WO2017092189A1 - 语音唤醒实现方法、装置及终端、计算机存储介质 - Google Patents

语音唤醒实现方法、装置及终端、计算机存储介质 Download PDF

Info

Publication number
WO2017092189A1
WO2017092189A1 PCT/CN2016/075627 CN2016075627W WO2017092189A1 WO 2017092189 A1 WO2017092189 A1 WO 2017092189A1 CN 2016075627 W CN2016075627 W CN 2016075627W WO 2017092189 A1 WO2017092189 A1 WO 2017092189A1
Authority
WO
WIPO (PCT)
Prior art keywords
wake
recording
training
voice
voiceprint
Prior art date
Application number
PCT/CN2016/075627
Other languages
English (en)
French (fr)
Inventor
刘汝虎
刘攀
Original Assignee
中兴通讯股份有限公司
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
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Priority to JP2018527923A priority Critical patent/JP2019502947A/ja
Priority to US15/780,149 priority patent/US20180350372A1/en
Priority to EP16869503.9A priority patent/EP3385947A4/en
Publication of WO2017092189A1 publication Critical patent/WO2017092189A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • 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
    • G10L17/00—Speaker identification or verification
    • G10L17/04—Training, enrolment or model building
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/06—Decision making techniques; Pattern matching strategies
    • G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • 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
    • 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
    • G10L15/08—Speech classification or search
    • G10L2015/088—Word spotting
    • 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

