WO2017096843A1 - 头戴设备的控制方法和装置 - Google Patents

头戴设备的控制方法和装置 Download PDF

Info

Publication number
WO2017096843A1
WO2017096843A1 PCT/CN2016/088884 CN2016088884W WO2017096843A1 WO 2017096843 A1 WO2017096843 A1 WO 2017096843A1 CN 2016088884 W CN2016088884 W CN 2016088884W WO 2017096843 A1 WO2017096843 A1 WO 2017096843A1
Authority
WO
WIPO (PCT)
Prior art keywords
audio information
information
recognition result
standard
collected
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2016/088884
Other languages
English (en)
French (fr)
Inventor
陈相金
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Le Holdings Beijing Co Ltd
Leshi Zhixin Electronic Technology Tianjin Co Ltd
Original Assignee
Le Holdings Beijing Co Ltd
Leshi Zhixin Electronic Technology Tianjin Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Le Holdings Beijing Co Ltd, Leshi Zhixin Electronic Technology Tianjin Co Ltd filed Critical Le Holdings Beijing Co Ltd
Priority to US15/247,569 priority Critical patent/US20170169820A1/en
Publication of WO2017096843A1 publication Critical patent/WO2017096843A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G5/00—Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators
    • G09G5/003—Details of a display terminal, the details relating to the control arrangement of the display terminal and to the interfaces thereto
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Definitions

