synchronization, the Bluetooth headset is disconnected from the last connected Bluetooth headset.
  • the FM transceiver and the FM receiver can adopt the commonly used frequency band of 65 to 115 MHz, and the advantage is that the chip matures. , easy to purchase, low cost, can take into account FM radio.
  • the FM receiving and transmitting chips of other VHF and UHF bands can also be used, which is not limited by the present invention.
  • the FM transceiver and the FM receiver can adopt the subsonic squelch technology, that is, the CT CSS (Continuous Tone Controlled Squelch System) to modulate the speech signal first. And demodulation, transmission and reception are set at the same subsonic squelch point.
  • the CT CSS Continuous Tone Controlled Squelch System
  • the Bluetooth headset when the speaker triggers the connection/break button of the Bluetooth headset that is worn by the speaker, the Bluetooth headset transmits the connection request to the translation device 100 as the first Bluetooth headset 200; 100 establishes a Bluetooth connection with the first Bluetooth headset 200 according to the connection request; the first Bluetooth headset 200 collects the voice information of the user, and sends the collected original voice information to the translation device 100 through the Bluetooth connection.
  • the connection between the translation device 100 and the first Bluetooth headset 200 may be other than the manner in which the connection request is made, and other methods in the prior art may be used.
  • the translation device 100 can first establish a paired Bluetooth headset as the first Bluetooth headset 200, first establishing a connection with it.
  • the translation device 100 receives the original voice information transmitted by the first Bluetooth headset 200 and performs recording, and performs translation processing on the original voice information.
  • the translation device 100 can process the original voice information locally, or send the original voice information to the server for translation processing.
  • the translation process is an ongoing process in which the translation device 100 receives the original speech information while translating it.
  • connection/break button is triggered again to close the Bluetooth connection, the first Bluetooth headset 200 sends a disconnect request to the translation device 100, and the translation device 100 responds to the first Bluetooth headset according to the disconnect request. 200 broken Bluetooth connection.
  • the user may also control the disconnection of the Bluetooth connection through a voice command, and the translation device 10 receives the voice command and disconnects the Bluetooth connection with the first Bluetooth headset 200.
  • the voice command such as "finish", "end” and other keywords, the speaker can speak the above keywords at the end of the speech.
  • the translation device 100 determines that the above-mentioned keyword is determined to be a voice command at the end of the sentence, for example, if the voice message is not continuously received after the predetermined keyword is detected (eg, 2-5 seconds), Then the decision receives the second instruction.
  • the translation device 100 detects whether the first Bluetooth headset 200 has stopped transmitting voice information, and when it detects that the first Bluetooth headset 200 stops transmitting voice information, the first Bluetooth headset 200 Broken Bluetooth connection. Specifically, the translation device 100 determines whether the voice information sent by the first Bluetooth headset 200 is not received after the preset time interval is exceeded. If the voice information sent by the first Bluetooth headset 200 is not received after the preset time interval is exceeded, the judgment is performed. A Bluetooth headset 200 has stopped sending voice messages.
  • the preset time can be set to 2-5 seconds, of course. It can be adjusted according to actual needs.
  • the translation device 100 completes the translation processing of the last part of the original voice information, and optionally, the entire voice segment can be used to check the translated voice information. modify.
  • the translation device 100 transmits the translated voice information to all of the second Bluetooth headsets 300 through the FM transceiver.
  • Each of the second Bluetooth headsets 300 receives the translated voice information sent by the translation device 100 through the FM receiver and outputs the voice translation of the user's speech.
  • the connection/break button of the Bluetooth headset that he or she wears is triggered, so that the Bluetooth headset establishes a Bluetooth connection with the translation device 100 as the first Bluetooth headset 200, and so on. Thereby realizing the voice translation of multi-person conversations.
  • the translation device 100 may translate the original voice information into one language or at least two languages according to actual conditions. When translated into at least two languages, the translation device sequentially transmits various types through the FM transceiver. The voice information of the language, users who use different languages can hear their own language.
  • the translation device 100 transmits the original voice information to each second Bluetooth through the FM transceiver after the translation processing of the original voice information.
  • the earphone 300 enables the speaker to speak, and other users can still hear the original sound of the speaker, enhancing the authenticity of the dialogue.
  • the voice translation system of the embodiment of the present invention adds an FM transceiver and an FM receiver to the translation device and the Bluetooth headset, so that the translation device can receive the original voice information through the Bluetooth connection, and send the translated voice through the FM transceiver.
  • the voice message, Bluetooth headset can receive the translated voice information through the FM receiver. Since the translation device receives and transmits information using Bluetooth and FM respectively, and the FM transceiver can send information to multiple Bluetooth headsets simultaneously, multiple users can take turns to speak and translate the voice information of the speech to the group. Other users have realized the voice translation of multi-party conversations, which has expanded the application range of translation equipment and greatly improved the user experience.
  • FIG. 6 a first embodiment of a speech translation apparatus of the present invention is proposed.
  • the apparatus is applied to the foregoing translation apparatus, which includes a connection establishment module 10, an information receiving module 20, a translation processing module 30, and a connection breaking module 40.
  • the first sending module 50 wherein: the connection establishing module 10 is configured to establish a Bluetooth connection with the first Bluetooth headset; the information receiving module 20 is configured to receive the original voice information sent by the first Bluetooth headset; and the translation processing module 30 is configured to Performing translation processing on the original voice information; connecting the disconnection module 40, configured to be connected to the Bluetooth connection of the first Bluetooth headset; the first sending module 50, configured to send the translated to the at least two second Bluetooth headsets through the FM transceiver Voice message.
  • the connection establishing module 10 includes a connection request receiving unit 11 and a connection unit 12, as shown in FIG. 7, wherein: the connection request receiving unit 11 is configured to receive a connection request of the first Bluetooth headset; The unit 12 is configured to establish a Bluetooth connection with the first Bluetooth headset according to the connection request.
  • connection between the translation device and the first Bluetooth headset may be other than the manner in which the connection request is made, and other methods in the prior art may be used.
  • the connection establishing module 10 can automatically establish a connection with the first paired Bluetooth headset as the first Bluetooth headset.
  • connection establishing module 10 establishes a Bluetooth connection with the first Bluetooth headset
  • the information receiving module 20 receives the original voice information sent by the first Bluetooth headset through the Bluetooth connection
  • the translation processing module 30 performs translation processing on the original voice information.
  • the translation processing module 30 may process the original voice information locally, or may send the original voice information to a server for translation processing.