Definitions

  • the present invention relates to the field of intelligent terminals, and in particular to a method and device for implementing voice wake-up, a terminal, and a computer storage medium.
  • voice wake-up and voiceprint encryption belong to two separate different hardware modules.
  • the successfully recorded wake-up words are directly set to the voice chip; in the voiceprint training process, the successfully recorded wake-up words are stored on the application processor (AP, Application Processor) side, and the two are recorded. They are carried out separately and there is no connection between them.
  • AP Application Processor
  • wake-up training and voiceprint training are two separate processes. If voice wake-up and voiceprint unlocking are set to different voice commands, the user needs to remember two wake-up words, which are easy to be confused or forgotten; if the voice wakes up The voice recording is unlocked and recorded in the same voice command, and the number of repeated recordings is more, which brings a bad user experience; on the other hand, since the smart terminal needs to be separately used for voice wake-up and voiceprint unlocking, The wake-up words of the voice wake-up do not have a special voiceprint verification, and there is also a certain probability of false wake-up.
  • the technical problem to be solved by the embodiments of the present invention is to provide a method and device for implementing voice wake-up, a terminal, and a computer storage medium, which can simplify the process of the user waking up and manipulating the smart terminal.
  • the technical solution provided by the embodiment of the present invention is as follows:
  • an embodiment of the present invention provides a voice wake-up implementation method, which is applied to an intelligent terminal, where the method includes:
  • the method before receiving the voice wakeup command input by the user, the method further includes:
  • the method before the completion of the unified training recording of the voice wake-up words including the voiceprint information, the method further includes:
  • the unified training recording of the voice wake-up words including the voiceprint information is completed.
  • the completion of the unified training recording of the voice wake-up words including voiceprint information includes:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the completion of the unified training recording of the voice wake-up words including voiceprint information includes:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the wake-up word training recording data is saved, and the wake-up word training recording is stopped, and the voiceprint training recording is continued.
  • the voiceprint training recording data is saved, and the unity training recording is completed, where m, n are integers greater than 1.
  • the completion of the unified training recording of the voice wake-up words including voiceprint information includes:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the completion of the unified training recording of the voice wake-up words including voiceprint information includes:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the embodiment of the invention further provides a voice wake-up implementation device, including:
  • a receiving module configured to receive a voice wake-up command input by a user
  • the determining module is configured to perform a wake-up word recognition judgment on the voice wake-up command by using a preset voice wake-up word to obtain a first judgment result, where the voice wake-up word includes voiceprint information, and the voice wake-up word is used to wake up the voice
  • the command performs voiceprint judgment to obtain a second judgment result
  • the processing module is configured to: when the first determination result and the second determination result both meet the preset condition, unlocking and waking up the smart terminal.
  • the device further includes:
  • a recording training module configured to complete a unified training recording of the voice wake-up words including voiceprint information
  • a voice chip configured to store the voice wake-up word.
  • the device further includes:
  • the recording processing module is configured to perform noise detection on the environment of the unified training recording before performing the unified training recording process
  • the recording training module is specifically configured to complete a unified training recording of the voice wake-up words including voiceprint information when the volume of the noise is lower than a preset decibel.
  • the recording training module includes:
  • a concurrent recording sub-module configured to control the left channel of the smart terminal to store the wake-up word training recording data during the unified training recording, and the right channel of the smart terminal stores the voiceprint training recording data;
  • the right channel of the smart terminal stores the wake-up word training recording data, and the left channel of the smart terminal stores the voiceprint training recording data.
  • the receiving module, the determining module, the processing module, the recording training module, the recording processing module, and the concurrent recording sub-module may use a central processing unit (CPU) when performing processing. , digital signal processor (DSP, Digital Singnal Processor) or programmable logic array (FPGA, Field-Programmable Gate Array) implementation.
  • CPU central processing unit
  • DSP Digital Singnal Processor
  • FPGA Field-Programmable Gate Array
  • the embodiment of the invention further provides an intelligent terminal, comprising the voice wake-up implementation device as described above.
  • the embodiment of the invention further provides a computer storage medium, wherein a computer program is stored, which is used to execute the above-mentioned voice wake-up implementation method of the embodiment of the invention.
  • the method for implementing the voice wake-up includes: receiving a voice wake-up command input by a user, and simultaneously using the preset voice wake-up word to perform a wake-up word recognition judgment and a voiceprint judgment on the voice wake-up instruction, when the judgment result meets the preset condition
  • the original two-step operation can be simplified into one step operation, and the steps of using the smart terminal after unlocking the voiceprint after waking up are omitted, simplifying user wake-up and manipulation The process of intelligent terminals.
  • FIG. 1 is a schematic diagram of a prior art training recording
  • FIG. 2 is a schematic diagram of performing a unified training recording according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of a wake-up and voiceprint unlocking of an intelligent terminal in the prior art
  • FIG. 4 is a schematic diagram of awakening and voiceprint unlocking of an intelligent terminal according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a device for implementing voice wakeup according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of performing a unified training recording according to Embodiment 4 of the present invention.
  • FIG. 7 is a schematic diagram of performing a unified training recording according to Embodiment 4 of the present invention.
  • FIG. 8 is a schematic diagram of performing a unified training recording according to Embodiment 5 of the present invention.
  • the embodiment of the present invention is directed to the problem that the voice wake-up and the voiceprint unlocking are separately performed in the prior art, resulting in a cumbersome operation of the user, and a voice wake-up implementation method, apparatus, and terminal are provided, which can simplify the process of the user waking up and manipulating the smart terminal.
  • the embodiment provides a voice wake-up implementation method, which is applied to an intelligent terminal, and the method includes:
  • the voice wake-up command input by the user is received, and the wake-up speech recognition command and the voiceprint judgment are simultaneously performed on the voice wake-up command by using the preset voice wake-up word, and the judgment result is consistent.
  • the smart terminal is unlocked and awake, and the technical solution of the present invention can simplify the original two-step operation into one step operation, omitting the steps of using the smart terminal after the wake-up sound file is unlocked, and simplifying the user wake-up. And the process of manipulating the smart terminal.
  • the method before receiving the voice wakeup command input by the user, the method further includes:
  • the method before the completion of the unified training recording of the voice wake-up words including the voiceprint information, the method further includes:
  • the unified training recording of the voice wake-up words including the voiceprint information is completed.
  • the completion of the unified training recording of the voice wake-up words including voiceprint information includes:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the completion of the unified training recording of the voice wake-up words including voiceprint information includes:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the completion of the unified training recording of the voice wake-up words including voiceprint information includes:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the completion of the unified training recording of the voice wake-up words including voiceprint information includes:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the wake-up word training recording and the voiceprint training recording are separately performed, as shown in FIG. 3, when the smart terminal is operated, the wake-up and the voiceprint unlocking are also performed separately.
  • FIG. 2 in the embodiment of the present invention, when the training recording is performed, the wake-up word training recording and the voiceprint training recording are performed simultaneously, as shown in FIG. 4, when the smart terminal is operated, the wake-up and the voiceprint unlocking are also simultaneously ongoing.
  • the embodiment provides a voice wake-up implementation device. As shown in FIG. 5, the embodiment includes:
  • a receiving module configured to receive a voice wake-up command input by a user
  • the determining module is configured to perform a wake-up word recognition judgment on the voice wake-up command by using a preset voice wake-up word to obtain a first judgment result, where the voice wake-up word includes voiceprint information, and the voice wake-up word is used to wake up the voice
  • the command performs voiceprint judgment to obtain a second judgment result
  • the processing module is configured to: when the first determination result and the second determination result both meet the preset condition, unlocking and waking up the smart terminal.
  • the apparatus further includes:
  • a recording training module configured to complete a unified training recording of the voice wake-up words including voiceprint information