  • Embodiments of the present invention relate to the field of headset devices, and in particular, to a method and apparatus for controlling a headset.
  • the headset usually has a matching remote controller, and the user can control the headset through the remote controller, or for the convenience of the user, a small number of buttons can be set on the headset, and the user can press the button. Wear equipment for control.
  • the inventors have found that in the above-mentioned manner controlled by the remote controller in the prior art, it is necessary to configure an additional accessory, which is inconvenient for the user to carry; in the above manner of controlling by the button, since the physical button usually takes mechanical contact The method is implemented, so it has defects in the service life, and since the head-wearing device needs to be worn on the head, the user needs to intuitively and tactilely sense the position of the button to perform the manipulation, and the user experience is poor.
  • the embodiment of the invention provides a method and a device for controlling a head-mounted device, which are used to solve the problem that the control technology of the head-mounted device is inconvenient and the user experience is poor.
  • An embodiment of the present invention provides a method for controlling a headset, including:
  • a control operation indicated by the recognition result is performed according to the recognition result.
  • An embodiment of the present invention provides a control device for a headset, including:
  • a determining module configured to determine whether the audio information collected by the collecting component on the headset is valid voice information
  • An identification module configured to identify the valid voice information when the determination result of the determining module is YES, to obtain a recognition result
  • control module configured to perform a control operation indicated by the recognition result according to the recognition result.
  • An embodiment of the present invention provides a computer program comprising computer readable code that causes the head mounted device to perform the above-described control method of the headset when the computer readable code is run on the headset.
  • Embodiments of the present invention provide a computer readable medium in which the above computer program is stored.
  • the control method and device for the headset device provided by the embodiment of the present invention are provided with an acquisition component for collecting audio information on the headset, and when the acquisition component collects the audio information, determining whether the audio information is valid voice information, if Then, the effective voice information is identified to obtain the recognition result, and then the head device can perform the control operation of the recognition result indication. Therefore, in the embodiment of the present invention, the headset device can be controlled by voice, so that the control of the headset device is more convenient and the user experience is improved without further control by using a button or a remote controller.
  • FIG. 1 is a flow chart showing the steps of a method for controlling a head mounted device according to Embodiment 1 of the present invention
  • FIG. 2 is a flow chart showing the steps of a method for controlling a head mounted device according to Embodiment 2 of the present invention
  • FIG. 3 is a schematic structural diagram of a head wear device according to Embodiment 2 of the present invention.
  • FIG. 4 is a structural block diagram of a control device for a head mounted device according to a third embodiment of the present invention.
  • FIG. 5 is a structural block diagram of a control device for a head mounted device according to Embodiment 4 of the present invention.
  • Figure 6 shows schematically a block diagram of a headset for carrying out the method according to the invention
  • Fig. 7 schematically shows a storage unit for holding or carrying program code implementing the method according to the invention.
  • FIG. 1 a flow chart of steps of a method for controlling a head mounted device according to a first embodiment of the present invention is shown.
  • Step 101 Determine whether the audio information collected by the collection component on the headset is valid voice information.
  • the headwear device includes, but is not limited to, a virtual helmet, virtual glasses, a riding helmet, and the like.
  • An acquisition component such as a microphone (MIC) or the like is set in advance on the headset, and the acquisition component is configured to collect external audio information, so as to realize the headset control by voice.
  • MIC microphone
  • the headset does not respond to all audio information, but only responds to valid voice information, such as noise information of the outside world or voice information that does not correspond to the headset, even if the collection component collects The above-mentioned noise information or voice information is not processed by the head-mounted device, and the above-mentioned noise information and voice information are invalid voice information. Therefore, after the collection component collects the audio information, the embodiment first determines whether the audio information is valid voice information, and then performs a corresponding operation according to the determination result.
  • Step 102 if yes, identifying the valid voice information to obtain a recognition result.
  • step 101 If it is determined in step 101 that the collected audio information is valid voice information, it will be further improved. Steps to identify the valid voice information, and obtain a recognition result, the recognition result is used to indicate a control operation on the headset device, and the headset device can perform the control operation indicated by the recognition result in response to the recognition result, thereby achieving voice control The purpose of wearing a device.
  • Step 103 Perform a control operation indicated by the recognition result according to the recognition result.
  • the control method of the headset device provided by the embodiment of the present invention is provided with an acquisition component for collecting audio information on the headset, and when the acquisition component collects the audio information, determining whether the audio information is valid voice information, and if so, The effective voice information is identified to obtain the recognition result, and then the head device can perform the control operation of the recognition result indication. Therefore, in the embodiment of the present invention, the headset device can be controlled by voice, so that the control of the headset device is more convenient and the user experience is improved without further control by using a button or a remote controller.
  • FIG. 2 a flow chart of steps of a method for controlling a head mounted device according to a second embodiment of the present invention is shown.
  • step 201 the collection component on the headset collects audio information.
  • the headset can include a MIC, a voice processing chip, a CPU (Central Processing Unit), and a WiFi (Wireless-Fidelity) module.
  • the MIC is an acquisition component, which is mainly used for collecting audio information, and the collected audio information (Audio) is sent to the voice processing chip for processing; the voice processing chip is mainly used for voice wake-up, voice noise reduction processing, etc.; Used for local voice recognition, local voice control, voice messaging to the cloud, and more.
  • the voice processing chip and the CPU can exchange commands and status through IIC (Inter Integrated Circuit), and can also control the CPU through interrupt (INT) (such as waking up the CPU, etc.), and can also send Audio to the CPU.
  • IIC Inter Integrated Circuit
  • INT interrupt
  • An SDIO Secure Digital Input and Output Card
  • the CPU can send audio information to the cloud server through the WiFi module, and the cloud server can perform voice recognition on the audio information.
  • the embodiment uses the collecting component to collect the audio information, and controls the head-mounted device through a series of processes of voice wake-up, voice recognition, and voice control. Detailed discussion.
  • Step 202 Determine whether the collected audio information is valid voice information. If yes, step 203 is performed; if not, the setting operation is performed.
  • This step corresponds to the voice wakeup process. Initially, the system of the headset is in the standby state, and the MIC is in the low-power listening mode to monitor whether there is audio information. After the MIC collects the audio information, the voice processing chip processes the audio information to confirm whether the audio information is Effective voice information.
  • the step 202 can include the following sub-steps:
  • Sub-step a1 comparing the collected audio information with a preset plurality of standard audio information for signal waveforms; if there is standard audio information that is successfully matched with the collected audio information, performing sub-step a2; if not Subsequent step a3 is performed by comparing the successfully obtained standard audio information with the collected audio information.
  • a plurality of standard audio information corresponding to the headset device may be preset in advance.
  • the corresponding audio information such as “LeTV, Hello” may be set as standard audio information.
  • the collected audio information and the preset standard audio information are audio signal waveforms, and the collected audio information can be compared with the standard audio information, and the standard audio information is effective voice for the headset device. Information, so if the collected audio information is successfully compared with a certain standard audio information, it can be determined that the collected audio information is valid voice information.
  • the sub-step a1 may include:
  • A11 comparing the first piece of audio information from the start to the set time in the collected audio information with a preset plurality of standard audio information; if there is no standard for successful comparison with the first piece of audio information For audio information, a12 is executed; if there is standard audio information that is successfully compared with the first piece of audio information, a13 is executed.
  • the audio information collected by the acquisition component may be noise information in the external environment, not voice information. For example, when wearing the headset in a noisy environment, the acquisition component may collect pure noise. Sound information. If the collected audio information is noise information, it is not necessary to compare the entire audio information when comparing the collected audio information with the standard audio information, and only need to compare a small piece of audio information, thereby reducing the processing process. The complexity.
  • the first piece of audio information from the start to the set time in the collected audio information is first compared with the preset plurality of standard audio information, if the first piece of audio does not exist
  • the information is compared with the successful standard audio information, and then the collected audio information can be determined as noise information, so the comparison will be stopped, and it is determined that there is no standard audio information that is successfully matched with the collected audio information.
  • the comparison success means that the signal waveforms of the two are the same.
  • a person skilled in the art can perform related setting according to actual experience, for example, it can be set to 10 ms, 30 ms, etc., which is not limited by the embodiment of the present invention.
  • A13 If there is standard audio information that is successfully compared with the first piece of audio information, continue to save the second piece of audio information except the first piece of audio information in the collected audio information and the standard audio information that is successfully compared. Performing signal waveform comparison; if there is no standard audio information that is successfully compared with the second piece of audio information, a14 is performed; if there is standard audio information that is successfully compared with the second piece of audio information, a15 is performed.
  • the collected audio information is not noise information, and in this case, the remaining audio information except the first piece of audio information continues to be collected.
  • the second piece of audio information is compared with the standard audio information of the comparison (here, the successful standard audio information refers to the standard audio information that is successfully compared with the first piece of audio information).
  • the collected audio information is voice information, but it is not valid voice information, so in this case, it is determined that there is no audio with the collected audio.
  • Information compares to successful standard audio information.
  • the standard audio information that is successfully compared with the second piece of audio information is standard audio information that is successfully matched with the collected audio information.
  • Sub-step a2 if there is standard audio information that is successfully matched with the collected audio information, determining that the collected audio information is valid voice information;
  • Sub-step a3 if there is no standard audio information that is successfully matched with the collected audio information, it is determined that the collected audio information is invalid voice information.
  • Step 203 if yes, identifying the valid voice information to obtain a recognition result.