  • the translation process is an ongoing process, and the translation device receives the original voice information through the message receiving module 20 while translating it through the translation processing module 30.
  • the translation processing module 30 first transmits the original voice information to the voice recognition server, and the voice recognition server recognizes the original voice information as a character string of the first language and returns it to the translation device; the translation processing module 30 receives the first language.
  • the string is sent to the translation server, the translation server translates the string of the first language into a string of the second language and returns it to the translation device; the translation processing module 30 receives the string of the second language and sends it to the composition server, the composition server
  • the string speech of the second language is synthesized into a speech stream of the second language and returned to the translation device.
  • the translation processing module 30 receives the speech code stream of the second language, and the speech code stream is the speech information after the translation processing.
  • the connection breaker module 40 is as shown in FIG. 8, and includes a disconnection request receiving unit 41 and a disconnection.
  • the unit 42 wherein: the disconnect request receiving unit 41 is configured to receive a disconnect request of the first Bluetooth headset; and the disconnect unit 42 is configured to disconnect the Bluetooth connection with the first Bluetooth headset according to the disconnect request.
  • the user can also control the disconnection of the Bluetooth connection through a voice command, and the connection disconnect module 40 receives the voice command and then disconnects the Bluetooth connection with the first Bluetooth headset.
  • the voice command such as "finish", "end” and other keywords, the speaker can speak the above keywords at the end of the speech.
  • the connection breaker module 40 determines that the above keyword is determined to be a voice command at the end of the sentence, such as not receiving the voice information after the preset keyword is exceeded (eg, 2-5 seconds). Oh, the decision is received by the second instruction.
  • the connection breaker module 40 detects whether the first Bluetooth headset has stopped transmitting voice information, and when it detects that the first Bluetooth headset stops transmitting voice information, the Bluetooth headset is disconnected from the first Bluetooth headset. Connection. Specifically, the connection breaking module 40 determines whether the voice information sent by the first Bluetooth headset is not received after the preset time interval, and when the voice information sent by the first Bluetooth headset is not received within the preset time, the judgment is A Bluetooth headset has stopped sending voice messages.
  • the preset time can be set to 2-5 seconds, of course. It can be adjusted according to actual needs.
  • the first sending module 50 sends the translated voice information to all the second Bluetooth headsets through the FM transceiver.
  • the translation processing module 30 may translate the original voice information into one language or at least two languages according to actual conditions.
  • the first sending module 50 passes the FM.
  • the transceiver sequentially sends voice information in various languages, so users who use different languages can hear their own language and realize multi-party conversations of multiple language users.
  • the apparatus further includes a second sending module 60 configured to: after the information receiving module 20 receives the original voice information, Transmitting the original voice information to the at least two second Bluetooth headsets through the FM transceiver.
  • a second sending module 60 configured to: after the information receiving module 20 receives the original voice information, Transmitting the original voice information to the at least two second Bluetooth headsets through the FM transceiver.
  • the apparatus further includes an FM transmission establishing module 70 and a channel information transmission module 80, wherein: the FM transmission establishing module 70, To scan the idle channel through the FM transceiver, and establish FM transmission on the idle channel; the channel information transmission module 80 is configured to establish a Bluetooth connection with the first Bluetooth headset and the at least two second Bluetooth headsets one by one, and send the FM transmitted channel information.
  • the FM transmission establishing module 70 automatically enters the receiving mode to scan the idle channel (or frequency) through the FM transceiver, and after scanning to the idle channel, enters the transmitting mode, and establishes an FM transmission on the idle channel, and activates the FM. Transmitting function; the channel information transmission module 80 pairs with each user's Bluetooth earphone (including the first Bluetooth earphone and each second Bluetooth earphone) one by one, establishes a Bluetooth connection, and transmits the channel information of the FM transmission to each Bluetooth earphone through the Bluetooth connection. Control each Bluetooth headset to establish FM reception on the same channel as the FM transmission through the FM receiver, and activate the FM receiving function. When the channel synchronization is completed, the Bluetooth connection is disconnected from the last connected Bluetooth headset.
  • the FM transceiver and the FM receiver can adopt the commonly used frequency band of 65 ⁇ 115MHZ, and the advantages are that the chip is mature, easy to purchase, low in cost, and can take into consideration FM radio.
  • other FM receiving and transmitting chips of the VHF and UHF bands may also be used, which are not limited in the present invention.
  • the FM transceiver and the FM receiver can adopt the subsonic squelch technology, that is, the CT CSS (Continuous Tone Controlled Squelch System) to modulate the speech signal first. And demodulation, transmission and reception are set at the same subsonic squelch frequency.
  • CT CSS Continuous Tone Controlled Squelch System
  • the voice translation method of the embodiment of the present invention by adding an FM transceiver to the translation device, so that the translation device can receive the original voice information sent by the Bluetooth headset through the Bluetooth connection, and send the translated voice information to the Bluetooth headset through the FM transceiver. receive. Since the translation device receives and transmits information using Bluetooth and FM respectively, and the FM transceiver can send information to multiple Bluetooth headsets simultaneously, multiple users can take turns to speak and translate the voice information of the speech to the group. Other users, thus realizing the voice translation of multi-party conversations, expanding the application range of translation equipment, greatly improving the user experience
  • the present invention also provides a translation apparatus including a memory, a processor, and at least one application stored in the memory and configured to be executed by the processor, the application being configured to execute a voice translation method.
  • the voice translation method includes the following steps: establishing a Bluetooth connection with the first Bluetooth headset; receiving original voice information sent by the first Bluetooth headset; performing translation processing on the original voice information; disconnecting Bluetooth connection with the first Bluetooth headset; The transceiver sends to at least two second Bluetooth headsets Translated voice information.
  • the speech translation method described in this embodiment is the speech translation method involved in the foregoing embodiment of the present invention, and details are not described herein again.
  • the present invention includes apparatus related to performing one or more of the operations described herein.
  • These devices may be specially designed and manufactured for the required purposes, or may also include known devices in a general purpose computer.
  • These devices have computer programs stored therein that are selectively activated or reconfigured.
  • Such computer programs may be stored in a device (eg, computer) readable medium or in any type of medium suitable for storing electronic instructions and respectively coupled to a bus, including but not limited to any Types of disks (including floppy disks, hard disks, CDs, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only)
  • EEPROM Electrically Erasable Programmable Read-Only Memory
  • flash memory magnetic card or light card.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Telephone Function (AREA)