  • a voice chip configured to store the voice wake-up word.
  • the present invention can simplify the original two-step operation into one step operation, omitting the steps of using the smart terminal after unlocking the voiceprint after waking up, simplifying the process of the user waking up and manipulating the smart terminal.
  • the apparatus further includes:
  • the recording processing module is configured to perform noise detection on the environment of the unified training recording before performing the unified training recording process
  • the recording training module is specifically configured to complete a unified training recording of the voice wake-up words including voiceprint information when the volume of the noise is lower than a preset decibel.
  • the recording training module can control the recording result of each time and judge whether the recording is successful or not and whether to enter the next recording.
  • the recording processing module performs environmental noise judgment before performing the unified training recording, and appropriately enhances the signal-to-noise ratio (SNR) judgment during the unified training recording process to improve the data quality of the recording training module, thereby improving the recognition success. rate.
  • SNR signal-to-noise ratio
  • the recording training module includes:
  • a concurrent recording sub-module configured to control the left channel of the smart terminal to store the wake-up word training recording data during the unified training recording, and the right channel of the smart terminal stores the voiceprint training recording data;
  • the right channel of the smart terminal stores the wake-up word training recording data, and the left channel of the smart terminal stores the voiceprint training recording data.
  • This embodiment provides an intelligent terminal, including the voice wakeup implementation device as described above.
  • the intelligent terminal of the embodiment receives the voice wake-up instruction input by the user, and uses the preset voice wake-up word to simultaneously perform the wake-up word recognition judgment and the voice pattern judgment on the voice wake-up instruction, when determining the knot If the smart terminal is unlocked and awake, the technical solution of the present invention can simplify the original two-step operation into one step operation, and omits the step of using the smart terminal after unlocking the voiceprint after waking up. Simplify the process of user wake-up and manipulation of the smart terminal.
  • the voice wake-up implementation method of the smart terminal the specific steps are:
  • the first step the user performs a unified training recording of the voice wake-up words with voiceprint information before using the smart terminal;
  • Step 2 Set the security lock screen of the smart terminal
  • the third step the smart terminal is in a state where the black screen or standby can work normally;
  • the fourth part the user speaks the wake-up word, performs the wake-up word recognition judgment and the voice pattern judgment, and if both meet the conditions, directly responds to the user to perform voice control on the smart terminal; otherwise, the prompt error.
  • Step 1 Before the united training recording, first check the environmental noise. If the current environment meets the recording conditions, continue to perform the unity training recording, otherwise it will prompt to record in a quiet environment. The criteria for conditional judgment are determined based on empirical values obtained from tests under different environmental conditions;
  • Step 2 In the process of unity training recording, it is assumed that the number of successes of the wake-up word training recording should reach m, and the number of successes of voiceprint training recording should reach n.
  • the principle of unity training recording is that the wake-up word or the voiceprint is successfully recorded first. The first one is to exit the united training recording, and the unsuccessful party independently performs the unity training recording.
  • the basic process of the unified training recording is as follows:
  • Step 3 Switch to the corresponding unified route every time the training recording is combined, and use the left and right channels to store the wake-up word training recording data and the voiceprint training recording data respectively.
  • the training recording When the training recording is performed independently, it switches to the independent recording route, and uses the left channel to store the current recording data;
  • Step 4 After the training is successfully recorded, the wake-up training recording data is stored in the voice chip, and the voiceprint training recording data is stored on the AP side, and then the smart terminal enters the standby working state;
  • Step 5 The user speaks the wake-up word, performs the wake-up word recognition judgment and the voiceprint judgment, and if both meet the conditions, directly responds to the user to perform voice control on the smart terminal; otherwise, the prompt error.
  • the user sets a security lock screen mode.
  • the wake-up words are spoken, and the smart terminal performs the wake-up word recognition judgment and the voiceprint unlocking judgment. If both of them meet the conditions, the user directly responds to the voice control, which simplifies the user's wake-up and manipulation of the smart terminal. the way.
  • Step 1 Before the united training recording, first check the environmental noise. If the current environment meets the recording conditions, continue to perform the unity training recording, otherwise it will prompt to record in a quiet environment. The criteria for conditional judgment are determined based on empirical values obtained from tests under different environmental conditions;
  • Step 2 In the process of unity training recording, it is assumed that the number of successes of the wake-up word training recording should reach m, and the number of successes of voiceprint training recording should reach n.
  • the principle of unity training recording is that the wake-up word or the voiceprint is successfully recorded first. The first one is to exit the united training recording, and the unsuccessful party independently performs the unity training recording.
  • the basic process of the unified training recording is as follows:
  • the wake-up word training recording and the voiceprint training recording of the voice wake-up words are performed, and the recording results are judged respectively;
  • the wake-up words are processed by the corresponding wake-up voice chip, and the voiceprint is processed by the corresponding voiceprint engine, and there may be timing differences in the process of the required processing, and each time in the present invention
  • Table 1 The training of different timing problems between the two trainings is shown in Table 1:
  • Step 3 Switch to the corresponding unified route every time the training recording is combined, and use the left and right channels to store the wake-up word training recording data and the voiceprint training recording data respectively.
  • the training recording When the training recording is performed independently, it switches to the independent recording route, and uses the left channel to store the current recording data;
  • Step 4 After the training is successfully recorded, the wake-up training recording data is stored in the voice chip, and the voiceprint training recording data is stored on the AP side, and then the smart terminal enters the standby working state;
  • Step 5 The user speaks the wake-up word, performs the wake-up word recognition judgment and the voiceprint judgment, and if both meet the conditions, directly responds to the user to perform voice control on the smart terminal; otherwise, the prompt error.
  • the user sets a security lock screen mode.
  • the wake-up words are spoken, and the smart terminal performs the wake-up word recognition judgment and the voiceprint unlocking judgment. If both of them meet the conditions, the user directly responds to the voice control, which simplifies the user's wake-up and manipulation of the smart terminal. the way.
  • the embodiment of the invention further provides a computer storage medium, wherein a computer program is stored, which is used to execute the above-mentioned voice wake-up implementation method of the embodiment of the invention.
  • the modules may be implemented in software for execution by various types of processors.
  • an identified executable code module can comprise one or more physical or logical blocks of computer instructions, which can be constructed, for example, as an object, procedure, or function. Nevertheless, the executable code of the identified modules need not be physically located together, but may include different instructions stored in different physicalities. When these instructions are logically combined, they constitute a module and achieve the specified purpose of the module. .
  • the executable code module can be a single instruction or a plurality of instructions, and can even be distributed across multiple different code segments, distributed among different programs, and distributed across multiple memory devices.
  • operational data may be identified within the modules and may be implemented in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set, or may be distributed at different locations (including on different storage devices), and may at least partially exist as an electronic signal on a system or network.
  • the module can be implemented by software, considering the level of the existing hardware process, the module can be implemented in software, and the technician can construct a corresponding hardware circuit to implement the corresponding function without considering the cost.
  • the hardware circuitry includes conventional Very Large Scale Integration (VLSI) circuits or gate arrays as well as existing semiconductors such as logic chips, transistors, or other discrete components.
  • VLSI Very Large Scale Integration
  • the modules can also be implemented with programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, and the like.
  • sequence numbers of the steps are not used to limit the sequence of the steps.
  • the steps of the steps are changed without any creative work. It is also within the scope of the invention.
  • the method for implementing the voice wake-up includes: receiving a voice wake-up command input by a user, and simultaneously using the preset voice wake-up word to perform a wake-up word recognition judgment and a voiceprint judgment on the voice wake-up instruction, when the judgment result meets the preset condition
  • the original two-step operation can be simplified into one step operation, and the steps of using the smart terminal after unlocking the voiceprint after waking up are omitted, simplifying user wake-up and manipulation The process of intelligent terminals.

