WO2016161641A1 - 语音识别方法、语音唤醒装置、语音识别装置及终端 - Google Patents

语音识别方法、语音唤醒装置、语音识别装置及终端 Download PDF

Info

Publication number
WO2016161641A1
WO2016161641A1 PCT/CN2015/076342 CN2015076342W WO2016161641A1 WO 2016161641 A1 WO2016161641 A1 WO 2016161641A1 CN 2015076342 W CN2015076342 W CN 2015076342W WO 2016161641 A1 WO2016161641 A1 WO 2016161641A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice
wake
voice information
monitored
module
Prior art date
Application number
PCT/CN2015/076342
Other languages
English (en)
French (fr)
Inventor
周均扬
Original Assignee
华为技术有限公司
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
Priority to EP15888197.9A priority Critical patent/EP3282445A4/en
Priority to BR112017021673-6A priority patent/BR112017021673B1/pt
Priority to PCT/CN2015/076342 priority patent/WO2016161641A1/zh
Priority to JP2017553159A priority patent/JP6564058B2/ja
Priority to CA2982196A priority patent/CA2982196C/en
Priority to CN201580023412.XA priority patent/CN106463112B/zh
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to AU2015390534A priority patent/AU2015390534B2/en
Publication of WO2016161641A1 publication Critical patent/WO2016161641A1/zh
Priority to US15/729,097 priority patent/US10943584B2/en
Priority to AU2019268131A priority patent/AU2019268131A1/en
Priority to US17/178,009 priority patent/US11783825B2/en
Priority to AU2021286393A priority patent/AU2021286393B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724—User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
    • H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M1/00—Substation equipment, e.g. for use by subscribers
    • H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/725—Cordless telephones
    • 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