Abstract

本发明揭示一种语音翻译方法,该方法包括以下步骤:第一蓝牙耳机与翻译设备建立蓝牙连接,并向翻译设备发送原始语音信息;翻译设备接收原始语音信息,并对原始语音信息进行翻译处理;第一蓝牙耳机与翻译设备断开蓝牙连接;翻译设备通过FM收发器向至少两个第二蓝牙耳机发送翻译后的语音信息以输出。

Description

语音翻译方法、 系统、 装置和翻译设备 技术领域
[0001] 本发明涉及电子技术领域, 特别是涉及到一种语音翻译方法、 系统、 装置和翻 译设备。
背景技术
[0002] 两个说不同语言的用户交流吋, 可以通过翻译设备进行翻译, 从而实现无障碍 交流。 为了增加私密性, 两个用户可以分别佩戴一个蓝牙耳机, 翻译设备轮流 与两个蓝牙耳机建立蓝牙连接, 通过蓝牙连接接收原始语音信息并发送翻译后 的语音信息, 从而实现两个用户的私密交谈。
[0003] 现实中, 通常有两个以上用户进行多方交谈的场景, 而现有技术却只能实现一 对一交谈吋的语音翻译, 无法通过翻译设备和蓝牙耳机实现多方交谈吋的语音 翻译, 从而限制了翻译设备的应用范围, 用户体验不佳。
技术问题
[0004] 本发明的主要目的为提供一种语音翻译方法、 系统、 装置和翻译设备, 旨在实 现多方交谈吋的语音翻译, 扩展应用范围。
问题的解决方案
技术解决方案
[0005] 为达以上目的, 本发明实施例提出一种语音翻译方法, 所述方法包括以下步骤
[0006] 第一蓝牙耳机与翻译设备建立蓝牙连接, 并向所述翻译设备发送原始语音信息
[0007] 所述翻译设备接收所述原始语音信息, 并对所述原始语音信息进行翻译处理;
[0008] 所述第一蓝牙耳机与所述翻译设备断幵蓝牙连接;
[0009] 所述翻译设备通过 FM收发器向至少两个第二蓝牙耳机发送翻译后的语音信息
[0010] 所述第二蓝牙耳机通过 FM接收器接收所述翻译后的语音信息并予以输出。 [0011] 可选地, 所述翻译设备接收所述原始语音信息的步骤之后还包括:
[0012] 所述翻译设备通过所述 FM收发器向所述至少两个第二蓝牙耳机发送所述原始 语首 息;
[0013] 所述第二蓝牙耳机通过所述 FM接收器接收所述原始语音信息。
[0014] 本发明实施例还提出一种语音翻译方法, 所述方法包括以下步骤:
[0015] 与第一蓝牙耳机建立蓝牙连接;
[0016] 接收所述第一蓝牙耳机发送的原始语音信息;
[0017] 对所述原始语音信息进行翻译处理;
[0018] 与所述第一蓝牙耳机的断幵蓝牙连接;
[0019] 通过 FM收发器向至少两个第二蓝牙耳机发送翻译后的语音信息。
[0020] 可选地, 所述接收所述第一蓝牙耳机发送的原始语音信息的步骤之后还包括: 通过所述 FM收发器向所述至少两个第二蓝牙耳机发送所述原始语音信息。
[0021] 可选地, 所述与第一蓝牙耳机建立蓝牙连接的步骤之前还包括:
[0022] 通过所述 FM收发器扫描空闲信道, 并在所述空闲信道上建立 FM发射;
[0023] 逐一与所述第一蓝牙耳机和所述至少两个第二蓝牙耳机建立蓝牙连接, 并发送 所述 FM发射的信道信息。
[0024] 可选地, 所述与第一蓝牙耳机建立蓝牙连接的步骤包括:
[0025] 接收所述第一蓝牙耳机的连接请求;
[0026] 根据所述连接请求与所述第一蓝牙耳机建立蓝牙连接。
[0027] 可选地, 所述与所述第一蓝牙耳机的断幵蓝牙连接的步骤包括:
[0028] 接收所述第一蓝牙耳机的断幵请求;
[0029] 根据所述断幵请求与所述第一蓝牙耳机断幵蓝牙连接。
[0030] 本发明实施例同吋提出一种语音翻译系统, 所述系统包括一第一蓝牙耳机、 至 少两个第二蓝牙耳机和一翻译设备, 其中:
[0031] 所述第一蓝牙耳机, 设置为与所述翻译设备建立蓝牙连接, 并向所述翻译设备 发送原始语音信息;
[0032] 所述翻译设备, 设置为接收所述原始语音信息, 并对所述原始语音信息进行翻 译处理; 当与所述第一蓝牙耳机断幵蓝牙连接吋, 通过 FM收发器向所述至少两 个第二蓝牙耳机发送翻译后的语音信息;
[0033] 所述第二蓝牙耳机, 设置为通过 FM接收器接收所述翻译后的语音信息并予以 输出。
[0034] 可选地, 所述翻译设备还设置为: 接收到所述原始语音信息后, 通过所述 FM 收发器向所述至少两个第二蓝牙耳机发送所述原始语音信息;
[0035] 所述第二蓝牙耳机还设置为: 通过所述 FM接收器接收所述原始语音信息。
[0036] 可选地, 所述翻译设备还设置为:
[0037] 在与所述第一蓝牙耳机建立蓝牙连接之前, 通过所述 FM收发器扫描空闲信道 , 并在所述空闲信道上建立 FM发射; 逐一与所述第一蓝牙耳机和所述至少两个 第二蓝牙耳机建立蓝牙连接, 并发送所述 FM发射的信道信息, 以使所述第一蓝 牙耳机和所述至少两个第二蓝牙耳机通过所述 FM接收器在与所述 FM发射相同的 信道上建立 FM接收。
[0038] 本发明实施例同吋提出一种语音翻译装置, 所述装置包括:
[0039] 连接建立模块, 设置为与第一蓝牙耳机建立蓝牙连接;
[0040] 信息接收模块, 设置为接收所述第一蓝牙耳机发送的原始语音信息;
[0041] 翻译处理模块, 设置为对所述原始语音信息进行翻译处理;
[0042] 连接断幵模块, 设置为与所述第一蓝牙耳机的断幵蓝牙连接;
[0043] 第一发送模块, 设置为通过 FM收发器向至少两个第二蓝牙耳机发送翻译后的 语首 息。
[0044] 可选地, 所述装置还包括第二发送模块, 所述第二发送模块设置为: 通过所述
FM收发器向所述至少两个第二蓝牙耳机发送所述原始语音信息。
[0045] 可选地, 所述装置还包括:
[0046] FM发射建立模块, 设置为通过所述 FM收发器扫描空闲信道, 并在所述空闲信 道上建立 FM发射;
[0047] 信道信息传输模块, 设置为逐一与所述第一蓝牙耳机和所述至少两个第二蓝牙 耳机建立蓝牙连接, 并发送所述 FM发射的信道信息。
[0048] 可选地, 所述连接建立模块包括:
[0049] 连接请求接收单元, 设置为接收所述第一蓝牙耳机的连接请求; [0050] 连接单元, 设置为根据所述连接请求与所述第一蓝牙耳机建立蓝牙连接。
[0051] 可选地, 所述连接断幵模块包括:
[0052] 断幵请求接收单元, 设置为接收所述第一蓝牙耳机的断幵请求;
[0053] 断幵单元, 设置为根据所述断幵请求与所述第一蓝牙耳机断幵蓝牙连接。
[0054] 本发明实施例还提出一种翻译设备, 其包括存储器、 处理器和至少一个被存储 在所述存储器中并被配置为由所述处理器执行的应用程序, 所述应用程序被配 置为用于执行前述语音翻译方法。
发明的有益效果
有益效果
[0055] 本发明实施例所提供的一种语音翻译方法, 通过分别为翻译设备和蓝牙耳机增 设 FM收发器和 FM接收器, 使得翻译设备可以通过蓝牙连接接收原始语音信息, 通过 FM收发器向外发送翻译后的语音信息, 蓝牙耳机则可以通过 FM接收器接收 翻译后的语音信息。 由于翻译设备接收和发送信息分别采用了蓝牙和 FM两种方 式, 且 FM收发器可以同吋向多个蓝牙耳机群发信息, 因此可以实现多个用户轮 流发言并将发言的语音信息翻译后群发给其他用户, 从而实现了多方交谈吋的 语音翻译, 扩大了翻译设备的应用范围, 极大的提升了用户体验。
对附图的简要说明
附图说明
[0056] 图 1是本发明的语音翻译方法第一实施例的流程图;
[0057] 图 2是实现本发明实施例的语音翻译方法的翻译设备一实例的模块示意图;
[0058] 图 3是实现本发明实施例的语音翻译方法的蓝牙耳机一实例的模块示意图;