Abstract

本发明提供了一种语音唤醒实现方法、装置及终端、计算机存储介质，属于智能终端领域。其中，语音唤醒实现方法，应用于智能终端，所述方法包括：接收用户输入的语音唤醒指令；利用预设的语音唤醒词对所述语音唤醒指令进行唤醒词识别判断得到第一判断结果，所述语音唤醒词包括有声纹信息；利用所述语音唤醒词对所述语音唤醒指令进行声纹判断得到第二判断结果；当所述第一判断结果与所述第二判断结果均符合预设条件时，对所述智能终端进行解锁和唤醒。本发明的技术方案能够简化用户唤醒并操控智能终端的过程。

Description

语音唤醒实现方法、装置及终端、计算机存储介质 技术领域
本发明涉及智能终端领域，特别是指一种语音唤醒实现方法、装置及终端、计算机存储介质。
背景技术
在现有的智能终端中，语音唤醒和声纹加密分别属于两个独立的不同硬件模块。在语音唤醒培训过程中，将成功录制的唤醒词直接设置到语音芯片中；在声纹培训过程中，将成功录制的唤醒词存储到应用处理器(AP，Application Processor)侧，两者的录制是分开进行的，彼此之间没有联系。
在使用智能终端时，需要先通过唤醒词进行语音唤醒，声纹加密状态下还需要继续进行声纹的验证，声纹验证通过之后才可以进行语音指令的操控。
基于上面的实现方法，唤醒培训和声纹培训是独立的两个过程，如果语音唤醒和声纹解锁设置成不同的语音指令，用户就需要记两个唤醒词，容易混淆或忘记；如果语音唤醒和声纹解锁录制成一样的语音指令，重复录制次数就比较多，给用户带来不好的使用体验；另一方面，由于在使用智能终端时，需要分别进行语音唤醒和声纹解锁，由于语音唤醒的唤醒词没有进行专门的声纹验证，也存在着一定的误唤醒几率。
发明内容
本发明实施例要解决的技术问题是提供一种语音唤醒实现方法、装置及终端、计算机存储介质，能够简化用户唤醒并操控智能终端的过程。
为解决上述技术问题，本发明实施例提供的技术方案如下：
一方面，本发明实施例提供了一种语音唤醒实现方法，应用于智能终端，所述方法包括：
接收用户输入的语音唤醒指令；
利用预设的语音唤醒词对所述语音唤醒指令进行唤醒词识别判断得到第一判断结果，所述语音唤醒词包括有声纹信息；
利用所述语音唤醒词对所述语音唤醒指令进行声纹判断得到第二判断结果；
当所述第一判断结果与所述第二判断结果均符合预设条件时，对所述智能终端进行解锁和唤醒。
上述方案中，所述接收用户输入的语音唤醒指令之前还包括：
完成包括声纹信息的所述语音唤醒词的合一培训录音，并存储所述语音唤醒词。
上述方案中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音之前还包括：
对合一培训录音的环境进行噪音检测；
所述完成包括声纹信息的所述语音唤醒词的合一培训录音具体为：
在所述噪音的音量低于预设分贝时，完成包括声纹信息的所述语音唤醒词的合一培训录音。
上述方案中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
若声纹培训录音成功次数达到n，唤醒词培训录音成功次数为0时，重新开始合一培训录音；或若唤醒词培训录音成功次数达到m，声纹培训录音成功次数为0时，重新开始合一培训录音，其中m，n为大于1的整数。
上述方案中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
若唤醒词培训录音成功次数达到m，声纹培训录音成功次数小于n，则保存唤醒词培训录音数据，并停止唤醒词培训录音，继续声纹培训录音， 当声纹培训录音成功次数达到n时，保存声纹培训录音数据，完成合一培训录音，其中m，n为大于1的整数。
上述方案中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
若声纹培训录音成功次数达到n，唤醒词培训录音成功次数小于m，则保存声纹培训录音数据，并停止声纹培训录音，继续唤醒词培训录音，当唤醒词培训录音成功次数达到m时，保存唤醒词培训录音数据，完成合一培训录音，其中m，n为大于1的整数。
上述方案中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
记录唤醒词培训录音和声纹培训录音同时成功的次数，当所述次数达到m时，保存唤醒词培训录音数据和声纹培训录音数据，完成合一培训录音，其中m为大于1的整数。
本发明实施例还提供了一种语音唤醒实现装置，包括：
接收模块，配置为接收用户输入的语音唤醒指令；
判断模块，配置为利用预设的语音唤醒词对所述语音唤醒指令进行唤醒词识别判断得到第一判断结果，所述语音唤醒词包括有声纹信息，利用所述语音唤醒词对所述语音唤醒指令进行声纹判断得到第二判断结果；
处理模块，配置为当所述第一判断结果与所述第二判断结果均符合预设条件时，对所述智能终端进行解锁和唤醒。
上述方案中，所述装置还包括：
录音培训模块，配置为完成包括声纹信息的所述语音唤醒词的合一培训录音；
语音芯片，配置为存储所述语音唤醒词。
上述方案中，所述装置还包括：
录音处理模块，配置为在进行合一培训录音过程前，对合一培训录音的环境进行噪音检测；
所述录音培训模块具体配置为在所述噪音的音量低于预设分贝时，完成包括声纹信息的所述语音唤醒词的合一培训录音。
上述方案中，所述录音培训模块包括：
并发录音子模块，配置为在合一培训录音过程中，控制所述智能终端的左声道存储唤醒词培训录音数据，所述智能终端的右声道存储声纹培训录音数据；或者制所述智能终端的右声道存储唤醒词培训录音数据，所述智能终端的左声道存储声纹培训录音数据。
所述接收模块、所述判断模块、所述处理模块、所述录音培训模块、所述录音处理模块、所述并发录音子模块在执行处理时，可以采用中央处理器(CPU，Central Processing Unit)、数字信号处理器(DSP，Digital Singnal Processor)或可编程逻辑阵列(FPGA，Field－Programmable Gate Array)实现。
本发明实施例还提供了一种智能终端，包括如上所述的语音唤醒实现装置。
本发明实施例还提供了一种计算机存储介质，其中存储有计算机程序，该计算机程序用于执行本发明实施例的上述语音唤醒实现方法。
本发明的实施例具有以下有益效果：
本发明实施例的语音唤醒实现方法，包括：接收用户输入的语音唤醒指令，利用预设的语音唤醒词对语音唤醒指令同时进行唤醒词识别判断和声纹判断，当判断结果均符合预设条件时，对智能终端进行解锁和唤醒，采用本发明实施例，能将原来的两步操作简化成一步操作，省略了唤醒后要进行声纹解锁后才能使用智能终端的步骤，简化用户唤醒并操控智能终端的过程。
附图说明
图1为现有技术进行培训录音的示意图；
图2为本发明实施例进行合一培训录音的示意图；
图3为现有技术对智能终端进行唤醒和声纹解锁的示意图；
图4为本发明实施例对智能终端进行唤醒和声纹解锁的示意图；
图5为本发明实施例语音唤醒实现装置的结构示意图；
图6为本发明实施例四进行合一培训录音的示意图；
图7为本发明实施例四进行合一培训录音的示意图；
图8为本发明实施例五进行合一培训录音的示意图。
具体实施方式
为使本发明的实施例要解决的技术问题、技术方案和优点更加清楚，下面将结合附图及具体实施例进行详细描述。
本发明的实施例针对现有技术中语音唤醒和声纹解锁分开进行，导致用户的操作繁琐的问题，提供一种语音唤醒实现方法、装置及终端，能够简化用户唤醒并操控智能终端的过程。
实施例一
本实施例提供一种语音唤醒实现方法，应用于智能终端，所述方法包括：
接收用户输入的语音唤醒指令；
利用预设的语音唤醒词对所述语音唤醒指令进行唤醒词识别判断得到第一判断结果，所述语音唤醒词包括有声纹信息；
利用所述语音唤醒词对所述语音唤醒指令进行声纹判断得到第二判断结果；
当所述第一判断结果与所述第二判断结果均符合预设条件时，对所述智能终端进行解锁和唤醒。
本实施例中，接收用户输入的语音唤醒指令，利用预设的语音唤醒词对语音唤醒指令同时进行唤醒词识别判断和声纹判断，当判断结果均符合 预设条件时，对智能终端进行解锁和唤醒，本发明的技术方案能将原来的两步操作简化成一步操作，省略了唤醒后要进行声纹解锁后才能使用智能终端的步骤，简化用户唤醒并操控智能终端的过程。
在本发明实施例一实施方式中，所述接收用户输入的语音唤醒指令之前还包括：
完成包括声纹信息的所述语音唤醒词的合一培训录音，并存储所述语音唤醒词。
在本发明实施例一实施方式中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音之前还包括：
对合一培训录音的环境进行噪音检测；
所述完成包括声纹信息的所述语音唤醒词的合一培训录音具体为：
在所述噪音的音量低于预设分贝时，完成包括声纹信息的所述语音唤醒词的合一培训录音。
在本发明实施例一实施方式中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
若声纹培训录音成功次数达到n，唤醒词培训录音成功次数为0时，重新开始合一培训录音；或若唤醒词培训录音成功次数达到m，声纹培训录音成功次数为0时，重新开始合一培训录音，其中m，n为大于1的整数。
在本发明实施例一实施方式中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
若唤醒词培训录音成功次数达到m，声纹培训录音成功次数小于n，则保存唤醒词培训录音数据，并停止唤醒词培训录音，继续声纹培训录音，当声纹培训录音成功次数达到n时，保存声纹培训录音数据，完成合一培训录音，其中m，n为大于1的整数。
在本发明实施例一实施方式中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
若声纹培训录音成功次数达到n，唤醒词培训录音成功次数小于m，则保存声纹培训录音数据，并停止声纹培训录音，继续唤醒词培训录音，当唤醒词培训录音成功次数达到m时，保存唤醒词培训录音数据，完成合一培训录音，其中m，n为大于1的整数。
在本发明实施例一实施方式中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