Definitions

  • the present invention relates to the field of mobile communications technologies, and in particular, to a voice recognition method, a voice wake-up device, a voice recognition device, and a terminal.
  • touch screen technology is becoming more and more mature.
  • touch screen technology facilitates the user's operation, when the telephone interaction is performed, multiple steps are required to complete, and when the driver is driving or inconvenient to touch, the answering call may be missed.
  • the embodiment of the invention provides a voice recognition method, a voice wake-up device, a voice recognition device and a terminal.
  • the user only needs to issue one command, and can meet the requirements of the user, no need for the assistance of the touch screen, and no need to input the command multiple times.
  • an embodiment of the present invention provides a voice recognition method, where the method includes:
  • the voice wake-up device listens to voice information in the surrounding environment
  • the voice wake-up device determines that the monitored voice information matches the voice wake-up model, the voice information of the first preset duration is buffered, and a trigger signal for triggering the voice recognition device is triggered, where the trigger signal is used to indicate After the voice recognition device is activated, the voice information buffered by the voice wake-up device is read and recognized.
  • the determining that the monitored voice information matches the voice wakeup model includes:
  • the determining that the monitored voice information matches the voice wakeup model includes:
  • an embodiment of the present invention provides a voice recognition method, where the method includes:
  • the voice recognition device receives a trigger signal sent by the voice wake-up device, and the trigger signal is used to instruct the voice recognition device to activate and identify the first voice information buffered by the voice wake-up device;
  • the voice recognition device After receiving the trigger signal, the voice recognition device starts and monitors the second voice information of the second preset duration;
  • the method further includes:
  • the voice recognition device matches the acquired recognition result with pre-stored voice instruction information
  • the voice recognition device performs an operation corresponding to the matched voice instruction information.
  • the method further includes:
  • the voice recognition device automatically turns off when the trigger signal is not received again within a third preset time period after receiving the trigger signal.
  • an embodiment of the present invention provides a voice recognition method, where the method includes:
  • the voice wake-up device listens to voice information in the surrounding environment
  • a trigger signal is triggered to trigger the voice recognition device to be activated.
  • the determining that the monitored voice information matches the voice wakeup model includes:
  • the determining that the monitored voice information matches the voice wakeup model includes:
  • an embodiment of the present invention provides a voice recognition method, where the method includes:
  • the voice recognition device receives the trigger signal sent by the voice wake-up device
  • the voice recognition device After receiving the trigger signal, the voice recognition device starts and sends a voice prompt instruction to the user;
  • the voice recognition device records a voice signal input by the user according to the voice prompt instruction, and identifies the voice signal to obtain a recognition result.
  • an embodiment of the present invention further provides a voice wake-up device, where the device includes:
  • a monitoring module for monitoring voice information in the surrounding environment
  • a determining module configured to determine whether the voice information monitored by the monitoring module matches the voice wakeup model
  • a cache module configured to cache, when the determining module determines that the voice information monitored by the monitoring module matches the voice wakeup model, the voice information of the first preset duration monitored by the monitoring module;
  • the sending module is configured to send a trigger signal that triggers the activation of the voice recognition device, and the trigger signal is used to indicate that the voice recognition device starts to read and recognize the voice information buffered by the voice wake device.
  • the determining module is configured to: when determining that the monitored voice information matches the predetermined wake-up voice information, determining the monitored voice information and Voice wake model matching.
  • the method further includes:
  • An extracting module configured to extract a voiceprint feature in the monitored voice signal when the determining module determines that the monitored voice information matches the predetermined wake-up voice information
  • the determining module is further configured to: when it is determined that the voiceprint feature extracted by the extraction module matches a predetermined voiceprint feature, determine that the monitored voice information matches the voice wakeup model.
  • an embodiment of the present invention provides a voice recognition apparatus, including:
  • a receiving module configured to receive a trigger signal sent by the voice wake-up device, where the trigger signal is used to instruct the voice recognition device to activate and identify the first voice information buffered by the voice wake-up device;
  • a monitoring module configured to: after the receiving module receives the trigger signal, start and monitor second voice information of a second preset duration;
  • the identification module is configured to identify the first voice information buffered by the voice wake-up device and the second voice information that is monitored by the monitoring module, to obtain a recognition result.
  • the method further includes:
  • a matching module configured to match the recognition result obtained by the identification module with the pre-stored voice instruction information
  • An execution module is configured to perform an operation corresponding to the matched voice instruction information.
  • the method further includes:
  • the closing module is configured to close the voice recognition module when it is determined that the trigger signal is not received again within a third preset time period after receiving the trigger signal.
  • a seventh aspect of the present invention provides a voice wake-up apparatus, including:
  • a monitoring module for monitoring voice information in the surrounding environment
  • a determining module configured to determine whether the monitored voice information matches the voice wakeup model
  • a sending module configured to determine, in the determining module, the monitored voice information and the voice wakeup model When matching, a trigger signal is generated that triggers the activation of the speech recognition device.
  • the determining module is configured to: when determining that the monitored voice information matches the predetermined wake-up voice information, determining the monitored voice information and Voice wake model matching.
  • the method further includes:
  • An extracting module configured to extract a voiceprint feature in the monitored voice signal when the determining module determines that the monitored voice information matches the predetermined wake-up voice information
  • the determining module is configured to determine that the extracted voiceprint feature matches the predetermined voiceprint feature, and then determine that the monitored voice information matches the voice wakeup model.
  • an embodiment of the present invention provides a voice recognition apparatus, including:
  • a receiving module configured to receive a trigger signal sent by the voice wake-up device
  • a sending module configured to: after the receiving module receives the trigger signal, initiate and send a voice prompting instruction to the user;
  • the processing module is configured to record a voice signal input by the user according to the voice prompt instruction, and identify the voice signal to obtain a recognition result.
  • a ninth aspect, the embodiment of the present invention provides a terminal, including:
  • the voice wake-up device is configured to monitor voice information in a surrounding environment; and when determining that the monitored voice information matches the voice wake-up model, buffering the first voice information that is monitored within the first preset duration, and issuing a trigger to initiate voice Identifying a trigger signal of the device;
  • the voice recognition device is configured to: after receiving the trigger signal sent by the voice wake-up device, start and monitor the second voice information in the second preset duration, and identify the first voice information buffered by the voice wake-up device and The second voice information that is monitored is obtained, and the recognition result is obtained.
  • the voice wake-up device is a digital signal processor DSP.
  • the voice recognition device is an application processor AP.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the voice information is buffered by the voice wake-up device, so that the voice recognition device monitors the second voice information after the startup, and identifies the cached first voice information and the second voice information, thereby preventing the voice from being started after the wake-up.
  • the identification device starts to acquire the voice information, the partial voice information sent by the user before the voice recognition device is activated is lost.
  • FIG. 1 is a schematic structural diagram of a terminal according to an embodiment of the present disclosure
  • FIG. 2 is a flowchart of a voice recognition method according to an embodiment of the present invention.
  • FIG. 3 is a flowchart of another voice recognition method according to an embodiment of the present invention.
  • FIG. 4 is a flowchart of still another voice recognition method according to an embodiment of the present invention.
  • FIG. 5 is a flowchart of still another voice recognition method according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of a voice wake-up device according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of a voice recognition apparatus according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of another voice wake-up device according to an embodiment of the present invention.
  • FIG. 9 is a schematic diagram of another voice recognition apparatus according to an embodiment of the present invention.
  • FIG. 10 is a schematic diagram of a voice recognition method according to an embodiment of the present invention.
  • the embodiment of the invention provides a voice recognition method, a voice wake-up device, a voice recognition device and a terminal, and the user only needs to issue a command to satisfy the user's request, and the touch screen is no longer needed. Help, you do not need to enter the command multiple times.
  • the method and the device are based on the same inventive concept. Since the principles of the method and the device for solving the problem are similar, the implementation of the terminal, the device and the method can be referred to each other, and the repeated description is not repeated.
  • a terminal is provided in the embodiment of the present invention. As shown in FIG. 1 , the terminal includes a voice wake-up device 101 and a voice recognition device 102.
  • the voice wake-up device 101 can be implemented by a digital signal processor (DSP).
  • DSP digital signal processor
  • the voice recognition device 102 can be implemented by an Application Processor (AP).
  • AP Application Processor
  • the voice recognition device 102 can also be implemented by a Central Process Unit (CPU).
  • the voice waking device 101 is configured to monitor voice information in a surrounding environment, and determine that the monitored voice information is buffered with the voice waking model, and the first voice information that is monitored in the first preset duration is buffered and sent out.
  • a trigger signal that triggers the activation of the speech recognition device.
  • the voice recognition device 102 is configured to: after receiving the trigger signal sent by the voice wake-up device, start and monitor the second voice information in the second preset duration, and identify the first voice information buffered by the voice wake-up device. That is, the second voice information that is monitored is obtained, and the recognition result is obtained.
  • the voice recognition device 102 automatically turns off when the trigger signal is not received again within a third preset duration after determining that the trigger signal is received.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the voice information is buffered by the voice wake-up device, so that the voice recognition device monitors the second voice information after the startup, and identifies the cached first voice information and the second voice information, thereby preventing the voice from being started after the wake-up.
  • the identification device starts to acquire the voice information, the partial voice information sent by the user before the voice recognition device is activated is lost.
  • the recording channel is started after the AP starts up; usually, the recording starts after the AP is started.
  • the DSP receives the wakeup information, it starts recording and buffering, and after the AP starts, it continues to record and obtain voice information, and then reads the voice information from the buffer of the DSP and the voice information obtained after the startup. Identification.
  • the DSP receives the wakeup information, it starts recording and buffering, and after the AP starts, it continues to record and obtain voice information, and then reads the voice information from the buffer of the DSP and the voice information obtained after the startup. Identification.
  • there is a time difference between the wake-up and the command word If the recording is started after the AP is started, only the voice information after the start can be recorded. The voice information of the above time difference is lost, and the recording starts when the wake-up is started. Cache so that the voice information of the above time difference can be obtained.
  • the time point at which the wake-up word is started is t0
  • the time point at which the wake-up word is finished is t1
  • the time point at which the command word is started is t2
  • the time point at which the AP is started is t3
  • the time t0 to t3 is stored.
  • Voice if you only record when you start the AP, you can only record the voice after t3; the voice from t0 to t3 cannot be recorded. Therefore, the solution provided by the embodiment of the present invention can obtain the voice information from the voice information for waking up, and avoids the loss of the voice information, thereby providing a voice recognition rate.
  • determining that the monitored voice information matches the voice wakeup model may be performed by:
  • the user can preset the wake-up voice information according to the prompt in the voice wake-up device, for example: Hi, small E. Or the preset wake-up voice information when the terminal is shipped from the factory.
  • the voice wake-up device detects the voice information in the surrounding environment, it compares it with the stored wake-up voice information, if the two are the same, it determines to match the voice wake-up model, and then sends a trigger command to the voice recognition device 102; Differently, the voice wake-up device 101 can discard the currently detected voice information and continue the work of detecting and judging.
  • the voiceprint feature includes one or more of the following features:
  • the setting device may be further included, and the voiceprint feature of the user is pre-extracted and saved in the voice wake-up device.
  • the user can record the voice information according to the prompt inside the setting module, then extract the voiceprint feature, and save the extracted voiceprint feature in the voice wake-up device.
  • the voice pattern is added to the wake-up model, so that the noise in the surrounding environment and the voice input of other users can be filtered, so that the voice wake-up device provides a reliable guarantee for the user.
  • the method further includes:
  • the voice recognition device matches the acquired recognition result with pre-stored voice instruction information; the voice recognition device controls an operation corresponding to the executed voice instruction information.
  • the voice command information is stored in advance in the voice recognition device.
  • the voice recognition device includes a plurality of voice command information.
  • the execution module of the operation corresponding to the voice instruction information may be further, and the voice recognition device may send the execution instruction to the execution module of the operation corresponding to the voice instruction information.
  • Examples include: speakers or lighting devices, and the like.
  • the voice waking module detects that the voice information in the surrounding environment satisfies the awake model
  • the first voice information of the first predetermined duration for example, 2S
  • the voice recognition module is triggered to start and listen to the second voice information, and then
  • the cached first voice information and the second voice information are identified, and the recognition result is fuzzyly compared with the voice command information to determine whether the voice information matches one of the voice command information.
  • the voice instruction information includes voice command information indicating a play ring tone or MP3, such as "play ring tone” or “play MP3”; may also include voice command information indicating a response, such as "Where are you?"; may also include Indicates the voice command information that illuminates the flash, such as “Turn on the flash”.
  • the terminal device such as a mobile phone
  • a mobile phone can be found by using the solution provided by the embodiment of the present invention.
  • mobile phones are usually placed at random, and it takes a while to find them when they need to be used.
  • the voice wakeup module of the mobile phone detects the voice information, and then the voice information is compared with the voice wakeup model. Matching (such as waking up the voice message to "Hello, Small E"), when the match is determined, the voice information is cached in the Buffer.
  • the voice recognition module starts and starts to monitor the voice information, and then recognizes the buffered voice information and the monitored voice information to obtain a recognition result (the text result is "Hello, little E, you are at Where"), and the text result is matched with the voice command information.
  • the voice command information matching the "Hello, Little E, Where are you” is to play MP3, and the user is prompted by playing MP3 music.
  • the embodiment of the invention further provides a voice recognition method, as shown in FIG. 2, the method includes:
  • Step 201 the voice wake-up device monitors voice information in the surrounding environment
  • Step 202 The voice wake-up device determines that the monitored voice information matches the voice wake-up model, buffers the monitored first preset duration voice information, and sends a trigger signal that triggers the voice recognition device to start.
  • the trigger signal is used to instruct the voice recognition device to read and recognize the voice information buffered by the voice wake device after being activated.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the voice recognition device starts and monitors the voice information, and then identifies the buffered voice information and the monitored voice information, thereby avoiding starting the voice recognition device after waking up and then starting to acquire the voice.
  • some voice information may be lost, and the speech recognition rate is improved.
  • the determining that the monitored voice information matches the voice wakeup model may be specifically performed by:
  • An embodiment of the present invention further provides a voice recognition method, as shown in FIG. 3, including:
  • Step 301 The voice recognition device receives a trigger signal sent by the voice wake-up device, where the trigger signal is used to instruct the voice recognition device to activate and identify the first voice information buffered by the voice wake-up device.
  • Step 302 After receiving the trigger signal, the voice recognition device starts and monitors the second voice information of the second preset duration.
  • Step 303 Identify the first voice information buffered by the voice wake-up device and the second voice information that is monitored, to obtain a recognition result.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the voice recognition device activates and monitors the voice information, and identifies the buffered voice information and the monitored voice information, thereby avoiding starting the voice recognition device after waking up and then starting to acquire the voice information. At the time, some voice information may be lost, and the voice recognition rate is provided.
  • the method further includes:
  • the voice recognition device matches the acquired recognition result with pre-stored voice instruction information
  • the voice recognition device controls an operation corresponding to execution of the matched voice instruction information.
  • the voice recognition device automatically turns off when the trigger signal is not received again within a third preset time period after receiving the trigger signal.
  • the embodiment of the invention further provides a voice recognition method, as shown in FIG. 4, the method includes:
  • Step 401 the voice wake-up device monitors voice information in the surrounding environment
  • Step 402 When the voice wake-up device determines that the monitored voice information matches the voice wake-up model, A trigger signal is generated that triggers the activation of the speech recognition device.
  • the determining that the monitored voice information matches the voice wakeup model may be specifically performed by:
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the voice recognition device activates and monitors the voice information, and identifies the buffered voice information and the monitored voice information, thereby avoiding starting the voice recognition device after waking up and then starting to acquire the voice information. At the time, some voice information may be lost, and the voice recognition rate is provided.
  • An embodiment of the present invention further provides a voice recognition method, as shown in FIG. 5, including:
  • Step 501 The voice recognition device receives a trigger signal sent by the voice wake-up device.
  • Step 502 After receiving the trigger signal, the voice recognition device starts and sends a voice prompt instruction to the user.
  • Step 503 The voice recognition device records a voice signal input by the user according to the voice prompt instruction, and identifies the voice signal to obtain a recognition result.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the method further includes:
  • the voice recognition device compares the obtained recognition result with the pre-stored voice instruction information Match
  • the voice recognition device controls an operation corresponding to execution of the matched voice instruction information.
  • the embodiment of the invention further provides a voice wake-up device, as shown in FIG. 6, the device includes:
  • the monitoring module 601 is configured to listen to voice information in the surrounding environment
  • the determining module 602 is configured to determine whether the voice information monitored by the monitoring module 601 matches the voice wakeup model
  • the cache module 603 is configured to cache the voice information of the first preset duration monitored by the monitoring module 601 when the determining module 602 determines that the voice information monitored by the monitoring module 601 matches the voice wakeup model;
  • the sending module 604 is configured to send a trigger signal that triggers the activation of the voice recognition device, and the trigger signal is used to instruct the voice recognition device to read and identify the voice information buffered by the voice wake device.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the voice recognition device activates and monitors the voice information, and identifies the buffered voice information and the monitored voice information, thereby avoiding starting the voice recognition device after waking up and then starting to acquire the voice information. At the time, some voice information may be lost, and the voice recognition rate is provided.
  • the determining module 602 is configured to determine that the monitored voice information matches the predetermined wake-up voice information, and then determine that the monitored voice information matches the voice wake-up model.
  • the device further includes:
  • An extracting module configured to extract a voiceprint feature in the monitored voice signal when the determining module 602 determines that the monitored voice information matches the predetermined wake-up voice information
  • the determining module 602 is further configured to: when it is determined that the voiceprint feature extracted by the extraction module matches a predetermined voiceprint feature, determine that the monitored voice information matches the voice wakeup model.
  • the embodiment of the invention further provides a voice recognition device. As shown in FIG. 7, the device includes:
  • the receiving module 701 is configured to receive a trigger signal sent by the voice wake-up device, where the trigger signal is used And indicating to the voice recognition device to activate and identify the first voice information buffered by the voice wake device;
  • the monitoring module 702 is configured to start and monitor the second voice information of the second preset duration after the receiving module 701 receives the trigger signal;
  • the identification module 703 is configured to identify the first voice information buffered by the voice wake-up device and the second voice information that is monitored by the monitoring module, to obtain a recognition result.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the device further includes:
  • a matching module configured to match the recognition result obtained by the identification module 703 with the pre-stored voice instruction information
  • An execution module is configured to perform an operation corresponding to the matched voice instruction information.
  • the device further includes:
  • a closing module configured to close the voice recognition module when the trigger signal is not received again within a third preset duration after the receiving module receives the trigger signal.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the voice recognition device activates and monitors the voice information, and identifies the buffered voice information and the monitored voice information, thereby avoiding starting the voice recognition device after waking up and then starting to acquire the voice information. At the time, some voice information may be lost, and the voice recognition rate is provided.
  • the embodiment of the invention further provides a voice wake-up device, as shown in FIG. 8, the device includes:
  • the monitoring module 801 is configured to listen to voice information in the surrounding environment
  • a determining module 802 configured to determine whether the monitored voice information matches the voice wakeup model
  • the sending module 803 is configured to, when the determining module 802 determines that the monitored voice information matches the voice wake-up model, issue a trigger signal that triggers the voice recognition device to be activated.
  • the determining module 802 is configured to determine that the monitored voice information matches the predetermined wake-up voice information, and then determine that the monitored voice information matches the voice wake-up model.
  • the device further includes:
  • An extracting module configured to: when the determining module 802 determines that the monitored voice information matches the predetermined wake-up voice information, extract the voiceprint feature in the monitored voice signal;
  • the determining module 802 is specifically configured to determine that the extracted voiceprint feature matches the predetermined voiceprint feature, and then determine that the monitored voice information matches the voice wakeup model.
  • the embodiment of the invention provides a voice recognition device. As shown in FIG. 9, the device includes:
  • the receiving module 901 is configured to receive a trigger signal sent by the voice wake-up device.
  • the sending module 902 is configured to start and send a voice prompting instruction to the user after the receiving module 901 receives the trigger signal;
  • the processing module 903 is configured to record a voice signal input by the user according to the voice prompt instruction, and identify the voice signal to obtain a recognition result.
  • the user only needs to issue an instruction once, and can meet the requirements of the user, and is applicable regardless of whether the terminal is in standby or non-standby state.
  • the speech recognition module can be divided into a driver layer, an audio hardware abstraction layer (Audio HAL), a framework layer (Framework), a speech recognition engine (VA Service), and an application setting (Setting).
  • Audio HAL audio hardware abstraction layer
  • framework layer Framework
  • VA Service speech recognition engine
  • Setting an application setting
  • P1 The event is reported. Specifically, the driver layer receives the trigger signal of the DSP, and reports the trigger event to the framework.
  • P2 The event is reported. Specifically, the audio HAL reports the above trigger event to the VA Service.
  • P3 Parameter setting. Specifically, set the data to be read from the buffer.
  • P5 The VA Service sends a startup recording indication to the Framework.
  • the Framework After receiving the start recording instruction, the Framework sends a command to read audio data to the Audio HAL.
  • the Audio HAL starts reading the Buffer data after receiving the instruction to read the audio data sent by the Framework.
  • Audio HAL sends a Buffer data command to the driver to send the driver to the DSP. Get the Buffer data instruction, then the DSP sends the Buffer data to the driver.
  • P9 The driver reports the received Buffer data to the VA Service.
  • the VA Service identifies and processes the Buffer data and the recorded data.
  • P11 The VA Service sends a stop recording indication to the Framework.
  • the Framework After receiving the stop recording instruction, the Framework sends a command to stop reading the audio data to the Audio HAL.
  • the Audio HAL closes the read Buffer data after receiving the instruction to stop reading the audio data sent by the Framework.
  • the Audio HAL sends a stop to acquire the Buffer data command to the driver.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device. Having a series of operational steps performed on a computer or other programmable device to produce computer-implemented processing such that instructions executed on a computer or other programmable device are provided for implementing one or more processes and/or block diagrams in the flowchart. The steps of a function specified in a box or multiple boxes.