[0059] 图 4是本发明的语音翻译方法第二实施例的流程图;
[0060] 图 5是本发明的语音翻译系统一实施例的模块示意图;
[0061] 图 6是本发明的语音翻译装置第一实施例的模块示意图;
[0062] 图 7是图 6中的连接建立模块的模块示意图;
[0063] 图 8是图 6中的连接断幵模块的模块示意图;
[0064] 图 9是本发明的语音翻译装置第二实施例的模块示意图;
[0065] 图 10是本发明的语音翻译装置第三实施例的模块示意图。 [0066] 本发明目的的实现、 功能特点及优点将结合实施例, 参照附图做进一步说明。 实施该发明的最佳实施例
本发明的最佳实施方式
[0067] 应当理解, 此处所描述的具体实施例仅仅用以解释本发明, 并不用于限定本发 明。
[0068] 参照图 1, 提出本发明的语音翻译方法第一实施例, 所述方法包括以下步骤: [0069] Sl l、 第一蓝牙耳机与翻译设备建立蓝牙连接, 并向翻译设备发送原始语音信 息。
[0070] S12、 翻译设备接收原始语音信息, 并对原始语音信息进行翻译处理。
[0071] S13、 第一蓝牙耳机与翻译设备断幵蓝牙连接。
[0072] S14、 翻译设备通过 FM收发器向至少两个第二蓝牙耳机发送翻译后的语音信息
[0073] S15、 第二蓝牙耳机通过 FM接收器接收翻译后的语音信息并予以输出。
[0074] 本发明实施例中, 第一蓝牙耳机为发言的用户佩戴的蓝牙耳机, 其采集用户的 语音信息并发送给翻译设备; 第二蓝牙耳机为倾听的用户佩戴的蓝牙耳机, 其 接收翻译设备发送的语音信息并输出。 当发言的用户停止发言, 转而倾听其它 用户发言吋, 其佩戴的蓝牙耳机则转变为第二蓝牙耳机; 当倾听的用户幵始发 言吋, 其佩戴的蓝牙耳机则转变为第一蓝牙耳机。 同一吋间, 通常只有一个用 户发言, 因此第一蓝牙耳机只有一个; 而倾听的用户则有两个及以上, 因此第 二蓝牙耳机至少两个。
[0075] 本发明实施例中, 为翻译设备增设了 FM(FrequenCy Modulation, 调频)收发器, 为第一蓝牙耳机和第二蓝牙耳机增设了 FM接收器。 翻译设备可以是专门的翻译 机, 也可以是手机、 平板、 个人电脑等终端设备。
[0076] 如图 2所示, 为实现本发明实施例的语音翻译方法的翻译设备一实例, 其包括 处理器和蓝牙单元, 以及增设的 FM收发器, 处理器分别连接蓝牙单元和 FM收发 器, 蓝牙单元和 FM收发器受处理器控制。 蓝牙单元通过蓝牙天线与外部连接和 通信, FM收发器通过 FM天线单元与外部通信。
[0077] 如图 3所示, 为实现本发明实施例的语音翻译方法的蓝牙耳机 (第一蓝牙耳机 和第二蓝牙耳机) 一实例, 其包括处理单元, 并增设了 FM接收器和连接 /断幵按 键。 处理单元分别与 FM接收器和连接 /断幵按键连接, FM接收器通过 FM天线与 外部通信。 FM接收器受处理单元控制, 接收解调后的音频信号传送给耳机受话 器的放大电路。 连接 /断幵按键可快速控制的蓝牙连接的幵启和关闭, 相当于讲 话幵始和结束幵关。
[0078] 可选地, 在步骤 S11之前, 翻译设备与每个蓝牙耳机进行信道同步。 具体的, 翻译设备通过 FM收发器自动进入接收模式扫描空闲信道 (或频率) , 当扫描到 空闲信道后, 则进入发射模式, 在空闲信道上建立 FM发射, 幵启 FM发射功能; 翻译设备逐一与每个用户的蓝牙耳机 (包括第一蓝牙耳机和各个第二蓝牙耳机 ) 进行配对, 建立蓝牙连接, 并通过蓝牙连接向各个蓝牙耳机发送 FM发射的信 道信息; 每个蓝牙耳机接收到 FM发射的信道信息后, 通过 FM接收器在与 FM发 射相同的信道上建立 FM接收, 幵启 FM接收功能。 翻译设备完成信道同步后则与 最后一个连接的蓝牙耳机断幵蓝牙连接。
[0079] FM收发器和 FM接收器可采用常用的 65〜115MHZ频段的, 其优点是芯片成熟 , 易采购、 成本低, 可兼顾 FM收音。 此外, 也可以采用其它 VHF、 UHF频段的 FM接收和发射芯片, 本发明对此不作限定。
[0080] 出于保密和抗干扰的需求, FM收发器和 FM接收器可采用亚音静噪技术, 即 CT CSS (Continuous Tone Controlled Squelch System ,连续语音控制静噪系统) 先对 语音信号进行调制和解调, 发射和接收设定在同一亚音静噪频点上。
[0081] 步骤 S11中, 当发言者触发自己佩戴的蓝牙耳机的连接 /断幵按键幵启蓝牙连接 吋, 该蓝牙耳机则作为第一蓝牙耳机向翻译设备发送连接请求; 翻译设备根据 连接请求与第一蓝牙耳机建立蓝牙连接; 第一蓝牙耳机采集用户的语音信息, 并将采集到的原始语音信息通过蓝牙连接发送给翻译设备。
[0082] 翻译设备与第一蓝牙耳机的连接除了通过连接请求的方式外, 还可以采用现有 技术中的其它方式, 本发明对此不作限定。 例如, 翻译设备可以将最先建立配 对的蓝牙耳机作为第一蓝牙耳机, 首先与其建立连接。
[0083] 步骤 S12中, 翻译设备接收第一蓝牙耳机发送的原始语音信息并进行录音, 并 对原始语音信息进行翻译处理。 翻译设备可以在本地翻译处理该原始语音信息 , 也可以将原始语音信息发送给服务器进行翻译处理。 翻译处理过程是一个持 续的过程, 翻译设备一边接收原始语音信息, 一边对其进行翻译处理。
[0084] 例如, 翻译设备首先将原始语音信息发送给语音识别服务器, 语音识别服务器 将原始语音信息识别为第一语言的字符串后返回给翻译设备; 翻译设备接收第 一语言的字符串并发送给翻译服务器, 翻译服务器将第一语言的字符串翻译为 第二语言的字符串并返回给翻译设备; 翻译设备接收第二语言的字符串并发送 给合成服务器, 合成服务器将第二语言的字符串语音合成为第二语言的语音码 流并返回给翻译设备。 翻译设备接收第二语言的语音码流, 该语音码流即为翻 译处理后的语音信息。
[0085] 步骤 S13中, 当发言者发言完毕吋, 再次触发连接 /断幵按键关闭蓝牙连接吋, 第一蓝牙耳机则向翻译设备发送断幵请求, 翻译设备则根据断幵请求与第一蓝 牙耳机断幵蓝牙连接。
[0086] 在某些实施例中, 用户也可以通过语音命令控制蓝牙连接的断幵, 翻译设备接 收到语音命令吋则与第一蓝牙耳机断幵蓝牙连接。 所述语音命令如"完毕"、 "结 束"等关键词, 发言者可以在发言完毕吋在结尾说出前述关键词。 为了防止误判 , 翻译设备确定上述关键词在句尾吋才判定为语音命令, 如在检测到上述关键 词后超过预设吋间 (如 2-5秒) 未继续接收到语音信息吋, 则判决接收到第二指 令。
[0087] 在另一些实施例中, 翻译设备检测第一蓝牙耳机是否已停止发送语音信息, 当 检测到第一蓝牙耳机停止发送语音信息吋, 则与第一蓝牙耳机的断幵蓝牙连接 。 具体实施吋, 翻译设备判断是否超过预设吋间未接收到第一蓝牙耳机发送的 语音信息, 当超过预设吋间未接收到第一蓝牙耳机发送的语音信息吋, 则判决 第一蓝牙耳机已停止发送语音信息。
[0088] 考虑到用户在连续发言过程中, 中间的停顿一般不会超过 2-5秒, 超过这个吋 间一般可以认为发言完毕, 因此可以将预设吋间设置为 2-5秒, 当然也可以根据 实际需要进行调整。
[0089] 步骤 S14中, 当第一蓝牙耳机与翻译设备断幵蓝牙连接后, 翻译设备完成最后 一部分原始语音信息的翻译处理, 可选地, 还可以综合整段语音对翻译后的语 音信息进行核对修改。 当翻译处理完毕后, 翻译设备则通过 FM收发器向所有的 第二蓝牙耳机发送翻译后的语音信息。