记录唤醒词培训录音和声纹培训录音同时成功的次数，当所述次数达到m时，保存唤醒词培训录音数据和声纹培训录音数据，完成合一培训录音，其中m为大于1的整数。
如图1所示，现有技术在进行培训录音时，唤醒词培训录音和声纹培训录音是分别进行的，如图3所示，在操作智能终端时，唤醒和声纹解锁也是分别进行的。而如图2所示，本发明实施例在进行培训录音时，唤醒词培训录音和声纹培训录音是同时进行的，如图4所示，在操作智能终端时，唤醒和声纹解锁也是同时进行的。
实施例二
本实施例提供了一种语音唤醒实现装置，如图5所示，本实施例包括：
接收模块，配置为接收用户输入的语音唤醒指令；
判断模块，配置为利用预设的语音唤醒词对所述语音唤醒指令进行唤醒词识别判断得到第一判断结果，所述语音唤醒词包括有声纹信息，利用所述语音唤醒词对所述语音唤醒指令进行声纹判断得到第二判断结果；
处理模块，配置为当所述第一判断结果与所述第二判断结果均符合预设条件时，对所述智能终端进行解锁和唤醒。
在本发明实施例一实施方式中，所述装置还包括：
录音培训模块，配置为完成包括声纹信息的所述语音唤醒词的合一培训录音；
语音芯片，配置为存储所述语音唤醒词。
接收用户输入的语音唤醒指令，利用预设的语音唤醒词对语音唤醒指令同时进行唤醒词识别判断和声纹判断，当判断结果均符合预设条件时，对智能终端进行解锁和唤醒，本发明的技术方案能将原来的两步操作简化成一步操作，省略了唤醒后要进行声纹解锁后才能使用智能终端的步骤，简化用户唤醒并操控智能终端的过程。
在本发明实施例一实施方式中，所述装置还包括：
录音处理模块，配置为在进行合一培训录音过程前，对合一培训录音的环境进行噪音检测；
所述录音培训模块具体配置为在所述噪音的音量低于预设分贝时，完成包括声纹信息的所述语音唤醒词的合一培训录音。
录音培训模块可以对每次的录音结果进行控制并判断当次录音是否成功，以及是否进入下一次录音。
录音处理模块在进行合一培训录音前先进行环境噪音判断，并且在合一培训录音过程中适当增强对信噪比(SNR)的判断，以提升录音培训模块的数据质量，进而提升识别的成功率。
在本发明实施例一实施方式中，所述录音培训模块包括：
并发录音子模块，配置为在合一培训录音过程中，控制所述智能终端的左声道存储唤醒词培训录音数据，所述智能终端的右声道存储声纹培训录音数据；或者制所述智能终端的右声道存储唤醒词培训录音数据，所述智能终端的左声道存储声纹培训录音数据。
实施例三
本实施例提供了一种智能终端，包括如上所述的语音唤醒实现装置。
本实施例的智能终端，接收用户输入的语音唤醒指令，利用预设的语音唤醒词对语音唤醒指令同时进行唤醒词识别判断和声纹判断，当判断结 果均符合预设条件时，对智能终端进行解锁和唤醒，本发明的技术方案能将原来的两步操作简化成一步操作，省略了唤醒后要进行声纹解锁后才能使用智能终端的步骤，简化用户唤醒并操控智能终端的过程。
该智能终端的语音唤醒实现方法，具体步骤为：
第一步：用户使用智能终端前先进行带声纹信息的语音唤醒词的合一培训录音；
第二步：设置智能终端的安全锁屏；
第三步：智能终端处在黑屏或待机可以正常工作的状态；
第四部：用户说出唤醒词，进行唤醒词识别判断和声纹判断，如果两者都符合条件后，直接响应用户进行语音操控智能终端；否则，提示错误。
实施例四
本实施例的语音唤醒实现方法包括：
步骤一、在合一培训录音前，先进行环境噪音的检测，若当前环境符合录制条件，则继续进行合一培训录音，否则提示到安静环境录制。条件判断的标准依据从不同的环境状态下测试得到的经验值来确定的；
步骤二、在合一培训录音过程中，假设唤醒词培训录音成功次数要达到m，声纹培训录音成功次数要达到n，合一培训录音原则为唤醒词或声纹任一方先录制成功则成功的先退出合一培训录音，未成功的一方则独立进行合一培训录音。合一培训录音的基本流程如下：
2.1)若声纹培训录音成功次数达到n，唤醒词培训录音成功次数为0时，重新开始合一培训录音；或若唤醒词培训录音成功次数达到m，声纹培训录音成功次数为0时，重新开始合一培训录音，其中m，n为大于1的整数。
2.2)如图6所示，若唤醒词培训录音成功次数达到m，声纹培训录音成功次数小于n，则保存唤醒词培训录音数据，并停止唤醒词培训录音，继续声纹培训录音，当声纹培训录音成功次数达到n时，保存声纹培训录音数据，完成合一培训录音，其中m，n为大于1的整数。
2.3)如图7所示，若声纹培训录音成功次数达到n，唤醒词培训录音 成功次数小于m，则保存声纹培训录音数据，并停止声纹培训录音，继续唤醒词培训录音，当唤醒词培训录音成功次数达到m时，保存唤醒词培训录音数据，完成合一培训录音，其中m，n为大于1的整数。
2.4)由于唤醒词培训录音或者声纹培训录音过程中，唤醒词由对应唤醒语音芯片处理，声纹由对应的声纹引擎处理，所需处理的过程中可能存在时序差异，本发明中对每一次合一培训这两者间不同时序问题的处理方式如表1所示：
Figure PCTCN2016075627-appb-000001
表1
步骤三、每次合一培训录音时则切换到对应的合一路由，同时采用左右声道，分别存储唤醒词培训录音数据和声纹培训录音数据。独立进行培训录音时，则切换到独立录音路由，采用左声道存储当前的录音数据；
步骤四、合一培训录制成功后将唤醒词培训录音数据存储到语音芯片，声纹培训录音数据存储到AP侧，随即智能终端进入待机工作状态；
步骤五、用户说出唤醒词，进行唤醒词识别判断和声纹判断，如果两者都符合条件后，直接响应用户进行语音操控智能终端；否则，提示错误。
本实施例中，用户在培训完成唤醒词后，设置安全锁屏方式。在黑屏或待机状态，说出唤醒词，智能终端进行唤醒词识别判断和声纹解锁判断，如果两者都符合条件后，直接响应用户进行语音操控，此方法简化了用户唤醒并操控智能终端的方式。
实施例五
本实施例的语音唤醒实现方法包括：
步骤一、在合一培训录音前，先进行环境噪音的检测，若当前环境符合录制条件，则继续进行合一培训录音，否则提示到安静环境录制。条件判断的标准依据从不同的环境状态下测试得到的经验值来确定的；
步骤二、在合一培训录音过程中，假设唤醒词培训录音成功次数要达到m，声纹培训录音成功次数要达到n，合一培训录音原则为唤醒词或声纹任一方先录制成功则成功的先退出合一培训录音，未成功的一方则独立进行合一培训录音。合一培训录音的基本流程如下：
同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
记录唤醒词培训录音和声纹培训录音同时成功的次数，当所述次数达到m时，保存唤醒词培训录音数据和声纹培训录音数据，完成合一培训录音，其中m为大于1的整数。
由于唤醒词培训录音或者声纹培训录音过程中，唤醒词由对应唤醒语音芯片处理，声纹由对应的声纹引擎处理，所需处理的过程中可能存在时序差异，本发明中对每一次合一培训这两者间不同时序问题的处理方式如表1所示：
步骤三、每次合一培训录音时则切换到对应的合一路由，同时采用左右声道，分别存储唤醒词培训录音数据和声纹培训录音数据。独立进行培训录音时，则切换到独立录音路由，采用左声道存储当前的录音数据；
步骤四、合一培训录制成功后将唤醒词培训录音数据存储到语音芯片，声纹培训录音数据存储到AP侧，随即智能终端进入待机工作状态；
步骤五、用户说出唤醒词，进行唤醒词识别判断和声纹判断，如果两者都符合条件后，直接响应用户进行语音操控智能终端；否则，提示错误。
本实施例中，用户在培训完成唤醒词后，设置安全锁屏方式。在黑屏或待机状态，说出唤醒词，智能终端进行唤醒词识别判断和声纹解锁判断，如果两者都符合条件后，直接响应用户进行语音操控，此方法简化了用户唤醒并操控智能终端的方式。
本发明实施例还提供了一种计算机存储介质，其中存储有计算机程序，该计算机程序用于执行本发明实施例的上述语音唤醒实现方法。
此说明书中所描述的许多功能部件都被称为模块，以便更加特别地强调其实现方式的独立性。
本发明实施例中，模块可以用软件实现，以便由各种类型的处理器执行。举例来说，一个标识的可执行代码模块可以包括计算机指令的一个或多个物理或者逻辑块，举例来说，其可以被构建为对象、过程或函数。尽管如此，所标识模块的可执行代码无需物理地位于一起，而是可以包括存储在不同物理上的不同的指令，当这些指令逻辑上结合在一起时，其构成模块并且实现该模块的规定目的。
实际上，可执行代码模块可以是单条指令或者是许多条指令，并且甚至可以分布在多个不同的代码段上，分布在不同程序当中，以及跨越多个存储器设备分布。同样地，操作数据可以在模块内被识别，并且可以依照任何适当的形式实现并且被组织在任何适当类型的数据结构内。所述操作数据可以作为单个数据集被收集，或者可以分布在不同位置上(包括在不同存储设备上)，并且至少部分地可以仅作为电子信号存在于系统或网络上。
在模块可以利用软件实现时，考虑到现有硬件工艺的水平，所以可以以软件实现的模块，在不考虑成本的情况下，本领域技术人员都可以搭建对应的硬件电路来实现对应的功能，所述硬件电路包括常规的超大规模集成(VLSI)电路或者门阵列以及诸如逻辑芯片、晶体管之类的现有半导体或者是其它分立的元件。模块还可以用可编程硬件设备，诸如现场可编程门阵列、可编程阵列逻辑、可编程逻辑设备等实现。
在本发明各方法实施例中，所述各步骤的序号并不能用于限定各步骤的先后顺序，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，对各步骤的先后变化也在本发明的保护范围之内。
以上所述是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明所述原理的前提下，还可以作出若干改 进和润饰，这些改进和润饰也应视为本发明的保护范围。
工业实用性
本发明实施例的语音唤醒实现方法，包括：接收用户输入的语音唤醒指令，利用预设的语音唤醒词对语音唤醒指令同时进行唤醒词识别判断和声纹判断，当判断结果均符合预设条件时，对智能终端进行解锁和唤醒，采用本发明实施例，能将原来的两步操作简化成一步操作，省略了唤醒后要进行声纹解锁后才能使用智能终端的步骤，简化用户唤醒并操控智能终端的过程。