Abstract

本发明实施例提供一种语音识别方法及终端，用户仅需发出一次指令，就能满足用户的要求，不再需要触摸屏的辅助，也不需要多次输入指令。该方法包括：语音唤醒装置监听周围环境中的语音信息；所述语音唤醒装置确定监听到的语音信息与语音唤醒模型匹配时，将监听到的第一预设时长的语音信息缓存，并发送触发启动语音识别装置的触发信号，所述触发信号用于指示所述语音识别装置启动后读取并识别所述语音唤醒装置缓存的语音信息。语音识别装置接收语音唤醒装置发送的触发信号；所述语音识别装置在接收到所述触发信号后，启动并监听第二预设时长的第二语音信息；识别所述语音唤醒装置缓存的第一语音信息以及监听到的第二语音信息，得到识别结果。

Description

语音识别方法、语音唤醒装置、语音识别装置及终端 技术领域
本发明涉及移动通信技术领域，尤其涉及一种语音识别方法、语音唤醒装置、语音识别装置及终端。
背景技术
目前，随着移动手持终端，特别是移动手机普及性越来越高，触摸屏技术也越来越成熟。触摸屏技术尽管方便了用户的操作，但是在进行电话交互时，需要触摸多个步骤才能完成，在开车或者不方便触摸的时候，可能错过接听电话。
因此，基于语音识别技术打电话或者发短信等功能随之产生。并且现在语音识别作为一种新的、重要的用户交互技术在移动终端中的应用越来越广泛。
但是现有无论是通过语音识别技术打电话或者发短信等等业务，需要与触摸屏技术配合，才能实现。
发明内容
本发明实施例提供一种语音识别方法、语音唤醒装置、语音识别装置及终端，用户仅需发出一次指令，就能满足用户的要求，不再需要触摸屏的辅助，也不需要多次输入指令。
第一方面，本发明实施例提供了一种语音识别方法，该方法包括：
语音唤醒装置监听周围环境中的语音信息；
所述语音唤醒装置确定监听到的语音信息与语音唤醒模型匹配时，将监听到的第一预设时长的语音信息缓存，并发送触发启动语音识别装置的触发信号，所述触发信号用于指示所述语音识别装置启动后读取并识别所述语音唤醒装置缓存的语音信息。
结合第一方面，在第一方面的第一种可能的实现方式中，所述确定监听到的语音信息与语音唤醒模型匹配，包括：
确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
结合第一方面，在第一方面的第二种可能的实现方式中，所述确定监听到的语音信息与语音唤醒模型匹配，包括：
确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征，确定提取到的声纹特征与预定的声纹特征匹配，则确定监听到的语音信息与语音唤醒模型匹配。
第二方面，本发明实施例提供了一种语音识别方法，该方法包括：
语音识别装置接收语音唤醒装置发送的触发信号，所述触发信号用于指示所述语音识别装置启动并识别所述语音唤醒装置缓存的第一语音信息；
所述语音识别装置在接收到所述触发信号后，启动并监听第二预设时长的第二语音信息；
识别所述语音唤醒装置缓存的第一语音信息以及监听到的第二语音信息，得到识别结果。
结合第二方面，在第二方面的第一种可能的实现方式中，所述语音识别装置获取到识别结果后，还包括：
所述语音识别装置将获取到的识别结果与预存储的语音指令信息进行匹配；
所述语音识别装置执行匹配的语音指令信息对应的操作。
结合第二方面或第二方面的第一种可能的实现方式，在第二方面的第二种可能的实现方式中，还包括：
所述语音识别装置在确定接收到所述触发信号后第三预设时长内未再次接收到所述触发信号时，自动关闭。
第三方面，本发明实施例提供了一种语音识别方法，该方法包括：
语音唤醒装置监听周围环境中的语音信息；
语音唤醒装置确定监听到的语音信息与语音唤醒模型匹配时，发出触发启动语音识别装置的触发信号。
结合第三方面，在第三方面的第一种可能的实现方式中，所述确定监听到的语音信息与语音唤醒模型匹配，包括：
确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
结合第三方面，在第三方面的第二种可能的实现方式中，所述确定监听到的语音信息与语音唤醒模型匹配，包括：
确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征，确定提取到的声纹特征与预定的声纹特征匹配，则确定监听到的语音信息与语音唤醒模型匹配。
第四方面，本发明实施例提供了一种语音识别方法，该方法包括：
语音识别装置接收语音唤醒装置发送的触发信号；
所述语音识别装置在接收到所述触发信号后，启动并向用户发送语音提示指令；
所述语音识别装置记录用户根据所述语音提示指令输入的语音信号，并对所述语音信号进行识别，得到识别结果。
第五方面，本发明实施例还提供了一种语音唤醒装置，该装置包括：
监听模块，用于监听周围环境中的语音信息；
确定模块，用于确定所述监听模块监听到的语音信息是否与语音唤醒模型匹配；
缓存模块，用于在所述确定模块确定所述监听模块监听到的语音信息与语音唤醒模型匹配时，将所述监听模块监听到的第一预设时长的语音信息缓存；
发送模块，用于发送触发启动语音识别装置的触发信号，所述触发信号用于指示所述语音识别装置启动后读取并识别所述语音唤醒装置缓存的语音信息。
结合第五方面，在第五方面的第一种可能的实现方式中，所述确定模块，具体用于确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
结合第五方面，在第五方面的第二种可能的实现方式中，还包括：
提取模块，用于在所述确定模块确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征；
所述确定模块，还用于在确定所述提取模块提取到的声纹特征与预定的声纹特征匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
第六方面，本发明实施例提供了一种语音识别装置，包括：
接收模块，用于接收语音唤醒装置发送的触发信号，所述触发信号用于指示语音识别装置启动并识别所述语音唤醒装置缓存的第一语音信息；
监听模块，用于在所述接收模块接收到所述触发信号后，启动并监听第二预设时长的第二语音信息；
识别模块，用于识别所述语音唤醒装置缓存的第一语音信息以及所述监听模块监听到的第二语音信息，得到识别结果。
结合第六方面，在第六方面的第一种可能的实现方式中，还包括：
匹配模块，用于将识别模块识别后得到的识别结果与预存储的语音指令信息进行匹配；
执行模块，用于执行匹配的语音指令信息对应的操作。
结合第六方面或第六方面的第一种可能的实现方式，在第六方面的第二种可能的实现方式中，还包括：
关闭模块，用于在确定接收到所述触发信号后第三预设时长内未再次接收到所述触发信号时，关闭语音识别模块。
第七方面，本发明实施例提供了一种语音唤醒装置，包括：
监听模块，用于监听周围环境中的语音信息；
确定模块，用于确定监听到的语音信息是否与语音唤醒模型匹配；
发送模块，用于在所述确定模块确定监听到的语音信息与语音唤醒模型 匹配时，发出触发启动语音识别装置的触发信号。
结合第七方面，在第七方面的第一种可能的实现方式中，所述确定模块，具体用于确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
结合第七方面，在第七方面的第二种可能的实现方式中，还包括：
提取模块，用于在所述确定模块确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征；
所述确定模块，具体用于确定提取到的声纹特征与预定的声纹特征匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
第八方面，本发明实施例提供了一种语音识别装置，包括：
接收模块，用于接收语音唤醒装置发送的触发信号；
发送模块，用于在所述接收模块接收到所述触发信号后，启动并向用户发送语音提示指令；
处理模块，用于记录用户根据所述语音提示指令输入的语音信号，并对所述语音信号进行识别，得到识别结果。
第九方面，本发明实施例提供了一种终端，包括：
语音唤醒装置及语音识别装置；
所述语音唤醒装置，用于监听周围环境中的语音信息；确定监听到的语音信息与语音唤醒模型匹配时，将第一预设时长内监听到的第一语音信息缓存，并发出触发启动语音识别装置的触发信号；
所述语音识别装置，用于在接收到所述语音唤醒装置发送的触发信号后，启动并监听第二预设时长内的第二语音信息，识别所述语音唤醒装置缓存的第一语音信息及监听到的第二语音信息，得到识别结果。
结合第九方面，在第九方面的第一种可能的实现方式中，所述语音唤醒装置为数字信号处理器DSP。
结合第九方面或第九方面的第一种可能的实现方式，在第九方面的第二种可能的实现方式中，所述语音识别装置为应用处理器AP。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。并且通过语音唤醒装置将监听到的语音信息进行缓存，使得语音识别装置在启动后监听第二语音信息，对缓存的第一语音信息以及第二语音信息进行识别，从而能够避免在唤醒后启动语音识别装置再开始获取语音信息时，使得在语音识别装置启动前用户发出的部分语音信息丢失。
附图说明
图1为本发明实施例提供的终端结构示意图；
图2为本发明实施例提供的一种语音识别方法流程图；
图3为本发明实施例提供的另一种语音识别方法流程图；
图4为本发明实施例提供的又一种语音识别方法流程图；
图5为本发明实施例提供的再一种语音识别方法流程图；
图6为本发明实施例提供的一种语音唤醒装置示意图；
图7为本发明实施例提供的一种语音识别装置示意图；
图8为本发明实施例提供的另一种语音唤醒装置示意图；
图9为本发明实施例提供的另一种语音识别装置示意图；
图10为本发明实施例提供的语音识别方法示意图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
本发明实施例提供一种语音识别方法、语音唤醒装置、语音识别装置及终端，用户仅需发出一次指令，就能满足用户的要求，不再需要触摸屏的辅 助，也不需要多次输入指令。其中，方法、装置是基于同一发明构思的，由于方法、装置解决问题的原理相似，因此终端、装置与方法的实施可以相互参见，重复之处不再赘述。
本发明实施例中提供了一种终端，如图1所示，该终端包括语音唤醒装置101及语音识别装置102。
其中，语音唤醒装置101可以由数字信号处理器(Digital Signal Processor，简称DSP)实现。语音识别装置102可以由应用处理器(Application Processor，简称AP)实现。语音识别装置102还可以由中央处理器(Central Process Unit，简称CPU)实现。
所述语音唤醒装置101，用于监听周围环境中的语音信息；确定监听到的语音信息与语音唤醒模型匹配时，将第一预设时长内所述监听到的第一语音信息缓存，并发出触发启动语音识别装置的触发信号。
所述语音识别装置102，用于在接收到所述语音唤醒装置发送的触发信号后，启动并监听第二预设时长内的第二语音信息，识别所述语音唤醒装置缓存的第一语音信息即监听到的第二语音信息，得到识别结果。
可选地，所述语音识别装置102在确定接收到所述触发信号后第三预设时长内未再次接收到触发信号时，则自动关闭。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。并且通过语音唤醒装置将监听到的语音信息进行缓存，使得语音识别装置在启动后监听第二语音信息，对缓存的第一语音信息以及第二语音信息进行识别，从而能够避免在唤醒后启动语音识别装置再开始获取语音信息时，使得在语音识别装置启动前用户发出的部分语音信息丢失。
具体的，一般DSP在发起触发信号后，AP启动后就启动录音通路录音；通常，这个录音是在AP启动后才开始的。但是在本方案中，启动AP前，DSP接收到唤醒信息时，开始录音并缓存，AP启动后继续录音得到语音信息，然后对从DSP的缓存中读取语音信息以及启动后得到的语音信息进行识别。在 One Shot场景中，唤醒后到说命令词期间，存在一个时间差，如果从AP启动后录音，只能录到启动后的语音信息，上述时间差的语音信息就丢失，而在唤醒时即开始录音并缓存，从而上述时间差的语音信息都能够获取到。
例如，开始说唤醒词的时间点为t0，说完唤醒词的时间点为t1，开始说命令词的时间点为t2，启动AP的时间点为t3；在缓存中，存有t0到t3的语音；而如果只在启动AP的时候录音，则只能录到t3后的语音；t0到t3的语音就不能录制。因此，本发明实施例提供的方案从用于唤醒的语音信息开始后语音信息均能获取到，避免了语音信息的丢失，从而提供了语音识别率。
可选地，确定监听到的语音信息与语音唤醒模型匹配，具体可以通过以下方式：
第一种实现方式：
确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
其中，用户可以预先在语音唤醒装置中根据提示设置唤醒语音信息，例如：Hi，小E。或者终端在出厂时，预设了的唤醒语音信息。当语音唤醒装置检测到周围环境中的语音信息时，将其与存储的唤醒语音信息进行比对，若两者相同则确定与语音唤醒模型匹配，然后发送触发指令到语音识别装置102；如果两者不相同，语音唤醒装置101可以丢弃当前检测到的语音信息，并继续执行检测及判断的工作。
第二种实现方式：
确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征，确定提取到的声纹特征与预定的声纹特征匹配，则确定监听到的语音信息与语音唤醒模型匹配。
所述声纹特征包括以下特征中的一项或者多项：