  • This step corresponds to the speech recognition process. If the collected audio information is invalid voice information, such as the above-mentioned noise information and the audio information that is not successfully compared with the standard audio information, the voice processing chip does not respond, and the system will continue to maintain the low power state; if the collected audio When the information is valid voice information, the voice processing chip wakes up the CPU and the system enters a normal working state.
  • the voice processing chip If the collected audio information is invalid voice information, such as the above-mentioned noise information and the audio information that is not successfully compared with the standard audio information, the voice processing chip does not respond, and the system will continue to maintain the low power state; if the collected audio When the information is valid voice information, the voice processing chip wakes up the CPU and the system enters a normal working state.
  • the voice processing chip sends valid voice information to the CPU for identification.
  • the voice processing chip may further perform noise reduction processing on the valid voice information, and then send the processing to the CPU.
  • noise and useful information in valid voice information can be separated by techniques such as blind source separation for noise reduction processing.
  • Blind source separation problem is the process of recovering the source signal only from the observed mixed signal according to the statistical characteristics of the source signal without knowing the prior information of the source signal and the transmission channel.
  • the blind source separation of the speech signal is blind.
  • a very important branch of the source separation technique for example, an independent component analysis (ICA) algorithm can be used for blind source separation.
  • ICA independent component analysis
  • the step of identifying the valid voice information, and obtaining the recognition result may include the following sub-steps:
  • Sub-step b1 the valid voice information is identified locally; if the local recognition result can be obtained, sub-step b2 is performed; if the local recognition result is not obtained, sub-step b3 is performed.
  • the local CPU recognizes the valid voice information, and the sub-step b1 may include:
  • the CPU can convert the valid voice information into the text information by using the set software algorithm (such as the Keda Xunfei, the music video, etc.).
  • the set software algorithm such as the Keda Xunfei, the music video, etc.
  • the person skilled in the art can perform related processing according to the actual experience, and the embodiment of the present invention This will not be discussed in detail.
  • a local command library is preset, and the local command library may include multiple standard text information, such as power on, power off, volume up, volume down, etc., and the converted text information and the local command library.
  • a search match is made to determine whether there is standard text information that matches the converted text information. Wherein, matching may mean that the converted text information is the same as the standard text information.
  • Sub-step b2 if the local recognition result can be obtained, the local recognition result is used as the recognition result;
  • Sub-step b3 if the local recognition result is not obtained, the valid voice information is sent to the cloud server, so that the cloud server identifies the valid voice information to obtain the cloud recognition result, receives the cloud recognition result returned by the cloud server, and uses the cloud recognition result as the cloud recognition result. Identify the results.
  • the local recognition result is used as the final recognition result, and the head wear device is controlled according to the recognition result.
  • the head wear device is controlled according to the recognition result.
  • Send to the cloud server and identify the valid voice information through the cloud server to obtain the cloud recognition result.
  • the cloud server obtains the corresponding text information by performing semantic analysis on the valid voice information, and performs corresponding operations according to the text information. For example, if the valid voice information is related to the audio and video resource search, the cloud server searches for audio and video resources. The audio and video resource search result is used as the cloud recognition result, and if the effective voice information is the map navigation information query related information, the cloud server performs the map query, and the navigation information query result is obtained as the cloud recognition result. After the cloud server identifies the result, the cloud recognition result is sent to the headset device locally, and the cloud recognition result is used as the recognition result locally.
  • Step 204 Perform a control operation indicated by the recognition result according to the recognition result.
  • This step corresponds to the voice manipulation process.
  • the head wear device After the local recognition result is obtained, the head wear device automatically performs the control operation indicated by the recognition result according to the recognition result.
  • the recognition result includes local identification Results and cloud recognition results.
  • the local recognition result may be an instruction capable of simply controlling the head mounted device, such as power on, power off, volume up, volume down, etc., and the headwear device performs a corresponding operation in response to the local recognition result.
  • the cloud recognition result may be some information obtained through the cloud server search, such as audio and video resource search result, navigation information query result, etc., after receiving the cloud recognition result, the headset may interact with the user, such as prompting the user whether to display, After playing the cloud search result, etc., after the user determines, the headset receives the determination instruction, performs operations such as displaying and playing the cloud search result.
  • the headset may interact with the user, such as prompting the user whether to display, After playing the cloud search result, etc., after the user determines, the headset receives the determination instruction, performs operations such as displaying and playing the cloud search result.
  • the audio information is collected by the microphone, transmitted to the voice processing chip for noise reduction processing (to improve the recognition rate), and the CPU is awakened, and the processed valid voice information is sent to the CPU for local or cloud server for voice recognition, and then according to The recognition result is controlled accordingly, so that it is no longer necessary to control by the button or the remote controller, which makes the control of the head wear device more convenient and improves the user experience.
  • FIG. 4 a block diagram of a control device of a head mounted device according to a third embodiment of the present invention is shown.
  • a determining module 401 configured to determine whether the audio information collected by the collecting component on the headset is valid voice information
  • the identifying module 402 is configured to identify the valid voice information when the determining result of the determining module is YES, and obtain the recognition result;
  • the control module 403 is configured to perform a control operation indicated by the recognition result according to the recognition result.
  • the control device of the headset device provided by the embodiment of the present invention is provided with an acquisition component for collecting audio information on the headset, and when the acquisition component collects the audio information, determining whether the audio information is valid voice information, and if so, Identifying valid voice information to get the recognition result, then
  • the head-mounted device can perform the control operation of the recognition result indication. Therefore, in the embodiment of the present invention, the headset device can be controlled by voice, so that the control of the headset device is more convenient and the user experience is improved without further control by using a button or a remote controller.
  • FIG. 5 there is shown a block diagram showing the structure of a control device for a head mounted device according to a fourth embodiment of the present invention.
  • a determining module 501 configured to determine whether the audio information collected by the collecting component on the headset is valid voice information
  • the identifying module 502 is configured to identify the valid voice information when the determining result of the determining module is YES, and obtain the recognition result;
  • the control module 503 is configured to perform a control operation indicated by the recognition result according to the recognition result.
  • the determining module 501 includes: an information comparison sub-module 5011, configured to compare the collected audio information with a preset plurality of standard audio information, and the information determining sub-module 5012 is configured to exist and collect When the obtained audio information is compared with the successful standard audio information, it is determined that the collected audio information is valid voice information; when there is no standard audio information that is successful compared with the collected audio information, it is determined that the collected audio information is invalid. voice message.
  • the information comparison sub-module 5011 includes: a first comparison sub-unit 50111, configured to perform the first piece of audio information from the start to the set time and the preset plurality of standard audio information in the collected audio information.
  • the second comparison subunit 50112 is configured to continue to save the collected audio information except the first piece of audio information when there is standard audio information that is successfully compared with the first piece of audio information.
  • the second piece of audio information is compared with the standard audio information that is successfully compared; the comparison determining subunit 50113 is configured to stop the comparison when there is no standard audio information that is successfully compared with the first piece of audio information.
  • the identification module 502 includes: a local identification sub-module 5021 for validating locally The voice information is identified; if the local recognition result is obtained, the local recognition result is used as the recognition result; the cloud recognition sub-module 5022 is configured to send the valid voice information to the cloud server when the local recognition sub-module does not obtain the local recognition result, The cloud server identifies the valid voice information to obtain the cloud recognition result, receives the cloud recognition result returned by the cloud server, and uses the cloud recognition result as the recognition result.
  • the local identification sub-module 5021 includes: an information conversion sub-unit 50211, configured to locally convert the valid voice information into text information; and the information matching sub-unit 50212 is configured to convert the converted text information with a preset plurality of standards.
  • the text information is matched; the result determining sub-unit 50213 is configured to use the matched standard text information as a local recognition result when there is standard text information matching the converted text information; and the text information obtained in the absence and conversion When matching the standard text information, it is determined that the local recognition result is not obtained.
  • the audio information is collected by the microphone, transmitted to the voice processing chip for noise reduction processing (to improve the recognition rate), and the CPU is awakened, and the processed valid voice information is sent to the CPU for local or cloud server for voice recognition, and then according to The recognition result is controlled accordingly, so that it is no longer necessary to control by the button or the remote controller, which makes the control of the head-mounted device more convenient and improves the user experience.
  • the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.
  • FIG. 6 shows that a headset can be implemented in accordance with the present invention.
  • the headset typically includes a processor 610 and a computer program product or computer readable medium in the form of a memory 620.
  • the memory 620 may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), an EPROM, a hard disk, or a ROM.
  • Memory 620 has a memory space 630 for program code 631 for performing any of the method steps described above.
  • storage space 630 for program code may include various program code 631 for implementing various steps in the above methods, respectively.
  • the program code can be read from or written to one or more computer program products.
  • Such computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks.
  • Such a computer program product is typically a portable or fixed storage unit as described with reference to FIG.
  • the storage unit may have a storage section, a storage space, and the like arranged similarly to the storage 620 in the headset of FIG.
  • the program code can be compressed, for example, in an appropriate form.
  • the storage unit includes computer readable code 631', ie, code that can be read by a processor, such as 610, that when run by the headset, causes the headset to perform the method described above The various steps.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Hardware Design (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种头戴设备的控制方法和装置。其中方法包括：确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息（101）；若是，则对有效语音信息进行识别，得到识别结果（102）；依据识别结果执行识别结果指示的控制操作（103）。该方法通过语音对头戴设备进行控制，从而无需再通过按键或遥控器进行控制，使头戴设备的控制更加方便，提升用户体验。