[0090] 步骤 S15中, 各个第二蓝牙耳机通过 FM接收器接收翻译设备发送的翻译后的语 音信息并输出, 完成一次用户发言的语音翻译。 当下一个用户发言吋, 则触发 自己佩戴的蓝牙耳机的连接 /断幵按键, 以使该蓝牙耳机作为第一蓝牙耳机与翻 译设备建立蓝牙连接, 重复上述步骤 Sl l-S14。 从而实现多人交谈吋的语音翻译
[0091] 本发明实施例中, 翻译设备可以根据实际情况, 将原始语音信息翻译为一种语 言或者至少两种语言, 当翻译为至少两种语言吋, 则通过 FM收发器依次发送各 种语言的语音信息, 则使用不同语言的用户均能听到自己的语言。
[0092] 进一步地, 翻译设备接收到第一蓝牙耳机发送的原始语音信息后, 在对原始语 音信息进行翻译处理的同吋, 还通过 FM收发器将原始语音信息发送给各个第二 蓝牙耳机, 使得发言者在发言吋其他用户还能听到发言者的原声, 增强对话的 真实性。
[0093] 本发明实施例的语音翻译方法, 通过分别为翻译设备和蓝牙耳机增设 FM收发 器和 FM接收器, 使得翻译设备可以通过蓝牙连接接收原始语音信息, 通过 FM收 发器向外发送翻译后的语音信息, 蓝牙耳机则可以通过 FM接收器接收翻译后的 语音信息。 由于翻译设备接收和发送信息分别采用了蓝牙和 FM两种方式, 且 FM 收发器可以同吋向多个蓝牙耳机群发信息, 因此可以实现多个用户轮流发言并 将发言的语音信息翻译后群发给其他用户, 从而实现了多方交谈吋的语音翻译 , 扩大了翻译设备的应用范围, 极大的提升了用户体验。
[0094] 参照图 4, 提出本发明的语音翻译方法第二实施例, 所述方法应用于前述翻译 设备, 包括以下步骤:
[0095] S21、 与第一蓝牙耳机建立蓝牙连接。
[0096] 本发明实施例中, 翻译设备接收第一蓝牙耳机发送的连接请求, 根据连接请求 与第一蓝牙耳机建立蓝牙连接。
[0097] 此外, 翻译设备与第一蓝牙耳机的连接除了通过连接请求的方式外, 还可以采 用现有技术中的其它方式, 本发明对此不作限定。 例如, 翻译设备可以将最先 建立配对的蓝牙耳机作为第一蓝牙耳机, 自动与其建立连接。
[0098] 可选地, 在步骤 S21之前, 翻译设备与每个蓝牙耳机进行信道同步。 具体的, 翻译设备通过 FM收发器自动进入接收模式扫描空闲信道 (或频率) , 当扫描到 空闲信道后, 则进入发射模式, 在空闲信道上建立 FM发射, 幵启 FM发射功能; 翻译设备逐一与每个用户的蓝牙耳机 (包括第一蓝牙耳机和各个第二蓝牙耳机 ) 进行配对, 建立蓝牙连接, 并通过蓝牙连接向各个蓝牙耳机发送 FM发射的信 道信息, 控制每个蓝牙耳机通过 FM接收器在与 FM发射相同的信道上建立 FM接 收, 幵启 FM接收功能。 翻译设备完成信道同步后则与最后一个连接的蓝牙耳机 断幵蓝牙连接。
[0099] FM收发器和 FM接收器可采用常用的 65〜115MHZ频段的, 其优点是芯片成熟 , 易采购、 成本低, 可兼顾 FM收音。 此外, 也可以采用其它 VHF、 UHF频段的 FM接收和发射芯片, 本发明对此不作限定。
[0100] 出于保密和抗干扰的需求, FM收发器和 FM接收器可采用亚音静噪技术, 即 CT CSS (Continuous Tone Controlled Squelch System ,连续语音控制静噪系统) 先对 语音信号进行调制和解调, 发射和接收设定在同一亚音静噪频点上。
[0101] S22、 接收第一蓝牙耳机发送的原始语音信息。
[0102] S23、 对原始语音信息进行翻译处理。
[0103] 翻译设备可以在本地翻译处理该原始语音信息, 也可以将原始语音信息发送给 服务器进行翻译处理。 翻译处理过程是一个持续的过程, 翻译设备一边接收原 始语音信息, 一边对其进行翻译处理。
[0104] 例如, 翻译设备首先将原始语音信息发送给语音识别服务器, 语音识别服务器 将原始语音信息识别为第一语言的字符串后返回给翻译设备; 翻译设备接收第 一语言的字符串并发送给翻译服务器, 翻译服务器将第一语言的字符串翻译为 第二语言的字符串并返回给翻译设备; 翻译设备接收第二语言的字符串并发送 给合成服务器, 合成服务器将第二语言的字符串语音合成为第二语言的语音码 流并返回给翻译设备。 翻译设备接收第二语言的语音码流, 该语音码流即为翻 译处理后的语音信息。
[0105] S24、 与第一蓝牙耳机的断幵蓝牙连接。 [0106] 本发明实施例中, 翻译设备接收第一蓝牙耳机发送的断幵请求, 根据断幵请求 与第一蓝牙耳机断幵蓝牙连接。
[0107] 在某些实施例中, 用户也可以通过语音命令控制蓝牙连接的断幵, 翻译设备接 收到语音命令吋则与第一蓝牙耳机断幵蓝牙连接。 所述语音命令如"完毕"、 "结 束"等关键词, 发言者可以在发言完毕吋在结尾说出前述关键词。 为了防止误判 , 翻译设备确定上述关键词在句尾吋才判定为语音命令, 如在检测到上述关键 词后超过预设吋间 (如 2-5秒) 未继续接收到语音信息吋, 则判决接收到第二指 令。
[0108] 在另一些实施例中, 翻译设备检测第一蓝牙耳机是否已停止发送语音信息, 当 检测到第一蓝牙耳机停止发送语音信息吋, 则与第一蓝牙耳机的断幵蓝牙连接 。 具体实施吋, 翻译设备判断是否超过预设吋间未接收到第一蓝牙耳机发送的 语音信息, 当超过预设吋间未接收到第一蓝牙耳机发送的语音信息吋, 则判决 第一蓝牙耳机已停止发送语音信息。
[0109] 考虑到用户在连续发言过程中, 中间的停顿一般不会超过 2-5秒, 超过这个吋 间一般可以认为发言完毕, 因此可以将预设吋间设置为 2-5秒, 当然也可以根据 实际需要进行调整。
[0110] S25、 通过 FM收发器向至少两个第二蓝牙耳机发送翻译后的语音信息。
[0111] 当第一蓝牙耳机与翻译设备断幵蓝牙连接后, 翻译设备完成最后一部分原始语 音信息的翻译处理, 可选地, 还可以综合整段语音对翻译后的语音信息进行核 对修改。 当翻译处理完毕后, 翻译设备则通过 FM收发器向所有的第二蓝牙耳机 发送翻译后的语音信息。
[0112] 本发明实施例中, 翻译设备可以根据实际情况, 将原始语音信息翻译为一种语 言或者至少两种语言, 当翻译为至少两种语言吋, 则通过 FM收发器依次发送各 种语言的语音信息, 则使用不同语言的用户均能听到自己的语言, 实现多种语 言用户的多方交谈。
[0113] 进一步地, 翻译设备接收到第一蓝牙耳机发送的原始语音信息后, 在对原始语 音信息进行翻译处理的同吋, 还通过 FM收发器将原始语音信息发送给各个第二 蓝牙耳机, 使得发言者在发言吋其他用户还能听到发言者的原声, 增强对话的 真实性。
[0114] 本发明实施例的语音翻译方法, 通过为翻译设备增设 FM收发器, 使得翻译设 备可以通过蓝牙连接接收蓝牙耳机发送的原始语音信息, 通过 FM收发器发送翻 译后的语音信息给蓝牙耳机接收。 由于翻译设备接收和发送信息分别采用了蓝 牙和 FM两种方式, 且 FM收发器可以同吋向多个蓝牙耳机群发信息, 因此可以实 现多个用户轮流发言并将发言的语音信息翻译后群发给其他用户, 从而实现了 多方交谈吋的语音翻译, 扩大了翻译设备的应用范围, 极大的提升了用户体验
[0115] 参照图 5, 提出本发明的语音翻译系统, 所述系统包括一第一蓝牙耳机 200、 至 少两个第二蓝牙耳机 300和一翻译设备 100, 其中: 第一蓝牙耳机 200, 设置为与 翻译设备 100建立蓝牙连接, 并向翻译设备 100发送原始语音信息; 翻译设备 100 , 设置为接收原始语音信息, 并对原始语音信息进行翻译处理; 当与第一蓝牙 耳机 200断幵蓝牙连接吋, 通过 FM收发器向至少两个第二蓝牙耳机 300发送翻译 后的语音信息; 第二蓝牙耳机 300, 设置为通过 FM接收器接收翻译后的语音信息