基音轮廓、线性预测系数、谱包络参数、谐波能量比、共振峰频率及其带宽、倒谱(又称功率倒频谱)、Mel频率倒谱系数(Mel Frequency Cepstrum Coefficient，简称MFCC)等反映声纹特征的声学参数，且不限于前述所提及 的声纹特征参数。
其中，本发明实施例中还可以包括设置装置，预先提取用户的声纹特征保存在语音唤醒装置中。例如用户可以根据提示录制语音信息在设置模块内部，然后提取声纹特征，并将提取的声纹特征保存在语音唤醒装置中。
利用本发明实施例提供的方案，在唤醒模型增加声纹特征，从而能够过滤周围环境中的噪声，以及其它用户的语音输入，使得语音唤醒装置给用户提供了一个可靠的保障。
可选地，所述语音识别装置获取到识别结果后，还包括：
所述语音识别装置将获取到的识别结果与预存储的语音指令信息进行匹配；所述语音识别装置控制执行匹配的语音指令信息对应的操作。
其中，语音指令信息预先存储在语音识别装置中。语音识别装置包括多种语音指令信息。
本发明实施例中还可以语音指令信息对应的操作的执行模块，则语音识别装置可以向语音指令信息对应的操作的执行模块发送执行指令。比如包括：扬声器或者发光装置等等。
例如，当语音唤醒模块检测到周围环境中的语音信息满足唤醒模型时，将第一预定时长(例如2S)的第一语音信息缓存，并触发语音识别模块启动及监听第二语音信息，然后对缓存的第一语音信息及第二语音信息进行识别，将识别结果与语音指令信息进行模糊比对，确定语音信息是否与语音指令信息中其中一个匹配。例如，语音指令信息包括指示播放铃音或MP3的语音指令信息，如“播放铃音”或“播放MP3”；还可以包括指示应答的语音指令信息，如“你在哪？”；还可以包括指示点亮闪光灯的语音指令信息，如“开启闪光灯”。
可以利用本发明实施例提供的方案找终端设备，例如手机。在家里，一般手机随便放置，在需要使用的时候需要费一番工夫才能找到。利用本发明实施例提供的方案，可以通过喊出例如“你好，小E，你在哪里”，则手机的语音唤醒模块则检测到该语音信息，则将该语音信息与语音唤醒模型进行匹 配(比如唤醒语音信息为“你好，小E”)，确定匹配时，将该语音信息缓存在Buffer中。并向语音识别模块发送触发信号，则语音识别模块启动并开始监听语音信息，然后对缓存的语音信息及监听的语音信息进行识别，得到识别结果(文本结果为“你好，小E，你在哪里”)，并将该文本结果与语音指令信息进行匹配，例如，匹配该“你好，小E，你在哪里”的语音指令信息是播放MP3，则通过播放MP3音乐提示用户。
还可以通过本发明实施例提供的方案打电话。由于无论是待机状态还可以锁屏状态，手机的语音唤醒模块均处于启动状态，则均可以监听到用户发出的语音信息。例如：“你好，小E，打电话给小A”。则能直接拨出电话，不需要其他任何操作。
本发明实施例还提供了一种语音识别方法，如图2所示，该方法包括：
步骤201，语音唤醒装置监听周围环境中的语音信息；
步骤202，所述语音唤醒装置确定监听到的语音信息与语音唤醒模型匹配时，将所述监听到的第一预设时长的语音信息缓存，并发送触发启动语音识别装置的触发信号，所述触发信号用于指示所述语音识别装置启动后读取并识别所述语音唤醒装置缓存的语音信息。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。并且通过将监听到的语音信息进行缓存，使得语音识别装置启动并监听语音信息后，然后对缓存的语音信息以及监听的语音信息进行识别，从而能够避免在唤醒后启动语音识别装置再开始获取语音信息时，可能会造成部分语音信息丢失，提高了语音识别率。
可选地，所述确定监听到的语音信息与语音唤醒模型匹配，具体可以通过以下方式：
第一种实现方式：
确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
第二种实现方式：
确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征，确定提取到的声纹特征与预定的声纹特征匹配，则确定监听到的语音信息与语音唤醒模型匹配。
本发明实施例还提供了一种语音识别方法，如图3所示，包括：
步骤301，语音识别装置接收语音唤醒装置发送的触发信号，所述触发信号用于指示所述语音识别装置启动并识别所述语音唤醒装置缓存的第一语音信息。
步骤302，所述语音识别装置在接收到所述触发信号后，启动并并监听第二预设时长的第二语音信息。
步骤303，识别所述语音唤醒装置缓存的第一语音信息以及监听到的第二语音信息，得到识别结果。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。并且通过将监听到的语音信息进行缓存，使得语音识别装置在启动并监听语音信息，对缓存的语音信息以及监听的语音信息进行识别，从而能够避免在唤醒后启动语音识别装置再开始获取语音信息时，可能会造成部分语音信息丢失，提供了语音识别率。
可选地，所述语音识别装置获取到识别结果后，还包括：
所述语音识别装置将获取到的识别结果与预存储的语音指令信息进行匹配；
所述语音识别装置控制执行匹配的语音指令信息对应的操作。
可选地，所述语音识别装置在确定接收到所述触发信号后第三预设时长内未再次接收到所述触发信号时，自动关闭。
本发明实施例还提供了一种语音识别方法，如图4所示，该方法包括：
步骤401，语音唤醒装置监听周围环境中的语音信息；
步骤402，语音唤醒装置确定监听到的语音信息与语音唤醒模型匹配时， 发出触发启动语音识别装置的触发信号。
可选地，所述确定监听到的语音信息与语音唤醒模型匹配，具体可以通过以下方式：
第一种实现方式：
确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
第二种实现方式：
确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征，确定提取到的声纹特征与预定的声纹特征匹配，则确定监听到的语音信息与语音唤醒模型匹配。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。并且通过将监听到的语音信息进行缓存，使得语音识别装置在启动并监听语音信息，对缓存的语音信息以及监听的语音信息进行识别，从而能够避免在唤醒后启动语音识别装置再开始获取语音信息时，可能会造成部分语音信息丢失，提供了语音识别率。
本发明实施例还提供了一种语音识别方法，如图5所示，包括：
步骤501，语音识别装置接收语音唤醒装置发送的触发信号；
步骤502，所述语音识别装置在接收到所述触发信号后，启动并向用户发送语音提示指令；
步骤503，所述语音识别装置记录用户根据所述语音提示指令输入的语音信号，并对所述语音信号进行识别得到识别结果。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。
可选地，所述语音识别装置对所述语音信号进行识别得到识别结果后，还包括：
所述语音识别装置将得到的识别结果与预存储的语音指令信息进行匹 配；
所述语音识别装置控制执行匹配的语音指令信息对应的操作。
本发明实施例还提供了一种语音唤醒装置，如图6所示，该装置包括：
监听模块601，用于监听周围环境中的语音信息；
确定模块602，用于确定所述监听模块601监听到的语音信息是否与语音唤醒模型匹配；
缓存模块603，用于在所述确定模块602确定所述监听模块601监听到的语音信息与语音唤醒模型匹配时，将所述监听模块601监听到的第一预设时长的语音信息缓存；
发送模块604，用于发送触发启动语音识别装置的触发信号，所述触发信号用于指示所述语音识别装置启动后读取并识别所述语音唤醒装置缓存的语音信息。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。并且通过将监听到的语音信息进行缓存，使得语音识别装置在启动并监听语音信息，对缓存的语音信息以及监听的语音信息进行识别，从而能够避免在唤醒后启动语音识别装置再开始获取语音信息时，可能会造成部分语音信息丢失，提供了语音识别率。
可选地，所述确定模块602，具体用于确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
可选地，该装置还包括：
提取模块，用于在所述确定模块602确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征；
所述确定模块602，还用于在确定所述提取模块提取到的声纹特征与预定的声纹特征匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
本发明实施例还提供了一种语音识别装置，如图7所示，该装置包括：
接收模块701，用于接收语音唤醒装置发送的触发信号，所述触发信号用 于指示语音识别装置启动并识别所述语音唤醒装置缓存的第一语音信息；
监听模块702，用于在所述接收模块701接收到所述触发信号后，启动并监听第二预设时长的第二语音信息；
识别模块703，用于识别所述语音唤醒装置缓存的第一语音信息以及所述监听模块监听到的第二语音信息，得到识别结果。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。
可选地，该装置还包括：
匹配模块，用于将识别模块703识别后得到的识别结果与预存储的语音指令信息进行匹配；
执行模块，用于执行匹配的语音指令信息对应的操作。
可选地，该装置还包括：
关闭模块，用于在确定所述接收模块接收到所述触发信号后第三预设时长内未再次接收到所述触发信号时，关闭语音识别模块。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。并且通过将监听到的语音信息进行缓存，使得语音识别装置在启动并监听语音信息，对缓存的语音信息以及监听的语音信息进行识别，从而能够避免在唤醒后启动语音识别装置再开始获取语音信息时，可能会造成部分语音信息丢失，提供了语音识别率。
本发明实施例还提供了一种语音唤醒装置，如图8所示，该装置包括：
监听模块801，用于监听周围环境中的语音信息；
确定模块802，用于确定监听到的语音信息是否与语音唤醒模型匹配；
发送模块803，用于在所述确定模块802确定监听到的语音信息与语音唤醒模型匹配时，发出触发启动语音识别装置的触发信号。
可选地，所述确定模块802，具体用于确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
可选地，该装置还包括：
提取模块，用于在所述确定模块802确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征；
所述确定模块802，具体用于确定提取到的声纹特征与预定的声纹特征匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
本发明实施例提供了一种语音识别装置，如图9所示，该装置包括：
接收模块901，用于接收语音唤醒装置发送的触发信号；
发送模块902，用于在所述接收模块901接收到所述触发信号后，启动并向用户发送语音提示指令；
处理模块903，用于记录用户根据所述语音提示指令输入的语音信号，并对所述语音信号进行识别，得到识别结果。
利用本发明实施例提供的方案，用户只需要发出一次指令，就能满足用户的要求，并且无论终端处于待机还是非待机状态下均适用。
下面结合软件实现过程对本发明实施例作具体说明，如图10所示。
语音识别模块从软件上可以划分为驱动层、音频的硬件抽象层(Audio HAL)、框架层(Framework)、语音识别引擎(VA Service)和应用设置(Setting)。
P1：事件上报。具体的，驱动层在接收到DSP的触发信号，将该触发事件上报给Framework。
P2：事件上报。具体的，Audio HAL将上述触发事件上报给VA Service。
P3：参数设置。具体的，设置从buffer中读取数据。
P4：VA Service启动。
P5：VA Service向Framework发送启动录音指示。
P6：Framework在接收到启动录音指示后，向Audio HAL发送读取音频数据指令。
P7：Audio HAL在接收到Framework发送的读取音频数据指示后，启动读取Buffer数据。
P8：Audio HAL向驱动发送获取Buffer数据指令，以使驱动向DSP发送 获取Buffer数据指令，然后DSP将Buffer数据发送给驱动。
P9：驱动将接收到的Buffer数据上报给VA Service。
P10：VA Service对Buffer数据以及录音数据进行识别处理。
P11：VA Service向Framework发送停止录音指示。
P12：Framework在接收到停止录音指示后，向Audio HAL发送停止读取音频数据指令。
P13：Audio HAL在接收到Framework发送的停止读取音频数据指示后，关闭读取Buffer数据。
P14：Audio HAL向驱动发送停止获取Buffer数据指令。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上， 使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。
显然，本领域的技术人员可以对本发明实施例进行各种改动和变型而不脱离本发明实施例的精神和范围。这样，倘若本发明实施例的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。