Description

头戴设备的控制方法和装置
本申请要求在2015年12月10日提交中国专利局、申请号为201510926119.6、发明名称为“头戴设备的控制方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明实施例涉及头戴设备技术领域，尤其涉及一种头戴设备的控制方法和装置。
背景技术
随着科技的飞速发展，多种多样的智能设备走进人们的生活，头戴设备作为一种智能设备越来越受到广大用户的喜爱，用户可以通过头戴设备更方便地进行各种各样的操控。
在现有技术中，头戴设备通常具有配套的遥控器，用户可以通过遥控器对头戴设备进行控制，或者为了方便用户使用，在头戴设备上可以设置少量按键，用户可以通过按键对头戴设备进行控制。
但是在实现本发明过程中，发明人发现现有技术中上述通过遥控器控制的方式中需要配置额外的配件，不便于用户携带；上述通过按键控制的方式中，由于实体按键通常采取机械接触的方式来实现，故其在使用寿命上存在缺陷，并且由于头戴设备需戴在头部使用，用户需要凭借直觉和触觉感知按键位置进行操控，用户体验较差。
发明内容
本发明实施例提供一种头戴设备的控制方法和装置，用以解决现有对头戴设备的控制技术中，控制不方便，用户体验差的问题。
本发明实施例提供一种头戴设备的控制方法，包括：
确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息；
若是，则对所述有效语音信息进行识别，得到识别结果；
依据所述识别结果执行所述识别结果指示的控制操作。
本发明实施例提供一种头戴设备的控制装置，包括：
确定模块，用于确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息；
识别模块，用于在所述确定模块的确定结果为是时，对所述有效语音信息进行识别，得到识别结果；
控制模块，用于依据所述识别结果执行所述识别结果指示的控制操作。
本发明实施例提供一种计算机程序，其包括计算机可读代码，当所述计算机可读代码在头戴设备上运行时，导致所述头戴设备执行上述的头戴设备的控制方法。
本发明实施例提供一种计算机可读介质，其中存储了上述的计算机程序。
本发明实施例提供的头戴设备的控制方法和装置，在头戴设备上设置有用于采集音频信息的采集部件，当采集部件采集到音频信息时，确定该音频信息是否为有效语音信息，若是，则对有效语音信息进行识别得到识别结果，然后头戴设备即可执行识别结果指示的控制操作。由此可知，本发明实施例中可以通过语音对头戴设备进行控制，从而无需再通过按键或遥控器进行控制，使头戴设备的控制更加方便，提升用户体验。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，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，还可以根据这些附图获得其他的附图。
图1为本发明实施例一的一种头戴设备的控制方法的步骤流程图；
图2为本发明实施例二的一种头戴设备的控制方法的步骤流程图；
图3为本发明实施例二的一种头戴设备的结构示意图；
图4为本发明实施例三的一种头戴设备的控制装置的结构框图；
图5为本发明实施例四的一种头戴设备的控制装置的结构框图；
图6示意性地示出了用于执行根据本发明的方法的头戴设备的框图；以及
图7示意性地示出了用于保持或者携带实现根据本发明的方法的程序代码的存储单元。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例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作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
实施例一
参照图1，示出了本发明实施例一的一种头戴设备的控制方法的步骤流程图。
本发明实施例的头戴设备的控制方法可以包括以下步骤：
步骤101，确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息。
本发明实施例中，头戴设备包括但不限于虚拟头盔、虚拟眼镜、骑行头盔等。预先在头戴设备上设置采集部件，如麦克风(MIC)等，该采集部件用于对外界的音频信息进行采集，以便实现通过语音控制头戴设备。
为了降低功耗，头戴设备并非对全部的音频信息都进行响应，而是仅对有效语音信息进行响应，例如对于外界的噪音信息或者与头戴设备不对应的语音信息，即使采集部件采集到上述噪音信息或者语音信息，头戴设备也不会对其进行处理，上述噪音信息和语音信息即为无效语音信息。故本发明实施例在采集部件采集到音频信息后，首先确定该音频信息是否为有效语音信息，然后根据确定结果执行相应的操作。
步骤102，若是，则对有效语音信息进行识别，得到识别结果。
如果在步骤101中确定出采集到的音频信息为有效语音信息，则将进一 步对该有效语音信息进行识别，得到识别结果，该识别结果用于指示对头戴设备的控制操作，头戴设备可以响应该识别结果，执行该识别结果指示的控制操作，从而达到通过语音控制头戴设备的目的。
步骤103，依据识别结果执行识别结果指示的控制操作。
本发明实施例对上述各个步骤进行了简单描述，对于上述各个步骤的具体过程，将在实施例二中进行详细论述。
本发明实施例提供的头戴设备的控制方法，在头戴设备上设置有用于采集音频信息的采集部件，当采集部件采集到音频信息时，确定该音频信息是否为有效语音信息，若是，则对有效语音信息进行识别得到识别结果，然后头戴设备即可执行识别结果指示的控制操作。由此可知，本发明实施例中可以通过语音对头戴设备进行控制，从而无需再通过按键或遥控器进行控制，使头戴设备的控制更加方便，提升用户体验。
实施例二
参照图2，示出了本发明实施例二的一种头戴设备的控制方法的步骤流程图。
本发明实施例的头戴设备的控制方法可以包括以下步骤：
步骤201，头戴设备上的采集部件采集音频信息。
参照图3，示出了本发明实施例二的一种头戴设备的结构示意图。该头戴设备可以包括MIC、语音处理芯片、CPU(Central Processing Unit，中央处理器)和WiFi(Wireless-Fidelity，无线保真)模块。其中，MIC即为采集部件，主要用于采集音频信息，并将采集的音频信息(Audio)送至语音处理芯片进行处理；语音处理芯片主要用于进行语音唤醒、语音降噪处理等；CPU主要用于进行本地语音识别、本地语音操控、语音信息送云端等。语音处理芯片与CPU之间可以通过IIC(Inter Integrated Circuit，集成电路总线)交换命令、状态等，还可以通过中断(INT)对CPU进行控制(如唤醒CPU等)，还可以将Audio发送至CPU。CPU与WiFi模块之间设置有SDIO(Secure Digital Input and Output Card，安全数字输入输出卡)接口，CPU可以通过WiFi模块将音频信息发送至云端服务器，云端服务器可以对音频信息进行语音识别。
本发明实施例为解决头戴设备控制不方便、用户体验差的问题，利用采集部件对音频信息进行采集，通过语音唤醒、语音识别、语音操控一系列流程来对头戴设备进行控制，以下将详细论述。