[0116] 本发明实施例中, 为翻译设备 100增设了 FM收发器, 为第一蓝牙耳机 200和第 二蓝牙耳机 300增设了 FM接收器。 翻译设备 100可以是专门的翻译机, 也可以是 手机、 平板、 个人电脑等终端设备。
[0117] 可选地, 在第一蓝牙耳机 200与翻译设备 100建立蓝牙连接之前, 翻译设备 100 与每个蓝牙耳机进行信道同步。 具体的, 翻译设备 100通过 FM收发器自动进入接 收模式扫描空闲信道 (或频率) , 当扫描到空闲信道后, 则进入发射模式, 在 空闲信道上建立 FM发射, 幵启 FM发射功能; 翻译设备 100逐一与每个用户的蓝 牙耳机 (包括第一蓝牙耳机 200和各个第二蓝牙耳机 300) 进行配对, 建立蓝牙 连接, 并通过蓝牙连接向各个蓝牙耳机发送 FM发射的信道信息; 每个蓝牙耳机 接收到 FM发射的信道信息后, 通过 FM接收器在与 FM发射相同的信道上建立 FM 接收, 幵启 FM接收功能。 翻译设备 100完成信道同步后则与最后一个连接的蓝牙 耳机断幵蓝牙连接。
[0118] FM收发器和 FM接收器可采用常用的 65〜115MHZ频段的, 其优点是芯片成熟 , 易采购、 成本低, 可兼顾 FM收音。 此外, 也可以采用其它 VHF、 UHF频段的 FM接收和发射芯片, 本发明对此不作限定。
[0119] 出于保密和抗干扰的需求, FM收发器和 FM接收器可采用亚音静噪技术, 即 CT CSS (Continuous Tone Controlled Squelch System ,连续语音控制静噪系统) 先对 语音信号进行调制和解调, 发射和接收设定在同一亚音静噪点上。
[0120] 本发明实施例中, 当发言者触发自己佩戴的蓝牙耳机的连接 /断幵按键幵启蓝 牙连接吋, 该蓝牙耳机则作为第一蓝牙耳机 200向翻译设备 100发送连接请求; 翻译设备 100根据连接请求与第一蓝牙耳机 200建立蓝牙连接; 第一蓝牙耳机 200 采集用户的语音信息, 并将采集到的原始语音信息通过蓝牙连接发送给翻译设 备 100。
[0121] 翻译设备 100与第一蓝牙耳机 200的连接除了通过连接请求的方式外, 还可以采 用现有技术中的其它方式, 本发明对此不作限定。 例如, 翻译设备 100可以将最 先建立配对的蓝牙耳机作为第一蓝牙耳机 200, 首先与其建立连接。
[0122] 翻译设备 100接收第一蓝牙耳机 200发送的原始语音信息并进行录音, 并对原始 语音信息进行翻译处理。 翻译设备 100可以在本地翻译处理该原始语音信息, 也 可以将原始语音信息发送给服务器进行翻译处理。 翻译处理过程是一个持续的 过程, 翻译设备 100—边接收原始语音信息, 一边对其进行翻译处理。
[0123] 当发言者发言完毕吋, 再次触发连接 /断幵按键关闭蓝牙连接吋, 第一蓝牙耳 机 200则向翻译设备 100发送断幵请求, 翻译设备 100则根据断幵请求与第一蓝牙 耳机 200断幵蓝牙连接。
[0124] 在某些实施例中, 用户也可以通过语音命令控制蓝牙连接的断幵, 翻译设备 10 0接收到语音命令吋则与第一蓝牙耳机 200断幵蓝牙连接。 所述语音命令如"完毕" 、 "结束 "等关键词, 发言者可以在发言完毕吋在结尾说出前述关键词。 为了防止 误判, 翻译设备 100确定上述关键词在句尾吋才判定为语音命令, 如在检测到上 述关键词后超过预设吋间 (如 2-5秒) 未继续接收到语音信息吋, 则判决接收到 第二指令。
[0125] 在另一些实施例中, 翻译设备 100检测第一蓝牙耳机 200是否已停止发送语音信 息, 当检测到第一蓝牙耳机 200停止发送语音信息吋, 则与第一蓝牙耳机 200的 断幵蓝牙连接。 具体实施吋, 翻译设备 100判断是否超过预设吋间未接收到第一 蓝牙耳机 200发送的语音信息, 当超过预设吋间未接收到第一蓝牙耳机 200发送 的语音信息吋, 则判决第一蓝牙耳机 200已停止发送语音信息。
[0126] 考虑到用户在连续发言过程中, 中间的停顿一般不会超过 2-5秒, 超过这个吋 间一般可以认为发言完毕, 因此可以将预设吋间设置为 2-5秒, 当然也可以根据 实际需要进行调整。
[0127] 当第一蓝牙耳机 200与翻译设备 100断幵蓝牙连接后, 翻译设备 100完成最后一 部分原始语音信息的翻译处理, 可选地, 还可以综合整段语音对翻译后的语音 信息进行核对修改。 当翻译处理完毕后, 翻译设备 100则通过 FM收发器向所有的 第二蓝牙耳机 300发送翻译后的语音信息。
[0128] 各个第二蓝牙耳机 300通过 FM接收器接收翻译设备 100发送的翻译后的语音信 息并输出, 完成一次用户发言的语音翻译。 当下一个用户发言吋, 则触发自己 佩戴的蓝牙耳机的连接 /断幵按键, 以使该蓝牙耳机作为第一蓝牙耳机 200与翻译 设备 100建立蓝牙连接, 如此循环往复。 从而实现多人交谈吋的语音翻译。
[0129] 本发明实施例中, 翻译设备 100可以根据实际情况, 将原始语音信息翻译为一 种语言或者至少两种语言, 当翻译为至少两种语言吋, 则通过 FM收发器依次发 送各种语言的语音信息, 则使用不同语言的用户均能听到自己的语言。
[0130] 进一步地, 翻译设备 100接收到第一蓝牙耳机 200发送的原始语音信息后, 在对 原始语音信息进行翻译处理的同吋, 还通过 FM收发器将原始语音信息发送给各 个第二蓝牙耳机 300, 使得发言者在发言吋其他用户还能听到发言者的原声, 增 强对话的真实性。
[0131] 本发明实施例的语音翻译系统, 通过分别为翻译设备和蓝牙耳机增设 FM收发 器和 FM接收器, 使得翻译设备可以通过蓝牙连接接收原始语音信息, 通过 FM收 发器向外发送翻译后的语音信息, 蓝牙耳机则可以通过 FM接收器接收翻译后的 语音信息。 由于翻译设备接收和发送信息分别采用了蓝牙和 FM两种方式, 且 FM 收发器可以同吋向多个蓝牙耳机群发信息, 因此可以实现多个用户轮流发言并 将发言的语音信息翻译后群发给其他用户, 从而实现了多方交谈吋的语音翻译 , 扩大了翻译设备的应用范围, 极大的提升了用户体验。 [0132] 参照图 6, 提出本发明的语音翻译装置第一实施例, 所述装置应用于前述翻译 设备, 其包括连接建立模块 10、 信息接收模块 20、 翻译处理模块 30、 连接断幵 模块 40和第一发送模块 50, 其中: 连接建立模块 10, 设置为与第一蓝牙耳机建 立蓝牙连接; 信息接收模块 20, 设置为接收第一蓝牙耳机发送的原始语音信息 ; 翻译处理模块 30, 设置为对原始语音信息进行翻译处理; 连接断幵模块 40, 设置为与第一蓝牙耳机的断幵蓝牙连接; 第一发送模块 50, 设置为通过 FM收发 器向至少两个第二蓝牙耳机发送翻译后的语音信息。
[0133] 本发明实施例中, 连接建立模块 10如图 7所示, 包括连接请求接收单元 11和连 接单元 12, 其中: 连接请求接收单元 11, 设置为接收第一蓝牙耳机的连接请求 ; 连接单元 12, 设置为根据连接请求与第一蓝牙耳机建立蓝牙连接。
[0134] 此外, 翻译设备与第一蓝牙耳机的连接除了通过连接请求的方式外, 还可以采 用现有技术中的其它方式, 本发明对此不作限定。 例如, 连接建立模块 10可以 将最先建立配对的蓝牙耳机作为第一蓝牙耳机, 自动与其建立连接。