Claims (23)

  1. 一种语音识别方法，其特征在于，包括：
    语音唤醒装置监听周围环境中的语音信息；
    所述语音唤醒装置确定监听到的语音信息与语音唤醒模型匹配时，将监听到的第一预设时长的语音信息缓存，并发送触发启动语音识别装置的触发信号，所述触发信号用于指示所述语音识别装置启动后读取并识别所述语音唤醒装置缓存的语音信息。
  2. 如权利要求1所述的方法，其特征在于，所述确定监听到的语音信息与语音唤醒模型匹配，包括：
    确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
  3. 如权利要求1所述的方法，其特征在于，所述确定监听到的语音信息与语音唤醒模型匹配，包括：
    确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征，确定提取到的声纹特征与预定的声纹特征匹配，则确定监听到的语音信息与语音唤醒模型匹配。
  4. 一种语音识别方法，其特征在于，包括：
    语音识别装置接收语音唤醒装置发送的触发信号，所述触发信号用于指示所述语音识别装置启动并识别所述语音唤醒装置缓存的第一语音信息；
    所述语音识别装置在接收到所述触发信号后，启动并监听第二预设时长的第二语音信息；
    识别所述语音唤醒装置缓存的第一语音信息以及监听到的第二语音信息，得到识别结果。
  5. 如权利要求4所述的方法，其特征在于，所述语音识别装置获取到识别结果后，还包括：
    所述语音识别装置将获取到的识别结果与预存储的语音指令信息进行匹 配；
    所述语音识别装置执行匹配的语音指令信息对应的操作。
  6. 如权利要求4或5所述的方法，其特征在于，还包括：
    所述语音识别装置在确定接收到所述触发信号后第三预设时长内未再次接收到所述触发信号时，自动关闭。
  7. 一种语音识别方法，其特征在于，包括：
    语音唤醒装置监听周围环境中的语音信息；
    语音唤醒装置确定监听到的语音信息与语音唤醒模型匹配时，发出触发启动语音识别装置的触发信号。
  8. 如权利要求7所述的方法，其特征在于，所述确定监听到的语音信息与语音唤醒模型匹配，包括：
    确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
  9. 如权利要求7所述的方法，其特征在于，所述确定监听到的语音信息与语音唤醒模型匹配，包括：
    确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征，确定提取到的声纹特征与预定的声纹特征匹配，则确定监听到的语音信息与语音唤醒模型匹配。
  10. 一种语音识别方法，其特征在于，包括：
    语音识别装置接收语音唤醒装置发送的触发信号；
    所述语音识别装置在接收到所述触发信号后，启动并向用户发送语音提示指令；
    所述语音识别装置记录用户根据所述语音提示指令输入的语音信号，并对所述语音信号进行识别，得到识别结果。
  11. 一种语音唤醒装置，其特征在于，包括：
    监听模块，用于监听周围环境中的语音信息；
    确定模块，用于确定所述监听模块监听到的语音信息是否与语音唤醒模 型匹配；
    缓存模块，用于在所述确定模块确定所述监听模块监听到的语音信息与语音唤醒模型匹配时，将所述监听模块监听到的第一预设时长的语音信息缓存；
    发送模块，用于发送触发启动语音识别装置的触发信号，所述触发信号用于指示所述语音识别装置启动后读取并识别所述语音唤醒装置缓存的语音信息。
  12. 如权利要求11所述的装置，其特征在于，所述确定模块，具体用于确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
  13. 如权利要求11所述的装置，其特征在于，还包括：
    提取模块，用于在所述确定模块确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征；
    所述确定模块，还用于在确定所述提取模块提取到的声纹特征与预定的声纹特征匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
  14. 一种语音识别装置，其特征在于，包括：
    接收模块，用于接收语音唤醒装置发送的触发信号，所述触发信号用于指示语音识别装置启动并识别所述语音唤醒装置缓存的第一语音信息；
    监听模块，用于在所述接收模块接收到所述触发信号后，启动并监听第二预设时长的第二语音信息；
    识别模块，用于识别所述语音唤醒装置缓存的第一语音信息以及所述监听模块监听到的第二语音信息，得到识别结果。
  15. 如权利要求14所述的装置，其特征在于，还包括：
    匹配模块，用于将识别模块识别后得到的识别结果与预存储的语音指令信息进行匹配；
    执行模块，用于执行匹配的语音指令信息对应的操作。
  16. 如权利要求14或15所述的装置，其特征在于，还包括：
    关闭模块，用于在确定接收到所述触发信号后第三预设时长内未再次接收到所述触发信号时，关闭语音识别模块。
  17. 一种语音唤醒装置，其特征在于，包括：
    监听模块，用于监听周围环境中的语音信息；
    确定模块，用于确定监听到的语音信息是否与语音唤醒模型匹配；
    发送模块，用于在所述确定模块确定监听到的语音信息与语音唤醒模型匹配时，发出触发启动语音识别装置的触发信号。
  18. 如权利要求17所述的装置，其特征在于，所述确定模块，具体用于确定监听到的语音信息与预定的唤醒语音信息匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
  19. 如权利要求17所述的装置，其特征在于，还包括：
    提取模块，用于在所述确定模块确定监听到的语音信息与预定的唤醒语音信息匹配时，提取监听到的语音信号中的声纹特征；
    所述确定模块，具体用于确定提取到的声纹特征与预定的声纹特征匹配时，则确定监听到的语音信息与语音唤醒模型匹配。
  20. 一种语音识别装置，其特征在于，包括：
    接收模块，用于接收语音唤醒装置发送的触发信号；
    发送模块，用于在所述接收模块接收到所述触发信号后，启动并向用户发送语音提示指令；
    处理模块，用于记录用户根据所述语音提示指令输入的语音信号，并对所述语音信号进行识别，得到识别结果。
  21. 一种终端，其特征在于，包括：
    语音唤醒装置及语音识别装置；
    所述语音唤醒装置，用于监听周围环境中的语音信息；确定监听到的语音信息与语音唤醒模型匹配时，将第一预设时长内监听到的第一语音信息缓存，并发出触发启动语音识别装置的触发信号；
    所述语音识别装置，用于在接收到所述语音唤醒装置发送的触发信号后， 启动并监听第二预设时长内的第二语音信息，识别所述语音唤醒装置缓存的第一语音信息及监听到的第二语音信息，得到识别结果。
  22. 如权利要求21所述的终端，其特征在于，所述语音唤醒装置为数字信号处理器DSP。
  23. 如权利要求21或22所述的终端，其特征在于，所述语音识别装置为应用处理器AP。
PCT/CN2015/076342 2015-04-10 2015-04-10 语音识别方法、语音唤醒装置、语音识别装置及终端 WO2016161641A1 (zh)