步骤202，确定采集到的音频信息是否为有效语音信息。若是，则执行步骤203；若否，则执行设定操作。
该步骤对应于语音唤醒流程。初始时头戴设备的系统处于待机状态，MIC处于低功耗监听模式，监听是否有音频信息，MIC采集到音频信息后，语音处理芯片对该音频信息进行相应处理，以确认该音频信息是否为有效语音信息。
优选地，该步骤202可以包括以下子步骤：
子步骤a1，将采集到的音频信息与预设的多个标准音频信息进行信号波形比对；若存在与采集到的音频信息比对成功的标准音频信息，则执行子步骤a2；若不存在与采集到的音频信息比对成功的标准音频信息，则执行子步骤a3。
本发明实施例中，可以针对头戴设备预先设置与其相对应的多个标准音频信息，如针对乐视的头戴设备，可以设置“乐视，您好”等对应的音频信息为标准音频信息。采集到的音频信息和预设的标准音频信息均为音频信号波形，可以将采集到的音频信息与标准音频信息进行信号波形比对，这些标准音频信息对该头戴设备来说即为有效语音信息，故如果采集到的音频信息与某个标准音频信息比对成功，则可以确定该采集到的音频信息为有效语音信息。
优选地，该子步骤a1可以包括：
a11，将采集到的音频信息中从开始到设定时间的第一段音频信息与预设的多个标准音频信息进行信号波形比对；若不存在与第一段音频信息比对成功的标准音频信息，则执行a12；若存在与第一段音频信息比对成功的标准音频信息，则执行a13。
a12，若不存在与第一段音频信息比对成功的标准音频信息，则停止比对，确定不存在与采集到的音频信息比对成功的标准音频信息；
采集部件采集到的音频信息有可能为外界环境中的噪音信息，而并非语音信息，如在嘈杂的环境中佩戴头戴设备时采集部件可能会采集到单纯的噪 音信息。如果采集到的音频信息是噪音信息，则在将采集到的音频信息与标准音频信息进行比对时无需将全段音频信息进行比对，仅需比较一小段音频信息即可，从而降低处理过程的复杂度。因此，在进行比对时首先将采集到的音频信息中从开始到设定时间的第一段音频信息与预设的多个标准音频信息进行信号波形比对，若不存在与第一段音频信息比对成功的标准音频信息，则可以确定采集到的音频信息为噪音信息，故将停止比对，并确定不存在与采集到的音频信息比对成功的标准音频信息。其中，比对成功是指比对的两者的信号波形相同。对于上述设定时间的具体数值，本领域技术人员根据实际经验进行相关设置即可，如可以设置为10ms、30ms等，本发明实施例对此并不加以限制。
a13，若存在与第一段音频信息比对成功的标准音频信息，则继续将采集到的音频信息中除第一段音频信息之外剩余的第二段音频信息与比对成功的标准音频信息进行信号波形比对；若不存在与第二段音频信息比对成功的标准音频信息，则执行a14；若存在与第二段音频信息比对成功的标准音频信息，则执行a15。
若存在与第一段音频信息比对成功的标准音频信息，则可以确定采集到的音频信息不是噪音信息，该种情况下继续将采集到的音频信息中除第一段音频信息之外剩余的第二段音频信息与比对成功的标准音频信息(此处比对成功的标准音频信息是指与第一段音频信息比对成功的标准音频信息)进行信号波形比对。
a14，若不存在与第二段音频信息比对成功的标准音频信息，则确定不存在与采集到的音频信息比对成功的标准音频信息；
若不存在与第二段音频信息比对成功的标准音频信息，则说明采集到的音频信息虽然为语音信息，但是并非是有效语音信息，故该种情况下仍然确定不存在与采集到的音频信息比对成功的标准音频信息。
a15，若存在与第二段音频信息比对成功的标准音频信息，则确定存在与采集到的音频信息比对成功的标准音频信息。
若存在与第二段音频信息比对成功的标准音频信息，则该与第二段音频信息比对成功的标准音频信息即为与采集到的音频信息比对成功的标准音频信息。
子步骤a2，若存在与采集到的音频信息比对成功的标准音频信息，则确定采集到的音频信息为有效语音信息；
子步骤a3，若不存在与采集到的音频信息比对成功的标准音频信息，则确定采集到的音频信息为无效语音信息。
步骤203，若是，则对有效语音信息进行识别，得到识别结果。
该步骤对应于语音识别流程。如果采集到的音频信息为无效语音信息，如上述的噪音信息及未与标准音频信息比对成功的音频信息，则语音处理芯片不作响应，系统将继续维持低功耗状态；如果采集到的音频信息为有效语音信息，则语音处理芯片将CPU唤醒，系统进入正常工作状态。
语音处理芯片将有效语音信息送往CPU进行识别。优选地，语音处理芯片还可以先对有效语音信息进行降噪处理，处理后再送至CPU。例如，可以通过盲源分离等技术将有效语音信息中的噪音和有用信息进行分离，以便进行降噪处理。盲源分离问题即在不知道源信号和传输通道的先验信息的情况下，根据源信号的统计特性，仅由观测到的混合信号恢复出源信号的过程，语音信号的盲源分离是盲源分离技术的一个非常重要的分支，例如可以利用独立量分析(independent component analysis，简称ICA)等算法进行盲源分离，对于盲源分离的具体过程，本领域技术人员根据实际经验进行相关处理即可，本发明实施例对此不再详细论述。
优选地，本发明实施例中对有效语音信息进行识别，得到识别结果的步骤可以包括以下子步骤：
子步骤b1，在本地对有效语音信息进行识别；若能够得到本地识别结果，则执行子步骤b2；若未得到本地识别结果，则执行子步骤b3。
首先在本地CPU对有效语音信息进行识别，该子步骤b1可以包括：
b11，在本地将有效语音信息转换为文本信息；
CPU可以将有效语音信息利用设定的软件算法(如科大讯飞、乐视语音等)转换为文本信息，对于转换的具体过程，本领域技术人员根据实际经验进行相关处理即可，本发明实施例对此不再详细论述。
b12，将转换得到的文本信息与预设的多个标准文本信息进行匹配；若存在与转换得到的文本信息相匹配的标准文本信息，则执行b13；若不存在与转换得到的文本信息相匹配的标准文本信息，则执行b14。
本发明实施例中，预先设置本地的命令库，该本地命令库中可以包括多个标准文本信息，如开机、关机、调大音量、调小音量等，将转换后的文本信息与本地命令库进行搜索匹配，确定是否存在与转换得到的文本信息相匹配的标准文本信息。其中，相匹配可以指转换得到的文本信息与标准文本信息相同。
b13，若存在与转换得到的文本信息相匹配的标准文本信息，则将相匹配的标准文本信息作为本地识别结果；
b14，若不存在与转换得到的文本信息相匹配的标准文本信息，则确定未得到本地识别结果。
子步骤b2，若能够得到本地识别结果，则将本地识别结果作为识别结果；
子步骤b3，若未得到本地识别结果，则将有效语音信息发送至云端服务器，以使云端服务器对有效语音信息进行识别得到云端识别结果，接收云端服务器返回的云端识别结果，将云端识别结果作为识别结果。