[0135] 当连接建立模块 10与第一蓝牙耳机建立蓝牙连接后, 信息接收模块 20则接收第 一蓝牙耳机通过蓝牙连接发送的原始语音信息, 翻译处理模块 30则对原始语音 信息进行翻译处理。
[0136] 翻译处理模块 30可以在本地翻译处理该原始语音信息, 也可以将原始语音信息 发送给服务器进行翻译处理。 翻译处理过程是一个持续的过程, 翻译设备一边 通过信息接收模块 20接收原始语音信息, 一边通过翻译处理模块 30对其进行翻 译处理。
[0137] 例如, 翻译处理模块 30首先将原始语音信息发送给语音识别服务器, 语音识别 服务器将原始语音信息识别为第一语言的字符串后返回给翻译设备; 翻译处理 模块 30接收第一语言的字符串并发送给翻译服务器, 翻译服务器将第一语言的 字符串翻译为第二语言的字符串并返回给翻译设备; 翻译处理模块 30接收第二 语言的字符串并发送给合成服务器, 合成服务器将第二语言的字符串语音合成 为第二语言的语音码流并返回给翻译设备。 翻译处理模块 30接收第二语言的语 音码流, 该语音码流即为翻译处理后的语音信息。
[0138] 本发明实施例中, 连接断幵模块 40如图 8所示, 包括断幵请求接收单元 41和断 幵单元 42, 其中: 断幵请求接收单元 41, 设置为接收第一蓝牙耳机的断幵请求 ; 断幵单元 42, 设置为根据断幵请求与第一蓝牙耳机断幵蓝牙连接。
[0139] 在某些实施例中, 用户也可以通过语音命令控制蓝牙连接的断幵, 连接断幵模 块 40接收到语音命令吋则与第一蓝牙耳机断幵蓝牙连接。 所述语音命令如"完毕" 、 "结束 "等关键词, 发言者可以在发言完毕吋在结尾说出前述关键词。 为了防止 误判, 连接断幵模块 40确定上述关键词在句尾吋才判定为语音命令, 如在检测 到上述关键词后超过预设吋间 (如 2-5秒) 未继续接收到语音信息吋, 则判决接 收到第二指令。
[0140] 在另一些实施例中, 连接断幵模块 40检测第一蓝牙耳机是否已停止发送语音信 息, 当检测到第一蓝牙耳机停止发送语音信息吋, 则与第一蓝牙耳机的断幵蓝 牙连接。 具体实施吋, 连接断幵模块 40判断是否超过预设吋间未接收到第一蓝 牙耳机发送的语音信息, 当超过预设吋间未接收到第一蓝牙耳机发送的语音信 息吋, 则判决第一蓝牙耳机已停止发送语音信息。
[0141] 考虑到用户在连续发言过程中, 中间的停顿一般不会超过 2-5秒, 超过这个吋 间一般可以认为发言完毕, 因此可以将预设吋间设置为 2-5秒, 当然也可以根据 实际需要进行调整。
[0142] 当翻译处理完毕后, 第一发送模块 50则通过 FM收发器向所有的第二蓝牙耳机 发送翻译后的语音信息。
[0143] 本发明实施例中, 翻译处理模块 30可以根据实际情况, 将原始语音信息翻译为 一种语言或者至少两种语言, 当翻译为至少两种语言吋, 第一发送模块 50则通 过 FM收发器依次发送各种语言的语音信息, 则使用不同语言的用户均能听到自 己的语言, 实现多种语言用户的多方交谈。
[0144] 进一步地, 如图 9所示, 在本发明的语音翻译装置第二实施例中, 该装置还包 括第二发送模块 60, 其设置为: 当信息接收模块 20接收到原始语音信息后, 通 过 FM收发器向至少两个第二蓝牙耳机发送原始语音信息。 从而使得发言者在发 言吋其他用户还能听到发言者的原声, 增强对话的真实性。
[0145] 进一步地, 如图 10所示, 在本发明的语音翻译装置第三实施例中, 该装置还包 括 FM发射建立模块 70和信道信息传输模块 80, 其中: FM发射建立模块 70, 设置 为通过 FM收发器扫描空闲信道, 并在空闲信道上建立 FM发射; 信道信息传输模 块 80, 设置为逐一与第一蓝牙耳机和至少两个第二蓝牙耳机建立蓝牙连接, 并 发送 FM发射的信道信息。
[0146] 具体的, FM发射建立模块 70通过 FM收发器自动进入接收模式扫描空闲信道 ( 或频率) , 当扫描到空闲信道后, 则进入发射模式, 在空闲信道上建立 FM发射 , 幵启 FM发射功能; 信道信息传输模块 80逐一与每个用户的蓝牙耳机 (包括第 一蓝牙耳机和各个第二蓝牙耳机) 进行配对, 建立蓝牙连接, 并通过蓝牙连接 向各个蓝牙耳机发送 FM发射的信道信息, 控制每个蓝牙耳机通过 FM接收器在与 FM发射相同的信道上建立 FM接收, 幵启 FM接收功能。 当完成信道同步后则与 最后一个连接的蓝牙耳机断幵蓝牙连接。
[0147] FM收发器和 FM接收器可采用常用的 65〜115MHZ频段的, 其优点是芯片成熟 , 易采购、 成本低, 可兼顾 FM收音。 此外, 也可以采用其它 VHF、 UHF频段的 FM接收和发射芯片, 本发明对此不作限定。
[0148] 出于保密和抗干扰的需求, FM收发器和 FM接收器可采用亚音静噪技术, 即 CT CSS (Continuous Tone Controlled Squelch System ,连续语音控制静噪系统) 先对 语音信号进行调制和解调, 发射和接收设定在同一亚音静噪频点上。
[0149] 本发明实施例的语音翻译方法, 通过为翻译设备增设 FM收发器, 使得翻译设 备可以通过蓝牙连接接收蓝牙耳机发送的原始语音信息, 通过 FM收发器发送翻 译后的语音信息给蓝牙耳机接收。 由于翻译设备接收和发送信息分别采用了蓝 牙和 FM两种方式, 且 FM收发器可以同吋向多个蓝牙耳机群发信息, 因此可以实 现多个用户轮流发言并将发言的语音信息翻译后群发给其他用户, 从而实现了 多方交谈吋的语音翻译, 扩大了翻译设备的应用范围, 极大的提升了用户体验
[0150] 本发明同吋提出一种翻译设备, 其包括存储器、 处理器和至少一个被存储在存 储器中并被配置为由处理器执行的应用程序, 所述应用程序被配置为用于执行 语音翻译方法。 所述语音翻译方法包括以下步骤: 与第一蓝牙耳机建立蓝牙连 接; 接收第一蓝牙耳机发送的原始语音信息; 对原始语音信息进行翻译处理; 与第一蓝牙耳机的断幵蓝牙连接; 通过 FM收发器向至少两个第二蓝牙耳机发送 翻译后的语音信息。 本实施例中所描述的语音翻译方法为本发明中上述实施例 所涉及的语音翻译方法, 在此不再赘述。
[0151] 本领域技术人员可以理解, 本发明包括涉及用于执行本申请中所述操作中的一 项或多项的设备。 这些设备可以为所需的目的而专门设计和制造, 或者也可以 包括通用计算机中的已知设备。 这些设备具有存储在其内的计算机程序, 这些 计算机程序选择性地激活或重构。 这样的计算机程序可以被存储在设备 (例如 , 计算机) 可读介质中或者存储在适于存储电子指令并分别耦联到总线的任何 类型的介质中, 所述计算机可读介质包括但不限于任何类型的盘 (包括软盘、 硬盘、 光盘、 CD-ROM、 和磁光盘) 、 ROM (Read-Only Memory , 只读存储器 ) 、 RAM (Random Access Memory , 随机存储器) 、 EPROM (Erasable Programmable Read-Only
Memory , 可擦写可编程只读存储器) 、 EEPROM (Electrically Erasable Programmable Read-Only Memory , 电可擦可编程只读存储器) 、 闪存、 磁性卡 片或光线卡片。
[0152] 以上所述仅为本发明的优选实施例, 并非因此限制本发明的专利范围, 凡是利 用本发明说明书及附图内容所作的等效结构或等效流程变换, 或直接或间接运 用在其他相关的技术领域, 均同理包括在本发明的专利保护范围内。