Priority Applications (11)

Application Number Priority Date Filing Date Title
BR112017021673-6A BR112017021673B1 (pt) 2015-04-10 2015-04-10 Método de controle de voz, meio não-transitório legível por computador e terminal
PCT/CN2015/076342 WO2016161641A1 (zh) 2015-04-10 2015-04-10 语音识别方法、语音唤醒装置、语音识别装置及终端
JP2017553159A JP6564058B2 (ja) 2015-04-10 2015-04-10 音声認識方法、音声ウェイクアップ装置、音声認識装置、および端末
CA2982196A CA2982196C (en) 2015-04-10 2015-04-10 Speech recognition method, speech wakeup apparatus, speech recognition apparatus, and terminal
CN201580023412.XA CN106463112B (zh) 2015-04-10 2015-04-10 语音识别方法、语音唤醒装置、语音识别装置及终端
EP15888197.9A EP3282445A4 (en) 2015-04-10 2015-04-10 Voice recognition method, voice wake-up device, voice recognition device and terminal
AU2015390534A AU2015390534B2 (en) 2015-04-10 2015-04-10 Speech recognition method, speech wakeup apparatus, speech recognition apparatus, and terminal
US15/729,097 US10943584B2 (en) 2015-04-10 2017-10-10 Speech recognition method, speech wakeup apparatus, speech recognition apparatus, and terminal
AU2019268131A AU2019268131A1 (en) 2015-04-10 2019-11-20 Speech recognition method, speech wakeup apparatus, speech recognition apparatus, and terminal
US17/178,009 US11783825B2 (en) 2015-04-10 2021-02-17 Speech recognition method, speech wakeup apparatus, speech recognition apparatus, and terminal
AU2021286393A AU2021286393B2 (en) 2015-04-10 2021-12-16 Speech recognition method, speech wakeup apparatus, speech recognition apparatus, and terminal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/076342 WO2016161641A1 (zh) 2015-04-10 2015-04-10 语音识别方法、语音唤醒装置、语音识别装置及终端

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/729,097 Continuation US10943584B2 (en) 2015-04-10 2017-10-10 Speech recognition method, speech wakeup apparatus, speech recognition apparatus, and terminal

Publications (1)

Publication Number Publication Date
WO2016161641A1 true WO2016161641A1 (zh) 2016-10-13

Family

ID=57071774

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/076342 WO2016161641A1 (zh) 2015-04-10 2015-04-10 语音识别方法、语音唤醒装置、语音识别装置及终端

Country Status (8)

Country Link
US (2) US10943584B2 (zh)
EP (1) EP3282445A4 (zh)
JP (1) JP6564058B2 (zh)
CN (1) CN106463112B (zh)
AU (3) AU2015390534B2 (zh)
BR (1) BR112017021673B1 (zh)
CA (1) CA2982196C (zh)
WO (1) WO2016161641A1 (zh)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109243462A (zh) * 2018-11-20 2019-01-18 广东小天才科技有限公司 一种语音唤醒方法及装置
CN109243447A (zh) * 2018-10-12 2019-01-18 西安蜂语信息科技有限公司 语音发送触发方法及装置
CN109545207A (zh) * 2018-11-16 2019-03-29 广东小天才科技有限公司 一种语音唤醒方法及装置
CN109979466A (zh) * 2019-03-21 2019-07-05 广州国音智能科技有限公司 一种声纹身份同一性鉴定方法、装置及计算机可读存储介质
JP2019185771A (ja) * 2018-03-30 2019-10-24 深▲せん▼市冠旭電子股▲ふん▼有限公司 ブルートゥーススピーカーデータ処理の方法、装置及びブルートゥーススピーカー
JP2020517977A (ja) * 2017-06-29 2020-06-18 アリババ グループ ホウルディング リミテッド 音声ウェイクアップ方法、装置及び電子デバイス
CN112363851A (zh) * 2020-10-28 2021-02-12 广东小天才科技有限公司 智能终端的语音唤醒方法、系统、智能手表及存储介质
US11037560B2 (en) 2018-04-02 2021-06-15 Baidu Online Network Technology (Beijing) Co., Ltd.X Method, apparatus and storage medium for wake up processing of application