Claims (13)

  1. 一种语音唤醒实现方法，应用于智能终端，所述方法包括：
    接收用户输入的语音唤醒指令；
    利用预设的语音唤醒词对所述语音唤醒指令进行唤醒词识别判断得到第一判断结果，所述语音唤醒词包括有声纹信息；
    利用所述语音唤醒词对所述语音唤醒指令进行声纹判断得到第二判断结果；
    当所述第一判断结果与所述第二判断结果均符合预设条件时，对所述智能终端进行解锁和唤醒。
  2. 根据权利要求1所述的语音唤醒实现方法，其中，所述接收用户输入的语音唤醒指令之前还包括：
    完成包括声纹信息的所述语音唤醒词的合一培训录音，并存储所述语音唤醒词。
  3. 根据权利要求2所述的语音唤醒实现方法，其中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音之前还包括：
    对合一培训录音的环境进行噪音检测；
    所述完成包括声纹信息的所述语音唤醒词的合一培训录音具体为：
    在所述噪音的音量低于预设分贝时，完成包括声纹信息的所述语音唤醒词的合一培训录音。
  4. 根据权利要求2所述的语音唤醒实现方法，其中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
    同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
    若声纹培训录音成功次数达到n，唤醒词培训录音成功次数为0时，重新开始合一培训录音；或若唤醒词培训录音成功次数达到m，声纹培训录音成功次数为0时，重新开始合一培训录音，其中m，n为大于1的整数。
  5. 根据权利要求2所述的语音唤醒实现方法，其中，所述完成包括声 纹信息的所述语音唤醒词的合一培训录音包括：
    同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
    若唤醒词培训录音成功次数达到m，声纹培训录音成功次数小于n，则保存唤醒词培训录音数据，并停止唤醒词培训录音，继续声纹培训录音，当声纹培训录音成功次数达到n时，保存声纹培训录音数据，完成合一培训录音，其中m，n为大于1的整数。
  6. 根据权利要求2所述的语音唤醒实现方法，其中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
    同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
    若声纹培训录音成功次数达到n，唤醒词培训录音成功次数小于m，则保存声纹培训录音数据，并停止声纹培训录音，继续唤醒词培训录音，当唤醒词培训录音成功次数达到m时，保存唤醒词培训录音数据，完成合一培训录音，其中m，n为大于1的整数。
  7. 根据权利要求2所述的语音唤醒实现方法，其中，所述完成包括声纹信息的所述语音唤醒词的合一培训录音包括：
    同时进行语音唤醒词的唤醒词培训录音和声纹培训录音，分别进行录音结果的判断；
    记录唤醒词培训录音和声纹培训录音同时成功的次数，当所述次数达到m时，保存唤醒词培训录音数据和声纹培训录音数据，完成合一培训录音，其中m为大于1的整数。
  8. 一种语音唤醒实现装置，包括：
    接收模块，配置为接收用户输入的语音唤醒指令；
    判断模块，配置为利用预设的语音唤醒词对所述语音唤醒指令进行唤醒词识别判断得到第一判断结果，所述语音唤醒词包括有声纹信息，利用所述语音唤醒词对所述语音唤醒指令进行声纹判断得到第二判断结果；
    处理模块，配置为当所述第一判断结果与所述第二判断结果均符合预 设条件时，对所述智能终端进行解锁和唤醒。
  9. 根据权利要求8所述的语音唤醒实现装置，其中，所述装置还包括：
    录音培训模块，配置为完成包括声纹信息的所述语音唤醒词的合一培训录音；
    语音芯片，配置为存储所述语音唤醒词。
  10. 根据权利要求9所述的语音唤醒实现装置，其中，所述装置还包括：
    录音处理模块，配置为在进行合一培训录音过程前，对合一培训录音的环境进行噪音检测；
    所述录音培训模块具体配置为在所述噪音的音量低于预设分贝时，完成包括声纹信息的所述语音唤醒词的合一培训录音。
  11. 根据权利要求9所述的语音唤醒实现装置，其中，所述录音培训模块包括：
    并发录音子模块，配置为在合一培训录音过程中，控制所述智能终端的左声道存储唤醒词培训录音数据，所述智能终端的右声道存储声纹培训录音数据；或者制所述智能终端的右声道存储唤醒词培训录音数据，所述智能终端的左声道存储声纹培训录音数据。
  12. 一种智能终端，包括如权利要求8-11中任一项所述的语音唤醒实现装置。
  13. 一种计算机存储介质，所述计算机存储介质中存储有计算机程序，该计算机程序用于上述权利要求1-7任一项所述的语音唤醒实现方法。
PCT/CN2016/075627 2015-11-30 2016-03-04 语音唤醒实现方法、装置及终端、计算机存储介质 WO2017092189A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2018527923A JP2019502947A (ja) 2015-11-30 2016-03-04 音声ウェイクアップ実現方法、装置及び端末、コンピュータ記憶媒体
US15/780,149 US20180350372A1 (en) 2015-11-30 2016-03-04 Method realizing voice wake-up, device, terminal, and computer storage medium
EP16869503.9A EP3385947A4 (en) 2015-11-30 2016-03-04 Method realizing voice wake-up, device, terminal, and computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510859545.2A CN106815507A (zh) 2015-11-30 2015-11-30 语音唤醒实现方法、装置及终端
CN201510859545.2 2015-11-30