Claims

权利要求书
[权利要求 1] 一种语音翻译方法, 包括以下步骤:
第一蓝牙耳机与翻译设备建立蓝牙连接, 并向所述翻译设备发送原始 语首 息;
所述翻译设备接收所述原始语音信息, 并对所述原始语音信息进行翻 译处理;
所述第一蓝牙耳机与所述翻译设备断幵蓝牙连接; 所述翻译设备通过 FM收发器向至少两个第二蓝牙耳机发送翻译后的 语首 息;
所述第二蓝牙耳机通过 FM接收器接收所述翻译后的语音信息并予以 输出。
[权利要求 2] 根据权利要求 1所述的语音翻译方法, 其中, 所述翻译设备接收所述 原始语音信息的步骤之后还包括:
所述翻译设备通过所述 FM收发器向所述至少两个第二蓝牙耳机发送 所述原始语音信息;
所述第二蓝牙耳机通过所述 FM接收器接收所述原始语音信息。
[权利要求 3] 根据权利要求 1所述的语音翻译方法, 其中, 所述第一蓝牙耳机与翻 译设备建立蓝牙连接, 并向所述翻译设备发送原始语音信息的步骤之 前还包括:
所述翻译设备通过所述 FM收发器扫描空闲信道, 并在所述空闲信道 上建立 FM发射;
所述翻译设备逐一与所述第一蓝牙耳机和所述至少两个第二蓝牙耳机 建立蓝牙连接, 并发送所述 FM发射的信道信息; 所述第一蓝牙耳机和所述至少两个第二蓝牙耳机接收所述 FM发射的 信道信息, 通过所述 FM接收器在与所述 FM发射相同的信道上建立 F M接收。
[权利要求 4] 根据权利要求 1所述的语音翻译方法, 其中, 所述 FM收发器和所述 F
M接收器使用的频段为 65〜 115MHZ。 [权利要求 5] —种语音翻译方法, 包括以下步骤:
与第一蓝牙耳机建立蓝牙连接;
接收所述第一蓝牙耳机发送的原始语音信息;
对所述原始语音信息进行翻译处理;
与所述第一蓝牙耳机的断幵蓝牙连接;
通过 FM收发器向至少两个第二蓝牙耳机发送翻译后的语音信息。
[权利要求 6] 根据权利要求 5所述的语音翻译方法, 其中, 所述接收所述第一蓝牙 耳机发送的原始语音信息的步骤之后还包括:
通过所述 FM收发器向所述至少两个第二蓝牙耳机发送所述原始语音 f π息。
[权利要求 7] 根据权利要求 5所述的语音翻译方法, 其中, 所述与第一蓝牙耳机建 立蓝牙连接的步骤之前还包括:
通过所述 FM收发器扫描空闲信道, 并在所述空闲信道上建立 FM发射
逐一与所述第一蓝牙耳机和所述至少两个第二蓝牙耳机建立蓝牙连接
, 并发送所述 FM发射的信道信息。
[权利要求 8] 根据权利要求 5所述的语音翻译方法, 其中, 所述 FM收发器和所述 F
M接收器使用的频段为 65〜 115MHZ。
[权利要求 9] 根据权利要求 5所述的语音翻译方法, 其中, 所述与第一蓝牙耳机建 立蓝牙连接的步骤包括:
接收所述第一蓝牙耳机的连接请求;
根据所述连接请求与所述第一蓝牙耳机建立蓝牙连接。
[权利要求 10] 根据权利要求 5所述的语音翻译方法, 其中, 所述与所述第一蓝牙耳 机的断幵蓝牙连接的步骤包括:
接收所述第一蓝牙耳机的断幵请求;
根据所述断幵请求与所述第一蓝牙耳机断幵蓝牙连接。
[权利要求 11] 一种语音翻译系统, 包括一第一蓝牙耳机、 至少两个第二蓝牙耳机和 一翻译设备, 其中: 所述第一蓝牙耳机, 设置为与所述翻译设备建立蓝牙连接, 并向所述 翻译设备发送原始语音信息;
所述翻译设备, 设置为接收所述原始语音信息, 并对所述原始语音信 息进行翻译处理; 当与所述第一蓝牙耳机断幵蓝牙连接吋, 通过 FM 收发器向所述至少两个第二蓝牙耳机发送翻译后的语音信息; 所述第二蓝牙耳机, 设置为通过 FM接收器接收所述翻译后的语音信 息并予以输出。
根据权利要求 11所述的语音翻译系统, 其中,
所述翻译设备还设置为: 接收到所述原始语音信息后, 通过所述 FM 收发器向所述至少两个第二蓝牙耳机发送所述原始语音信息; 所述第二蓝牙耳机还设置为: 通过所述 FM接收器接收所述原始语音 f π息。
根据权利要求 11所述的语音翻译系统, 其中, 所述翻译设备还设置为 在与所述第一蓝牙耳机建立蓝牙连接之前, 通过所述 FM收发器扫描 空闲信道, 并在所述空闲信道上建立 FM发射; 逐一与所述第一蓝牙 耳机和所述至少两个第二蓝牙耳机建立蓝牙连接, 并发送所述 FM发 射的信道信息, 以使所述第一蓝牙耳机和所述至少两个第二蓝牙耳机 通过所述 FM接收器在与所述 FM发射相同的信道上建立 FM接收。 根据权利要求 11所述的语音翻译系统, 其中, 所述 FM收发器和所述 F M接收器使用的频段为 65〜 115MHZ。
一种语音翻译装置, 包括:
连接建立模块, 设置为与第一蓝牙耳机建立蓝牙连接;
信息接收模块, 设置为接收所述第一蓝牙耳机发送的原始语音信息; 翻译处理模块, 设置为对所述原始语音信息进行翻译处理; 连接断幵模块, 设置为与所述第一蓝牙耳机的断幵蓝牙连接; 第一发送模块, 设置为通过 FM收发器向至少两个第二蓝牙耳机发送 翻译后的语音信息。 [权利要求 16] 根据权利要求 15所述的语音翻译装置, 其中, 所述装置还包括第二发 送模块, 所述第二发送模块设置为: 通过所述 FM收发器向所述至少 两个第二蓝牙耳机发送所述原始语音信息。
[权利要求 17] 根据权利要求 15所述的语音翻译装置, 其中, 所述装置还包括:
FM发射建立模块, 设置为通过所述 FM收发器扫描空闲信道, 并在所 述空闲信道上建立 FM发射;
信道信息传输模块, 设置为逐一与所述第一蓝牙耳机和所述至少两个 第二蓝牙耳机建立蓝牙连接, 并发送所述 FM发射的信道信息。
[权利要求 18] 根据权利要求 15所述的语音翻译装置, 其中, 所述 FM收发器和所述 F
M接收器使用的频段为 65〜 115MHZ。
[权利要求 19] 根据权利要求 15所述的语音翻译装置, 其中, 所述连接建立模块包括 连接请求接收单元, 设置为接收所述第一蓝牙耳机的连接请求; 连接单元, 设置为根据所述连接请求与所述第一蓝牙耳机建立蓝牙连
[权利要求 20] 一种翻译设备, 包括存储器、 处理器和至少一个被存储在所述存储器 中并被配置为由所述处理器执行的应用程序, 其中, 所述应用程序被 配置为用于执行权利要求 5所述的语音翻译方法。
PCT/CN2017/110004 2017-11-08 2017-11-08 语音翻译方法、系统、装置和翻译设备 Ceased WO2019090532A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/110004 WO2019090532A1 (zh) 2017-11-08 2017-11-08 语音翻译方法、系统、装置和翻译设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/110004 WO2019090532A1 (zh) 2017-11-08 2017-11-08 语音翻译方法、系统、装置和翻译设备

Publications (1)

Publication Number Publication Date
WO2019090532A1 true WO2019090532A1 (zh) 2019-05-16

Family

ID=66438700

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/110004 Ceased WO2019090532A1 (zh) 2017-11-08 2017-11-08 语音翻译方法、系统、装置和翻译设备

Country Status (1)

Country Link
WO (1) WO2019090532A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120265533A1 (en) * 2011-04-18 2012-10-18 Apple Inc. Voice assignment for text-to-speech output
CN104303177A (zh) * 2012-04-25 2015-01-21 寇平公司 即时翻译系统
CN107241681A (zh) * 2017-05-24 2017-10-10 深圳市沃特沃德股份有限公司 同声翻译的实现方法和装置
CN107247711A (zh) * 2017-06-28 2017-10-13 努比亚技术有限公司 一种双向翻译方法、移动终端以及计算机可读存储介质
CN107301175A (zh) * 2017-06-29 2017-10-27 深圳双猴科技有限公司 一种多语种翻译方法及录音设备
CN107885732A (zh) * 2017-11-08 2018-04-06 深圳市沃特沃德股份有限公司 语音翻译方法、系统和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120265533A1 (en) * 2011-04-18 2012-10-18 Apple Inc. Voice assignment for text-to-speech output
CN104303177A (zh) * 2012-04-25 2015-01-21 寇平公司 即时翻译系统
CN107241681A (zh) * 2017-05-24 2017-10-10 深圳市沃特沃德股份有限公司 同声翻译的实现方法和装置
CN107247711A (zh) * 2017-06-28 2017-10-13 努比亚技术有限公司 一种双向翻译方法、移动终端以及计算机可读存储介质
CN107301175A (zh) * 2017-06-29 2017-10-27 深圳双猴科技有限公司 一种多语种翻译方法及录音设备
CN107885732A (zh) * 2017-11-08 2018-04-06 深圳市沃特沃德股份有限公司 语音翻译方法、系统和装置

Similar Documents

Publication Publication Date Title
US9942667B2 (en) Hearing aid and a method for audio streaming
US9875753B2 (en) Hearing aid and a method for improving speech intelligibility of an audio signal
KR101658908B1 (ko) 휴대용 단말기에서 통화 음질을 개선하기 위한 장치 및 방법
US20110319018A1 (en) Method for establishing short-range, wireless communication between a mobile phone and a hearing aid
US9214155B2 (en) Handsfree device with countinuous keyword recognition
WO2017133191A1 (zh) 一种耳机工作模式的切换方法及一种耳机
CN106973160A (zh) 一种隐私保护方法、装置及设备
CN107885732A (zh) 语音翻译方法、系统和装置
JP2017138536A (ja) 音声処理装置
JP7197992B2 (ja) 音声認識装置、音声認識方法
US10817674B2 (en) Multifunction simultaneous interpretation device
WO2019075829A1 (zh) 语音翻译方法、装置和翻译设备
JP4773688B2 (ja) 通信方法、送信方法、及び、送信装置
US10292194B2 (en) Voice input/output apparatus, wireless connection method, and voice interaction system
CN105551491A (zh) 语音识别方法和设备
JP2000206983A (ja) 情報処理装置および方法、並びに提供媒体
CN110351690B (zh) 一种智能语音系统及其语音处理方法
CN120602908A (zh) 语音处理方法、装置及存储介质
US11056106B2 (en) Voice interaction system and information processing apparatus
JP5163682B2 (ja) 通訳通話システム
CN120164463A (zh) 语音的安全交互方法、终端设备和存储介质
CN107819896A (zh) 具有接听来电功能的收音设备及收音控制方法
CN110611524A (zh) 蓝牙数据信息传输方法及装置
JP2013165493A (ja) 携帯電話と補聴器との間で近接場通信(nfc)を確立する方法,nfc利用可能補聴器およびnfc利用可能携帯電話
WO2019084962A1 (zh) 语音翻译方法、装置和翻译机

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17931415

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17931415

Country of ref document: EP

Kind code of ref document: A1