Families Citing this family (85)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9318108B2 (en) 2010-01-18 2016-04-19 Apple Inc. Intelligent automated assistant
US8977255B2 (en) 2007-04-03 2015-03-10 Apple Inc. Method and system for operating a multi-function portable electronic device using voice-activation
US8676904B2 (en) 2008-10-02 2014-03-18 Apple Inc. Electronic devices with voice command and contextual data processing capabilities
US10255566B2 (en) 2011-06-03 2019-04-09 Apple Inc. Generating and processing task items that represent tasks to perform
US10417037B2 (en) 2012-05-15 2019-09-17 Apple Inc. Systems and methods for integrating third party services with a digital assistant
BR112015018905B1 (pt) 2013-02-07 2022-02-22 Apple Inc Método de operação de recurso de ativação por voz, mídia de armazenamento legível por computador e dispositivo eletrônico
US10652394B2 (en) 2013-03-14 2020-05-12 Apple Inc. System and method for processing voicemail
US10748529B1 (en) 2013-03-15 2020-08-18 Apple Inc. Voice activated device for use with a voice-based digital assistant
US10176167B2 (en) 2013-06-09 2019-01-08 Apple Inc. System and method for inferring user intent from speech inputs
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
CN106471570B (zh) 2014-05-30 2019-10-01 苹果公司 多命令单一话语输入方法
US10170123B2 (en) 2014-05-30 2019-01-01 Apple Inc. Intelligent assistant for home automation
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US10200824B2 (en) 2015-05-27 2019-02-05 Apple Inc. Systems and methods for proactively identifying and surfacing relevant content on a touch-sensitive device
US20160378747A1 (en) 2015-06-29 2016-12-29 Apple Inc. Virtual assistant for media playback
US10331312B2 (en) 2015-09-08 2019-06-25 Apple Inc. Intelligent automated assistant in a media environment
US10740384B2 (en) 2015-09-08 2020-08-11 Apple Inc. Intelligent automated assistant for media search and playback
US10747498B2 (en) 2015-09-08 2020-08-18 Apple Inc. Zero latency digital assistant
US10671428B2 (en) 2015-09-08 2020-06-02 Apple Inc. Distributed personal assistant
US10691473B2 (en) 2015-11-06 2020-06-23 Apple Inc. Intelligent automated assistant in a messaging environment
US10956666B2 (en) 2015-11-09 2021-03-23 Apple Inc. Unconventional virtual assistant interactions
US10223066B2 (en) 2015-12-23 2019-03-05 Apple Inc. Proactive assistance based on dialog communication between devices
US10586535B2 (en) 2016-06-10 2020-03-10 Apple Inc. Intelligent digital assistant in a multi-tasking environment
DK179415B1 (en) 2016-06-11 2018-06-14 Apple Inc Intelligent device arbitration and control
DK201670540A1 (en) 2016-06-11 2018-01-08 Apple Inc Application integration with a digital assistant
US10726832B2 (en) 2017-05-11 2020-07-28 Apple Inc. Maintaining privacy of personal information
DK180048B1 (en) 2017-05-11 2020-02-04 Apple Inc. MAINTAINING THE DATA PROTECTION OF PERSONAL INFORMATION
DK179496B1 (en) 2017-05-12 2019-01-15 Apple Inc. USER-SPECIFIC Acoustic Models
DK179745B1 (en) 2017-05-12 2019-05-01 Apple Inc. SYNCHRONIZATION AND TASK DELEGATION OF A DIGITAL ASSISTANT
DK201770427A1 (en) 2017-05-12 2018-12-20 Apple Inc. LOW-LATENCY INTELLIGENT AUTOMATED ASSISTANT
US20180336892A1 (en) 2017-05-16 2018-11-22 Apple Inc. Detecting a trigger of a digital assistant
US20180336275A1 (en) 2017-05-16 2018-11-22 Apple Inc. Intelligent automated assistant for media exploration
CN107181869A (zh) * 2017-06-06 2017-09-19 上海传英信息技术有限公司 移动终端和利用语音识别开启移动终端应用的方法
CN116364077A (zh) * 2017-07-04 2023-06-30 阿里巴巴集团控股有限公司 一种处理方法、控制方法、识别方法及其装置和电子设备
US11361763B1 (en) * 2017-09-01 2022-06-14 Amazon Technologies, Inc. Detecting system-directed speech
CN110800045A (zh) * 2017-10-24 2020-02-14 北京嘀嘀无限科技发展有限公司 用于不间断应用唤醒和语音识别的系统和方法
CN107808670B (zh) 2017-10-25 2021-05-14 百度在线网络技术（北京）有限公司 语音数据处理方法、装置、设备及存储介质
CN108062949A (zh) * 2017-12-11 2018-05-22 广州朗国电子科技有限公司 语音控制跑步机的方法及装置
WO2019169591A1 (zh) * 2018-03-07 2019-09-12 华为技术有限公司 一种语音交互的方法及装置
CN110299137B (zh) * 2018-03-22 2023-12-12 腾讯科技（深圳）有限公司 语音交互方法和装置
US10818288B2 (en) * 2018-03-26 2020-10-27 Apple Inc. Natural assistant interaction
CN108538291A (zh) * 2018-04-11 2018-09-14 百度在线网络技术（北京）有限公司 语音控制方法、终端设备、云端服务器及系统
EP3786945B1 (en) * 2018-04-12 2023-07-19 Spotify AB Voice-based authentication
US10928918B2 (en) 2018-05-07 2021-02-23 Apple Inc. Raise to speak
US11145294B2 (en) 2018-05-07 2021-10-12 Apple Inc. Intelligent automated assistant for delivering content from user experiences
CN108735210A (zh) * 2018-05-08 2018-11-02 宇龙计算机通信科技(深圳)有限公司 一种语音控制方法及终端
US10892996B2 (en) 2018-06-01 2021-01-12 Apple Inc. Variable latency device coordination
DK179822B1 (da) 2018-06-01 2019-07-12 Apple Inc. Voice interaction at a primary device to access call functionality of a companion device
DK180639B1 (en) 2018-06-01 2021-11-04 Apple Inc DISABILITY OF ATTENTION-ATTENTIVE VIRTUAL ASSISTANT
US10777196B2 (en) * 2018-06-27 2020-09-15 The Travelers Indemnity Company Systems and methods for cooperatively-overlapped and artificial intelligence managed interfaces
CN109215646B (zh) * 2018-08-15 2021-08-17 北京百度网讯科技有限公司 语音交互处理方法、装置、计算机设备及存储介质
CN110853632A (zh) * 2018-08-21 2020-02-28 蔚来汽车有限公司 基于声纹信息的语音识别方法及智能交互设备
CN109446533B (zh) * 2018-09-17 2020-12-22 深圳市沃特沃德股份有限公司 蓝牙翻译机、蓝牙翻译的交互方式及其装置
US11462215B2 (en) 2018-09-28 2022-10-04 Apple Inc. Multi-modal inputs for voice commands
JP7242248B2 (ja) * 2018-10-31 2023-03-20 キヤノン株式会社 電子機器、その制御方法、およびそのプログラム
CN109448720A (zh) * 2018-12-18 2019-03-08 维拓智能科技（深圳）有限公司 便民服务自助终端及其语音唤醒方法
CN111383633B (zh) * 2018-12-29 2023-08-01 深圳Tcl新技术有限公司 语音识别连续性控制方法、装置、智能终端及存储介质
CN109448725A (zh) * 2019-01-11 2019-03-08 百度在线网络技术（北京）有限公司 一种语音交互设备唤醒方法、装置、设备及存储介质
US11348573B2 (en) 2019-03-18 2022-05-31 Apple Inc. Multimodality in digital assistant systems
US11776538B1 (en) * 2019-04-01 2023-10-03 Dialog Semiconductor B.V. Signal processing
DK201970509A1 (en) 2019-05-06 2021-01-15 Apple Inc Spoken notifications
US11307752B2 (en) 2019-05-06 2022-04-19 Apple Inc. User configurable task triggers
CN110225386B (zh) * 2019-05-09 2021-09-14 海信视像科技股份有限公司 一种显示控制方法、显示设备
CN110232916A (zh) * 2019-05-10 2019-09-13 平安科技（深圳）有限公司 语音处理方法、装置、计算机设备及存储介质
US11140099B2 (en) 2019-05-21 2021-10-05 Apple Inc. Providing message response suggestions
US20200380139A1 (en) * 2019-05-29 2020-12-03 Denso International America, Inc. System and method for enhancing vehicle occupant voice data privacy
DK201970511A1 (en) 2019-05-31 2021-02-15 Apple Inc Voice identification in digital assistant systems
DK180129B1 (en) 2019-05-31 2020-06-02 Apple Inc. USER ACTIVITY SHORTCUT SUGGESTIONS
US11227599B2 (en) 2019-06-01 2022-01-18 Apple Inc. Methods and user interfaces for voice-based control of electronic devices
CN110223687B (zh) * 2019-06-03 2021-09-28 Oppo广东移动通信有限公司 指令执行方法、装置、存储介质及电子设备
CN112216277A (zh) * 2019-07-12 2021-01-12 Oppo广东移动通信有限公司 通过耳机进行语音识别的方法、耳机、语音识别装置
CN110265031A (zh) * 2019-07-25 2019-09-20 秒针信息技术有限公司 一种语音处理方法及装置
EP3792912B1 (en) * 2019-09-11 2021-11-03 Oracle International Corporation Improved wake-word recognition in low-power devices
CN111292510A (zh) * 2020-01-16 2020-06-16 广州华铭电力科技有限公司 一种城市电缆被外力破坏的识别预警方法
US11038934B1 (en) 2020-05-11 2021-06-15 Apple Inc. Digital assistant hardware abstraction
US11061543B1 (en) 2020-05-11 2021-07-13 Apple Inc. Providing relevant data items based on context
US11755276B2 (en) 2020-05-12 2023-09-12 Apple Inc. Reducing description length based on confidence
IT202000015973A1 (it) * 2020-07-02 2022-01-02 Voiceme S R L Sistema elettronico e metodo per abilitare il pagamento di un bene o servizio per mezzo di comandi vocali
US11490204B2 (en) 2020-07-20 2022-11-01 Apple Inc. Multi-device audio adjustment coordination
US11438683B2 (en) 2020-07-21 2022-09-06 Apple Inc. User identification using headphones
CN112037784B (zh) * 2020-08-14 2023-10-20 南京创维信息技术研究院有限公司 显示设备语音控制方法、显示设备和存储介质
CN112581956A (zh) * 2020-12-04 2021-03-30 海能达通信股份有限公司 一种双模终端的语音识别方法及双模终端
TWI765485B (zh) * 2020-12-21 2022-05-21 矽統科技股份有限公司 外接式語音喚醒裝置及其控制方法
CN114254076B (zh) * 2021-12-16 2023-03-07 天翼爱音乐文化科技有限公司 一种多媒体教学的音频处理方法、系统及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102905029A (zh) * 2012-10-17 2013-01-30 广东欧珀移动通信有限公司 一种手机及智能语音寻找手机的方法
CN103021413A (zh) * 2013-01-07 2013-04-03 北京播思软件技术有限公司 语音控制方法及装置
CN103095911A (zh) * 2012-12-18 2013-05-08 苏州思必驰信息科技有限公司 一种通过语音唤醒寻找手机的方法及系统
CN103338311A (zh) * 2013-07-11 2013-10-02 成都西可科技有限公司 一种智能手机锁屏界面启动app的方法
CN103594089A (zh) * 2013-11-18 2014-02-19 联想(北京)有限公司 一种语音识别方法及电子设备
CN103632667A (zh) * 2013-11-25 2014-03-12 华为技术有限公司 声学模型优化方法、装置及语音唤醒方法、装置和终端
US20140163978A1 (en) * 2012-12-11 2014-06-12 Amazon Technologies, Inc. Speech recognition power management
CN103929540A (zh) * 2014-04-25 2014-07-16 浙江翼信科技有限公司 一种消息操作方法及装置