Publications (1)

Publication Number Publication Date
WO2017092189A1 true WO2017092189A1 (zh) 2017-06-08

Family

ID=58796244

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/075627 WO2017092189A1 (zh) 2015-11-30 2016-03-04 语音唤醒实现方法、装置及终端、计算机存储介质

Country Status (5)

Country Link
US (1) US20180350372A1 (zh)
EP (1) EP3385947A4 (zh)
JP (1) JP2019502947A (zh)
CN (1) CN106815507A (zh)
WO (1) WO2017092189A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109003611A (zh) * 2018-09-29 2018-12-14 百度在线网络技术（北京）有限公司 用于车辆语音控制的方法、装置、设备和介质
CN109584860A (zh) * 2017-09-27 2019-04-05 九阳股份有限公司 一种语音唤醒词定义方法和系统
CN110400568A (zh) * 2018-04-20 2019-11-01 比亚迪股份有限公司 智能语音系统的唤醒方法、智能语音系统及车辆
CN112201239A (zh) * 2020-09-25 2021-01-08 海尔优家智能科技（北京）有限公司 目标设备的确定方法及装置、存储介质、电子装置

Families Citing this family (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107705785A (zh) * 2017-08-01 2018-02-16 百度在线网络技术（北京）有限公司 智能音箱的声源定位方法、智能音箱及计算机可读介质
CN107919124B (zh) * 2017-12-22 2021-07-13 北京小米移动软件有限公司 设备唤醒方法及装置
US11152006B2 (en) * 2018-05-07 2021-10-19 Microsoft Technology Licensing, Llc Voice identification enrollment
CN108877790A (zh) * 2018-05-21 2018-11-23 江西午诺科技有限公司 音箱控制方法、装置、可读存储介质及移动终端
CN109166571B (zh) * 2018-08-06 2020-11-24 广东美的厨房电器制造有限公司 家电设备的唤醒词训练方法、装置及家电设备
CN109032554B (zh) * 2018-06-29 2021-11-16 联想(北京)有限公司 一种音频处理方法和电子设备
CN110827824B (zh) * 2018-08-08 2022-05-17 Oppo广东移动通信有限公司 语音处理方法、装置、存储介质及电子设备
CN112740321A (zh) * 2018-11-20 2021-04-30 深圳市欢太科技有限公司 唤醒设备的方法、装置、存储介质及电子设备
CN111354357A (zh) * 2018-12-24 2020-06-30 中移（杭州）信息技术有限公司 一种音频资源播放的方法、装置、电子设备及存储介质
CN109887508A (zh) * 2019-01-25 2019-06-14 广州富港万嘉智能科技有限公司 一种基于声纹的会议自动记录方法、电子设备及存储介质
CN110119083A (zh) * 2019-04-17 2019-08-13 惠州市惠泽电器有限公司 智能手表的唤醒方法
CN110134233B (zh) * 2019-04-24 2022-07-12 福建联迪商用设备有限公司 一种基于人脸识别的智能音箱唤醒方法及终端
JP6856697B2 (ja) * 2019-04-24 2021-04-07 ヤフー株式会社 情報処理装置、情報処理方法、情報処理プログラム、学習装置、学習方法および学習プログラム
CN112309383A (zh) * 2019-08-01 2021-02-02 北京声智科技有限公司 语音交互方法、装置及机顶盒
CN110473556B (zh) * 2019-09-17 2022-06-21 深圳市万普拉斯科技有限公司 语音识别方法、装置和移动终端
CN110782891B (zh) * 2019-10-10 2022-02-18 珠海格力电器股份有限公司 一种音频处理方法、装置、计算设备及存储介质
CN110827836B (zh) * 2019-10-23 2022-05-03 珠海格力电器股份有限公司 一种重设唤醒词的方法、装置、电子设备及存储介质
CN110989963B (zh) * 2019-11-22 2023-08-01 北京梧桐车联科技有限责任公司 唤醒词推荐方法及装置、存储介质
CN110827820B (zh) * 2019-11-27 2022-09-27 北京梧桐车联科技有限责任公司 语音唤醒方法、装置、设备、计算机存储介质及车辆
CN113593541B (zh) * 2020-04-30 2024-03-12 阿里巴巴集团控股有限公司 数据处理方法、装置、电子设备和计算机存储介质
CN111696555A (zh) * 2020-06-11 2020-09-22 北京声智科技有限公司 一种唤醒词的确认方法及系统
CN111880988B (zh) * 2020-07-09 2022-11-04 Oppo广东移动通信有限公司 一种声纹唤醒日志收集方法及装置
CN111899722B (zh) * 2020-08-11 2024-02-06 Oppo广东移动通信有限公司 一种语音处理方法及装置、存储介质
CN112233676A (zh) * 2020-11-20 2021-01-15 深圳市欧瑞博科技股份有限公司 智能设备唤醒方法、装置、电子设备及存储介质
CN112951229A (zh) * 2021-02-07 2021-06-11 深圳市今视通数码科技有限公司 理疗机器人的语音唤醒方法、系统和存储介质
CN115312068B (zh) * 2022-07-14 2023-05-09 荣耀终端有限公司 语音控制方法、设备及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040101112A1 (en) * 2002-11-26 2004-05-27 Lite-On Technology Corporation Voice identification method for cellular phone and cellular phone with voiceprint password
EP2509291A1 (en) * 2011-04-06 2012-10-10 Research In Motion Limited System and method for locating a misplaced mobile device
CN103051781A (zh) * 2012-12-07 2013-04-17 百度在线网络技术（北京）有限公司 语音后台控制方法及移动终端
CN104143326A (zh) * 2013-12-03 2014-11-12 腾讯科技（深圳）有限公司 一种语音命令识别方法和装置
CN104202486A (zh) * 2014-09-26 2014-12-10 上海华勤通讯技术有限公司 移动终端及其屏幕解锁方法
CN104217152A (zh) * 2014-09-23 2014-12-17 陈包容 一种移动终端在待机状态下进入应用程序的实现方法和装置
CN104575504A (zh) * 2014-12-24 2015-04-29 上海师范大学 采用声纹和语音识别进行个性化电视语音唤醒的方法
CN104658533A (zh) * 2013-11-20 2015-05-27 中兴通讯股份有限公司 一种终端解锁的方法、装置及终端