如果能够得到本地识别结果，则将本地识别结果作为最终识别结果，依据该识别结果对头戴设备进行控制。但是，基于本地的条件限制(如存储空间等的限制)，可能无法将对头戴设备对应的控制命令全部保存至本地命令库中，如有效语音信息为“现在北京什么天气”等，该种情况并非是简单地是对头戴设备进行开关机等的控制，而是还需要进行信息搜索等操作，因此还存在本地识别时未得到本地识别结果的情况，该种情况下CPU将有效语音信息发送至云端服务器，通过云端服务器对有效语音信息进行识别得到云端识别结果。云端服务器通过对有效语音信息进行语义分析，得到对应的文本信息，并根据该文本信息执行相应的操作，如有效语音信息为音视频资源搜索相关的信息，则云端服务器进行音视频资源搜索，得到音视频资源搜索结果作为云端识别结果，再如有效语音信息为地图导航信息查询相关的信息，则云端服务器进行地图查询，得到导航信息查询结果作为云端识别结果。云端服务器云端识别结果后，将云端识别结果发送至头戴设备本地，本地将该云端识别结果作为识别结果。
步骤204，依据识别结果执行识别结果指示的控制操作。
该步骤对应于语音操控流程。本地得到识别结果后，头戴设备将依据识别结果自动执行该识别结果指示的控制操作。其中，识别结果包括本地识别 结果和云端识别结果。本地识别结果可以为能够简单控制头戴设备的指令，如开机、关机、调大音量、调小音量等，头戴设备响应该本地识别结果执行相应的操作。云端识别结果可以为通过云端服务器搜索得到的一些信息，如音视频资源搜索结果、导航信息查询结果等，头戴设备接收到云端识别结果后，可以与用户进行交互操作，如提示用户是否显示、播放云端搜索结果等，用户在确定后，头戴设备接收到确定指令，进行显示、播放云端搜索结果等操作。
本实施例中通过麦克风对音频信息进行采集，传输到语音处理芯片进行降噪处理(以提高识别率)并唤醒CPU，处理后有效语音信息送往CPU进行本地或云端服务器进行语音识别，然后根据识别结果进行相应的控制操作，从而无需再通过按键或遥控器进行控制，使头戴设备的控制更加方便，提升用户体验。
对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，因为依据本发明，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本发明所必须的。
实施例三
参照图4，示出了本发明实施例三的一种头戴设备的控制装置的结构框图。
本发明实施例的头戴设备的控制装置可以包括以下模块：
确定模块401，用于确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息；
识别模块402，用于在确定模块的确定结果为是时，对有效语音信息进行识别，得到识别结果；
控制模块403，用于依据识别结果执行识别结果指示的控制操作。
本发明实施例提供的头戴设备的控制装置，在头戴设备上设置有用于采集音频信息的采集部件，当采集部件采集到音频信息时，确定该音频信息是否为有效语音信息，若是，则对有效语音信息进行识别得到识别结果，然后 头戴设备即可执行识别结果指示的控制操作。由此可知，本发明实施例中可以通过语音对头戴设备进行控制，从而无需再通过按键或遥控器进行控制，使头戴设备的控制更加方便，提升用户体验。
实施例四
参照图5，示出了本发明实施例四的一种头戴设备的控制装置的结构框图。
本发明实施例的头戴设备的控制装置可以包括以下模块：
确定模块501，用于确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息；
识别模块502，用于在确定模块的确定结果为是时，对有效语音信息进行识别，得到识别结果；
控制模块503，用于依据识别结果执行识别结果指示的控制操作。
优选地，确定模块501包括：信息比对子模块5011，用于将采集到的音频信息与预设的多个标准音频信息进行信号波形比对；信息确定子模块5012，用于在存在与采集到的音频信息比对成功的标准音频信息时，确定采集到的音频信息为有效语音信息；在不存在与采集到的音频信息比对成功的标准音频信息时，确定采集到的音频信息为无效语音信息。
优选地，信息比对子模块5011包括：第一比对子单元50111，用于将采集到的音频信息中从开始到设定时间的第一段音频信息与预设的多个标准音频信息进行信号波形比对；第二比对子单元50112，用于在存在与第一段音频信息比对成功的标准音频信息时，继续将采集到的音频信息中除第一段音频信息之外剩余的第二段音频信息与比对成功的标准音频信息进行信号波形比对；比对确定子单元50113，用于在不存在与第一段音频信息比对成功的标准音频信息时，停止比对，确定不存在与采集到的音频信息比对成功的标准音频信息；在不存在与第二段音频信息比对成功的标准音频信息时，确定不存在与采集到的音频信息比对成功的标准音频信息；在存在与第二段音频信息比对成功的标准音频信息时，确定存在与采集到的音频信息比对成功的标准音频信息。
优选地，识别模块502包括：本地识别子模块5021，用于在本地对有效 语音信息进行识别；若能够得到本地识别结果，则将本地识别结果作为识别结果；云端识别子模块5022，用于在本地识别子模块未得到本地识别结果时，将有效语音信息发送至云端服务器，以使云端服务器对有效语音信息进行识别得到云端识别结果，接收云端服务器返回的云端识别结果，将云端识别结果作为识别结果。
优选地，本地识别子模块5021包括：信息转换子单元50211，用于在本地将有效语音信息转换为文本信息；信息匹配子单元50212，用于将转换得到的文本信息与预设的多个标准文本信息进行匹配；结果确定子单元50213，用于在存在与转换得到的文本信息相匹配的标准文本信息时，将相匹配的标准文本信息作为本地识别结果；在不存在与转换得到的文本信息相匹配的标准文本信息时，确定未得到本地识别结果。
本实施例中通过麦克风对音频信息进行采集，传输到语音处理芯片进行降噪处理(以提高识别率)并唤醒CPU，处理后有效语音信息送往CPU进行本地或云端服务器进行语音识别，然后根据识别结果进行相应的控制操作，从而无需再通过按键或遥控器进行控制，使头戴设备的控制更加方便，提升用户体验
对于装置实施例而言，由于其与方法实施例基本相似，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台 计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
例如，图6示出了可以实现根据本发明的头戴设备。该头戴设备传统上包括处理器610和以存储器620形式的计算机程序产品或者计算机可读介质。存储器620可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器620具有用于执行上述方法中的任何方法步骤的程序代码631的存储空间630。例如，用于程序代码的存储空间630可以包括分别用于实现上面的方法中的各种步骤的各个程序代码631。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘，紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为如参考图7所述的便携式或者固定存储单元。该存储单元可以具有与图6的头戴设备中的存储器620类似布置的存储段、存储空间等。程序代码可以例如以适当形式进行压缩。通常，存储单元包括计算机可读代码631’，即可以由例如诸如610之类的处理器读取的代码，这些代码当由头戴设备运行时，导致该头戴设备执行上面所描述的方法中的各个步骤。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (12)