Family Cites Families (71)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5774859A (en) * 1995-01-03 1998-06-30 Scientific-Atlanta, Inc. Information system having a speech interface
US5857172A (en) * 1995-07-31 1999-01-05 Microsoft Corporation Activation control of a speech recognizer through use of a pointing device
US20050091057A1 (en) * 1999-04-12 2005-04-28 General Magic, Inc. Voice application development methodology
US7725307B2 (en) * 1999-11-12 2010-05-25 Phoenix Solutions, Inc. Query engine for processing voice based queries including semantic decoding
US6591239B1 (en) * 1999-12-09 2003-07-08 Steris Inc. Voice controlled surgical suite
JP2004516517A (ja) * 2000-12-20 2004-06-03 コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ 発話による対話言語の設定
US7610199B2 (en) 2004-09-01 2009-10-27 Sri International Method and apparatus for obtaining complete speech signals for speech recognition applications
KR100690740B1 (ko) 2004-11-24 2007-03-09 엘지전자 주식회사 이동 통신 단말기의 슬립 모드 전환 방법
US20080140397A1 (en) * 2006-12-07 2008-06-12 Jonathan Travis Millman Sequencing for location determination
US8600741B2 (en) * 2008-08-20 2013-12-03 General Motors Llc Method of using microphone characteristics to optimize speech recognition performance
US9070282B2 (en) * 2009-01-30 2015-06-30 Altorr Corp. Smartphone control of electrical devices
KR20110031797A (ko) 2009-09-21 2011-03-29 삼성전자주식회사 휴대 단말기의 입력 장치 및 방법
US20110165541A1 (en) * 2010-01-02 2011-07-07 Yong Liu Reviewing a word in the playback of audio data
CN102196096A (zh) 2011-05-19 2011-09-21 青岛海信移动通信技术股份有限公司 一种移动终端执行特定操作的方法、移动终端及通信系统
US8768707B2 (en) * 2011-09-27 2014-07-01 Sensory Incorporated Background speech recognition assistant using speaker verification
US8452597B2 (en) * 2011-09-30 2013-05-28 Google Inc. Systems and methods for continual speech recognition and detection in mobile computing devices
US9992745B2 (en) 2011-11-01 2018-06-05 Qualcomm Incorporated Extraction and analysis of buffered audio data using multiple codec rates each greater than a low-power processor rate
US9117449B2 (en) * 2012-04-26 2015-08-25 Nuance Communications, Inc. Embedded system for construction of small footprint speech recognition with user-definable constraints
KR20130133629A (ko) * 2012-05-29 2013-12-09 삼성전자주식회사 전자장치에서 음성명령을 실행시키기 위한 장치 및 방법
US9646610B2 (en) * 2012-10-30 2017-05-09 Motorola Solutions, Inc. Method and apparatus for activating a particular wireless communication device to accept speech and/or voice commands using identification data consisting of speech, voice, image recognition
US9275637B1 (en) * 2012-11-06 2016-03-01 Amazon Technologies, Inc. Wake word evaluation
KR20140060040A (ko) * 2012-11-09 2014-05-19 삼성전자주식회사 디스플레이장치, 음성취득장치 및 그 음성인식방법
CN103871408B (zh) * 2012-12-14 2017-05-24 联想(北京)有限公司 一种语音识别方法及装置、电子设备
DE102013001219B4 (de) 2013-01-25 2019-08-29 Inodyn Newmedia Gmbh Verfahren und System zur Sprachaktivierung eines Software-Agenten aus einem Standby-Modus
US9818407B1 (en) * 2013-02-07 2017-11-14 Amazon Technologies, Inc. Distributed endpointing for speech recognition
BR112015018905B1 (pt) 2013-02-07 2022-02-22 Apple Inc Método de operação de recurso de ativação por voz, mídia de armazenamento legível por computador e dispositivo eletrônico
US9842489B2 (en) * 2013-02-14 2017-12-12 Google Llc Waking other devices for additional data
US20150348538A1 (en) * 2013-03-14 2015-12-03 Aliphcom Speech summary and action item generation
US9703350B2 (en) * 2013-03-15 2017-07-11 Maxim Integrated Products, Inc. Always-on low-power keyword spotting
WO2014144579A1 (en) * 2013-03-15 2014-09-18 Apple Inc. System and method for updating an adaptive speech recognition model
KR101505127B1 (ko) * 2013-03-15 2015-03-26 주식회사 팬택 음성 명령에 의한 오브젝트 실행 장치 및 방법
US9202463B2 (en) * 2013-04-01 2015-12-01 Zanavox Voice-activated precision timing
US20140358535A1 (en) 2013-05-28 2014-12-04 Samsung Electronics Co., Ltd. Method of executing voice recognition of electronic device and electronic device using the same
US20140358552A1 (en) * 2013-05-31 2014-12-04 Cirrus Logic, Inc. Low-power voice gate for device wake-up
US20140365225A1 (en) * 2013-06-05 2014-12-11 DSP Group Ultra-low-power adaptive, user independent, voice triggering schemes
JP2015011170A (ja) 2013-06-28 2015-01-19 株式会社ＡＴＲ−Ｔｒｅｋ ローカルな音声認識を行なう音声認識クライアント装置
US9445209B2 (en) * 2013-07-11 2016-09-13 Intel Corporation Mechanism and apparatus for seamless voice wake and speaker verification
US9548047B2 (en) * 2013-07-31 2017-01-17 Google Technology Holdings LLC Method and apparatus for evaluating trigger phrase enrollment
JP2015041123A (ja) * 2013-08-20 2015-03-02 株式会社リコー 画像形成装置
JP6312053B2 (ja) 2013-09-06 2018-04-18 株式会社ユピテル システム及びプログラム
US10134395B2 (en) 2013-09-25 2018-11-20 Amazon Technologies, Inc. In-call virtual assistants
US8775191B1 (en) * 2013-11-13 2014-07-08 Google Inc. Efficient utterance-specific endpointer triggering for always-on hotwording
CN103595869A (zh) * 2013-11-15 2014-02-19 华为终端有限公司 一种终端语音控制方法、装置及终端
US9443522B2 (en) 2013-11-18 2016-09-13 Beijing Lenovo Software Ltd. Voice recognition method, voice controlling method, information processing method, and electronic apparatus
CN104143326B (zh) * 2013-12-03 2016-11-02 腾讯科技（深圳）有限公司 一种语音命令识别方法和装置
US11138971B2 (en) * 2013-12-05 2021-10-05 Lenovo (Singapore) Pte. Ltd. Using context to interpret natural language speech recognition commands
GB2523984B (en) * 2013-12-18 2017-07-26 Cirrus Logic Int Semiconductor Ltd Processing received speech data
GB2524222B (en) * 2013-12-18 2018-07-18 Cirrus Logic Int Semiconductor Ltd Activating speech processing
US20150221307A1 (en) 2013-12-20 2015-08-06 Saurin Shah Transition from low power always listening mode to high power speech recognition mode
WO2015116151A1 (en) * 2014-01-31 2015-08-06 Hewlett-Packard Development Company, L.P. Voice input command
US20180108001A1 (en) * 2014-03-24 2018-04-19 Thomas Jason Taylor Voice triggered transactions
US20150302856A1 (en) * 2014-04-17 2015-10-22 Qualcomm Incorporated Method and apparatus for performing function by speech input
US10770075B2 (en) * 2014-04-21 2020-09-08 Qualcomm Incorporated Method and apparatus for activating application by speech input
US9466290B2 (en) * 2014-05-06 2016-10-11 Honeywell International Inc. Systems and methods for aviation communication monitoring using speech recognition
HUE039773T2 (hu) * 2014-06-11 2019-02-28 Huawei Tech Co Ltd Eljárás és terminál egy alkalmazás szolgáltatás gyorsindítására
KR102208477B1 (ko) * 2014-06-30 2021-01-27 삼성전자주식회사 마이크 운용 방법 및 이를 지원하는 전자 장치
US20160012827A1 (en) * 2014-07-10 2016-01-14 Cambridge Silicon Radio Limited Smart speakerphone
US20160055847A1 (en) * 2014-08-19 2016-02-25 Nuance Communications, Inc. System and method for speech validation
US9335966B2 (en) * 2014-09-11 2016-05-10 Nuance Communications, Inc. Methods and apparatus for unsupervised wakeup
US9354687B2 (en) * 2014-09-11 2016-05-31 Nuance Communications, Inc. Methods and apparatus for unsupervised wakeup with time-correlated acoustic events
US9582296B2 (en) * 2014-09-18 2017-02-28 International Business Machines Corporation Dynamic multi-user computer configuration settings
CN104301109B (zh) * 2014-09-24 2017-06-06 飞天诚信科技股份有限公司 一种语音动态令牌的工作方法
KR102299330B1 (ko) * 2014-11-26 2021-09-08 삼성전자주식회사 음성 인식 방법 및 그 전자 장치
US9653079B2 (en) 2015-02-12 2017-05-16 Apple Inc. Clock switching in always-on component
KR102346302B1 (ko) * 2015-02-16 2022-01-03 삼성전자 주식회사 전자 장치 및 음성 인식 기능 운용 방법
US10192546B1 (en) * 2015-03-30 2019-01-29 Amazon Technologies, Inc. Pre-wakeword speech processing
US10026399B2 (en) * 2015-09-11 2018-07-17 Amazon Technologies, Inc. Arbitration between voice-enabled devices
CN105204963A (zh) * 2015-09-28 2015-12-30 北京奇虎科技有限公司 数据缓存方法及装置
TWI557599B (zh) * 2015-11-05 2016-11-11 宏碁股份有限公司 語音控制方法及語音控制系統
US9728188B1 (en) * 2016-06-28 2017-08-08 Amazon Technologies, Inc. Methods and devices for ignoring similar audio being received by a system
US10074371B1 (en) * 2017-03-14 2018-09-11 Amazon Technologies, Inc. Voice control of remote device by disabling wakeword detection

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102905029A (zh) * 2012-10-17 2013-01-30 广东欧珀移动通信有限公司 一种手机及智能语音寻找手机的方法
US20140163978A1 (en) * 2012-12-11 2014-06-12 Amazon Technologies, Inc. Speech recognition power management
CN103095911A (zh) * 2012-12-18 2013-05-08 苏州思必驰信息科技有限公司 一种通过语音唤醒寻找手机的方法及系统
CN103021413A (zh) * 2013-01-07 2013-04-03 北京播思软件技术有限公司 语音控制方法及装置
CN103338311A (zh) * 2013-07-11 2013-10-02 成都西可科技有限公司 一种智能手机锁屏界面启动app的方法
CN103594089A (zh) * 2013-11-18 2014-02-19 联想(北京)有限公司 一种语音识别方法及电子设备
CN103632667A (zh) * 2013-11-25 2014-03-12 华为技术有限公司 声学模型优化方法、装置及语音唤醒方法、装置和终端
CN103929540A (zh) * 2014-04-25 2014-07-16 浙江翼信科技有限公司 一种消息操作方法及装置

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020517977A (ja) * 2017-06-29 2020-06-18 アリババ グループ ホウルディング リミテッド 音声ウェイクアップ方法、装置及び電子デバイス
JP2019185771A (ja) * 2018-03-30 2019-10-24 深▲せん▼市冠旭電子股▲ふん▼有限公司 ブルートゥーススピーカーデータ処理の方法、装置及びブルートゥーススピーカー
US11037560B2 (en) 2018-04-02 2021-06-15 Baidu Online Network Technology (Beijing) Co., Ltd.X Method, apparatus and storage medium for wake up processing of application
CN109243447A (zh) * 2018-10-12 2019-01-18 西安蜂语信息科技有限公司 语音发送触发方法及装置
CN109545207A (zh) * 2018-11-16 2019-03-29 广东小天才科技有限公司 一种语音唤醒方法及装置
CN109243462A (zh) * 2018-11-20 2019-01-18 广东小天才科技有限公司 一种语音唤醒方法及装置
CN109979466A (zh) * 2019-03-21 2019-07-05 广州国音智能科技有限公司 一种声纹身份同一性鉴定方法、装置及计算机可读存储介质
CN112363851A (zh) * 2020-10-28 2021-02-12 广东小天才科技有限公司 智能终端的语音唤醒方法、系统、智能手表及存储介质

Also Published As

Publication number Publication date
AU2021286393B2 (en) 2023-09-21
EP3282445A1 (en) 2018-02-14
JP2018517919A (ja) 2018-07-05
US20210287671A1 (en) 2021-09-16
BR112017021673A2 (zh) 2018-07-10
CA2982196C (en) 2022-07-19
CA2982196A1 (en) 2016-10-13
US10943584B2 (en) 2021-03-09
AU2021286393A1 (en) 2022-01-20
JP6564058B2 (ja) 2019-08-21
AU2015390534B2 (en) 2019-08-22
AU2019268131A1 (en) 2019-12-12
CN106463112B (zh) 2020-12-08
EP3282445A4 (en) 2018-05-02
AU2015390534A1 (en) 2017-11-30
US20180033436A1 (en) 2018-02-01
CN106463112A (zh) 2017-02-22
US11783825B2 (en) 2023-10-10
BR112017021673B1 (pt) 2023-02-14

Similar Documents

Publication Publication Date Title
WO2016161641A1 (zh) 语音识别方法、语音唤醒装置、语音识别装置及终端
JP6811758B2 (ja) 音声対話方法、装置、デバイス及び記憶媒体
US8909537B2 (en) Device capable of playing music and method for controlling music playing in electronic device
JP2015084544A (ja) 電話での会話をテキストに書き起こすための方法及びシステム
WO2015188459A1 (zh) 一种终端控制方法、装置、语音控制装置及终端
JP2017509009A (ja) オーディオストリームの中の音楽の追跡
TWI633425B (zh) 麥克風裝置
JP2017138536A (ja) 音声処理装置
US11437022B2 (en) Performing speaker change detection and speaker recognition on a trigger phrase
JP6817386B2 (ja) 音声認識方法、音声ウェイクアップ装置、音声認識装置、および端末
CN110910876A (zh) 物品声寻装置及控制方法、语音控制设置方法和系统
CN107680592A (zh) 一种移动终端语音识别方法、及移动终端及存储介质
CN111862965A (zh) 唤醒处理方法、装置、智能音箱及电子设备
US20160165035A1 (en) Electronic device and method for controlling electronic device using headset
JP7258007B2 (ja) 音声認識方法、音声ウェイクアップ装置、音声認識装置、および端末
US11699438B2 (en) Open smart speaker
JP2019144836A (ja) 音声出力装置、プログラム、および、プログラムの記録媒体
CN112992133A (zh) 声音信号控制方法、系统、可读存储介质和设备
TW202025701A (zh) 電子裝置及電子裝置的模式切換方法
TW201336290A (zh) 通信裝置及通信方法
WO2021077245A1 (zh) 语音控制的方法、装置、终端及存储介质
JP2013153338A (ja) アラーム装置、携帯端末、およびアラーム音の停止方法
TW201408036A (zh) 自動結束通話方法及通訊裝置
WO2019047220A1 (zh) 一种应用程序启动方法及终端、计算机可读存储介质
JP2019144835A (ja) 音声出力装置、プログラム、および、プログラムの記録媒体

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: 15888197

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2982196

Country of ref document: CA

Ref document number: 2017553159

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2015390534

Country of ref document: AU

Date of ref document: 20150410

Kind code of ref document: A

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112017021673

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 112017021673

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20171009