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11194795A (ja) * 1997-12-26 1999-07-21 Kyocera Corp 音声認識作動装置
JP4897040B2 (ja) * 2007-03-14 2012-03-14 パイオニア株式会社 音響モデル登録装置、話者認識装置、音響モデル登録方法及び音響モデル登録処理プログラム
US8775187B2 (en) * 2008-09-05 2014-07-08 Auraya Pty Ltd Voice authentication system and methods
JP2010152423A (ja) * 2008-12-24 2010-07-08 Brother Ind Ltd 個人認証装置、個人認証方法、および個人認証プログラム
US8871260B2 (en) * 2012-09-19 2014-10-28 Transdermal Biotechnology, Inc. Methods and compositions for muscular and neuromuscular diseases
US9691377B2 (en) * 2013-07-23 2017-06-27 Google Technology Holdings LLC Method and device for voice recognition training
JP2014092777A (ja) * 2012-11-06 2014-05-19 Magic Hand:Kk モバイル通信機器の音声による起動
US10134392B2 (en) * 2013-01-10 2018-11-20 Nec Corporation Terminal, unlocking method, and program
WO2015005927A1 (en) * 2013-07-11 2015-01-15 Intel Corporation Device wake and speaker verification using the same audio input
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
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
CN104282307A (zh) * 2014-09-05 2015-01-14 中兴通讯股份有限公司 唤醒语音控制系统的方法、装置及终端

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040101112A1 (en) * 2002-11-26 2004-05-27 Lite-On Technology Corporation Voice identification method for cellular phone and cellular phone with voiceprint password
EP2509291A1 (en) * 2011-04-06 2012-10-10 Research In Motion Limited System and method for locating a misplaced mobile device
CN103051781A (zh) * 2012-12-07 2013-04-17 百度在线网络技术（北京）有限公司 语音后台控制方法及移动终端
CN104658533A (zh) * 2013-11-20 2015-05-27 中兴通讯股份有限公司 一种终端解锁的方法、装置及终端
CN104143326A (zh) * 2013-12-03 2014-11-12 腾讯科技（深圳）有限公司 一种语音命令识别方法和装置
CN104217152A (zh) * 2014-09-23 2014-12-17 陈包容 一种移动终端在待机状态下进入应用程序的实现方法和装置
CN104202486A (zh) * 2014-09-26 2014-12-10 上海华勤通讯技术有限公司 移动终端及其屏幕解锁方法
CN104575504A (zh) * 2014-12-24 2015-04-29 上海师范大学 采用声纹和语音识别进行个性化电视语音唤醒的方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3385947A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109584860A (zh) * 2017-09-27 2019-04-05 九阳股份有限公司 一种语音唤醒词定义方法和系统
CN110400568A (zh) * 2018-04-20 2019-11-01 比亚迪股份有限公司 智能语音系统的唤醒方法、智能语音系统及车辆
CN109003611A (zh) * 2018-09-29 2018-12-14 百度在线网络技术（北京）有限公司 用于车辆语音控制的方法、装置、设备和介质
CN112201239A (zh) * 2020-09-25 2021-01-08 海尔优家智能科技（北京）有限公司 目标设备的确定方法及装置、存储介质、电子装置

Also Published As

Publication number Publication date
EP3385947A1 (en) 2018-10-10
US20180350372A1 (en) 2018-12-06
JP2019502947A (ja) 2019-01-31
CN106815507A (zh) 2017-06-09
EP3385947A4 (en) 2018-12-05

Similar Documents

Publication Publication Date Title
WO2017092189A1 (zh) 语音唤醒实现方法、装置及终端、计算机存储介质
CN105989333B (zh) 指纹认证方法、系统及支持指纹认证功能的终端
CN106782536B (zh) 一种语音唤醒方法及装置
US20200227049A1 (en) Method, apparatus and device for waking up voice interaction device, and storage medium
US20170344802A1 (en) Method and device for fingerprint unlocking and user terminal
CN107112017A (zh) 操作语音识别功能的电子设备和方法
WO2015074411A1 (zh) 一种终端解锁的方法、装置及终端
JP2019128938A (ja) 読話による音声ウェイクアップ方法、装置、設備及びコンピュータ可読媒体
CN108766438A (zh) 人机交互方法、装置、存储介质及智能终端
US20190130411A1 (en) Method and system for data processing
CN106297801A (zh) 语音处理方法及装置
CN110290280B (zh) 一种终端状态的识别方法、装置及存储介质
EP3407256A1 (en) Recognizing biological feature
CN110546641B (zh) 一种访问控制方法、装置、智能设备及存储介质
WO2016198019A1 (zh) 一种电子设备的操作方法、装置及电子设备
CN110544468B (zh) 应用唤醒方法、装置、存储介质及电子设备
US20180032533A1 (en) Tool for mining chat sessions
US20090006857A1 (en) Method and apparatus for starting up a computing system
CN106531168B (zh) 一种语音识别方法及装置
WO2021169711A1 (zh) 指令执行方法、装置、存储介质及电子设备
CN106782498A (zh) 语音信息播放方法、装置及终端
US10818298B2 (en) Audio processing
CN110164431B (zh) 一种音频数据处理方法及装置、存储介质
CN110046276A (zh) 一种语音中关键词的检索方法和装置
CN112740321A (zh) 唤醒设备的方法、装置、存储介质及电子设备

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: 16869503

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2018527923

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2016869503

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2016869503

Country of ref document: EP

Effective date: 20180702