  1. 一种头戴设备的控制方法，其特征在于，包括：
    确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息；
    若是，则对所述有效语音信息进行识别，得到识别结果；
    依据所述识别结果执行所述识别结果指示的控制操作。
  2. 根据权利要求1所述的方法，其特征在于，所述确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息的步骤，包括：
    将所述采集到的音频信息与预设的多个标准音频信息进行信号波形比对；
    若存在与所述采集到的音频信息比对成功的标准音频信息，则确定所述采集到的音频信息为有效语音信息；
    若不存在与所述采集到的音频信息比对成功的标准音频信息，则确定所述采集到的音频信息为无效语音信息。
  3. 根据权利要求2所述的方法，其特征在于，所述将所述采集到的音频信息与预设的多个标准音频信息进行信号波形比对的步骤，包括：
    将所述采集到的音频信息中从开始到设定时间的第一段音频信息与预设的多个标准音频信息进行信号波形比对；
    若不存在与所述第一段音频信息比对成功的标准音频信息，则停止比对，确定不存在与所述采集到的音频信息比对成功的标准音频信息；
    若存在与所述第一段音频信息比对成功的标准音频信息，则继续将所述采集到的音频信息中除所述第一段音频信息之外剩余的第二段音频信息与所述比对成功的标准音频信息进行信号波形比对；
    若不存在与所述第二段音频信息比对成功的标准音频信息，则确定不存在与所述采集到的音频信息比对成功的标准音频信息；
    若存在与所述第二段音频信息比对成功的标准音频信息，则确定存在与所述采集到的音频信息比对成功的标准音频信息。
  4. 根据权利要求1所述的方法，其特征在于，所述对所述有效语音信息进行识别，得到识别结果的步骤，包括：
    在本地对所述有效语音信息进行识别；
    若能够得到本地识别结果，则将所述本地识别结果作为识别结果；
    若未得到本地识别结果，则将所述有效语音信息发送至云端服务器，以使所述云端服务器对所述有效语音信息进行识别得到云端识别结果，接收所述云端服务器返回的所述云端识别结果，将所述云端识别结果作为识别结果。
  5. 根据权利要求4所述的方法，其特征在于，所述在本地对所述有效语音信息进行识别的步骤，包括：
    在本地将所述有效语音信息转换为文本信息；
    将转换得到的文本信息与预设的多个标准文本信息进行匹配；
    若存在与所述转换得到的文本信息相匹配的标准文本信息，则将所述相匹配的标准文本信息作为本地识别结果；
    若不存在与所述转换得到的文本信息相匹配的标准文本信息，则确定未得到本地识别结果。
  6. 一种头戴设备的控制装置，其特征在于，包括：
    确定模块，用于确定头戴设备上的采集部件采集到的音频信息是否为有效语音信息；
    识别模块，用于在所述确定模块的确定结果为是时，对所述有效语音信息进行识别，得到识别结果；
    控制模块，用于依据所述识别结果执行所述识别结果指示的控制操作。
  7. 根据权利要求6所述的装置，其特征在于，所述确定模块包括：
    信息比对子模块，用于将所述采集到的音频信息与预设的多个标准音频信息进行信号波形比对；
    信息确定子模块，用于在存在与所述采集到的音频信息比对成功的标准音频信息时，确定所述采集到的音频信息为有效语音信息；在不存在与所述采集到的音频信息比对成功的标准音频信息时，确定所述采集到的音频信息为无效语音信息。
  8. 根据权利要求7所述的装置，其特征在于，所述信息比对子模块包括：
    第一比对子单元，用于将所述采集到的音频信息中从开始到设定时间的第一段音频信息与预设的多个标准音频信息进行信号波形比对；
    第二比对子单元，用于在存在与所述第一段音频信息比对成功的标准音频信息时，继续将所述采集到的音频信息中除所述第一段音频信息之外剩余 的第二段音频信息与所述比对成功的标准音频信息进行信号波形比对；
    比对确定子单元，用于在不存在与所述第一段音频信息比对成功的标准音频信息时，停止比对，确定不存在与所述采集到的音频信息比对成功的标准音频信息；在不存在与所述第二段音频信息比对成功的标准音频信息时，确定不存在与所述采集到的音频信息比对成功的标准音频信息；在存在与所述第二段音频信息比对成功的标准音频信息时，确定存在与所述采集到的音频信息比对成功的标准音频信息。
  9. 根据权利要求6所述的装置，其特征在于，所述识别模块包括：
    本地识别子模块，用于在本地对所述有效语音信息进行识别；若能够得到本地识别结果，则将所述本地识别结果作为识别结果；
    云端识别子模块，用于在本地识别子模块未得到本地识别结果时，将所述有效语音信息发送至云端服务器，以使所述云端服务器对所述有效语音信息进行识别得到云端识别结果，接收所述云端服务器返回的所述云端识别结果，将所述云端识别结果作为识别结果。
  10. 根据权利要求9所述的装置，其特征在于，所述本地识别子模块包括：
    信息转换子单元，用于在本地将所述有效语音信息转换为文本信息；
    信息匹配子单元，用于将转换得到的文本信息与预设的多个标准文本信息进行匹配；
    结果确定子单元，用于在存在与所述转换得到的文本信息相匹配的标准文本信息时，将所述相匹配的标准文本信息作为本地识别结果；在不存在与所述转换得到的文本信息相匹配的标准文本信息时，确定未得到本地识别结果。
  11. 一种计算机程序，包括计算机可读代码，当所述计算机可读代码在头戴设备上运行时，导致所述头戴设备执行根据权利要求1-5中的任一个所述的头戴设备的控制方法。
  12. 一种计算机可读介质，其中存储了如权利要求11所述的计算机程序。
PCT/CN2016/088884 2015-12-10 2016-07-06 头戴设备的控制方法和装置 Ceased WO2017096843A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/247,569 US20170169820A1 (en) 2015-12-10 2016-08-25 Electronic device and method for controlling head-mounted device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510926119.6 2015-12-10
CN201510926119.6A CN105976814B (zh) 2015-12-10 2015-12-10 头戴设备的控制方法和装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/247,569 Continuation US20170169820A1 (en) 2015-12-10 2016-08-25 Electronic device and method for controlling head-mounted device

Publications (1)

Publication Number Publication Date
WO2017096843A1 true WO2017096843A1 (zh) 2017-06-15

Family

ID=56988372

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/088884 Ceased WO2017096843A1 (zh) 2015-12-10 2016-07-06 头戴设备的控制方法和装置

Country Status (3)

Country Link
US (1) US20170169820A1 (zh)
CN (1) CN105976814B (zh)
WO (1) WO2017096843A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112118610A (zh) * 2019-06-19 2020-12-22 杭州萤石软件有限公司 无线智能设备配网方法及系统

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909603A (zh) * 2016-08-31 2017-06-30 阿里巴巴集团控股有限公司 搜索信息处理方法及装置
CN107731226A (zh) * 2017-09-29 2018-02-23 杭州聪普智能科技有限公司 基于语音识别的控制方法、装置及电子设备
CN108198552B (zh) * 2018-01-18 2021-02-02 深圳市大疆创新科技有限公司 一种语音控制方法及视频眼镜
CN109255064A (zh) * 2018-08-30 2019-01-22 Oppo广东移动通信有限公司 信息搜索方法、装置、智能眼镜及存储介质
CN109104572A (zh) * 2018-09-07 2018-12-28 北京金茂绿建科技有限公司 一种头戴设备
CN109036415A (zh) * 2018-10-22 2018-12-18 广东格兰仕集团有限公司 一种智能冰箱的语音控制系统
CN109887490A (zh) * 2019-03-06 2019-06-14 百度国际科技（深圳）有限公司 用于识别语音的方法和装置
CN110136704B (zh) * 2019-04-03 2021-12-28 北京石头世纪科技股份有限公司 机器人语音控制方法、装置、机器人和介质
CN110232923B (zh) * 2019-05-09 2021-05-11 海信视像科技股份有限公司 一种语音控制指令生成方法、装置及电子设备
CN111326156A (zh) * 2020-04-16 2020-06-23 杭州趣慧科技有限公司 一种智能头盔控制方法、装置
CN112435670A (zh) * 2020-11-11 2021-03-02 青岛歌尔智能传感器有限公司 语音识别方法、语音识别设备和计算机可读存储介质
CN112420039A (zh) * 2020-11-13 2021-02-26 深圳市麦积电子科技有限公司 一种交通工具的人机交互方法及其系统
CN115938358A (zh) * 2022-10-19 2023-04-07 岚图汽车科技有限公司 车辆免唤醒语音控制方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030130852A1 (en) * 2002-01-07 2003-07-10 Kabushiki Kaisha Toshiba Headset with radio communication function for speech processing system using speech recognition
US20090132256A1 (en) * 2007-11-16 2009-05-21 Embarq Holdings Company, Llc Command and control of devices and applications by voice using a communication base system
CN102138337A (zh) * 2008-08-13 2011-07-27 W·W·格雷林 具有自包含的语音反馈和语音命令的佩戴型头戴式耳机
CN103811003A (zh) * 2012-11-13 2014-05-21 联想(北京)有限公司 一种语音识别方法以及电子设备
CN104410883A (zh) * 2014-11-29 2015-03-11 华南理工大学 一种移动可穿戴非接触式交互系统与方法
CN105009202A (zh) * 2013-01-04 2015-10-28 寇平公司 分为两部分的语音识别

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040006470A1 (en) * 2002-07-03 2004-01-08 Pioneer Corporation Word-spotting apparatus, word-spotting method, and word-spotting program
JP2005189294A (ja) * 2003-12-24 2005-07-14 Toyota Central Res & Dev Lab Inc 音声認識装置
CN101587724A (zh) * 2009-06-18 2009-11-25 广州番禺巨大汽车音响设备有限公司 一种语音识别的网络多媒体播放器系统及方法
CN102103858B (zh) * 2010-12-15 2013-07-24 方正国际软件有限公司 一种基于语音的控制方法及系统
CN102945672B (zh) * 2012-09-29 2013-10-16 深圳市国华识别科技开发有限公司 一种多媒体设备语音控制系统及方法
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
CN103714815A (zh) * 2013-12-09 2014-04-09 何永 语音控制方法及其设备
US9922667B2 (en) * 2014-04-17 2018-03-20 Microsoft Technology Licensing, Llc Conversation, presence and context detection for hologram suppression
CN105141758A (zh) * 2015-07-31 2015-12-09 小米科技有限责任公司 终端控制方法及装置
CN105139850A (zh) * 2015-08-12 2015-12-09 西安诺瓦电子科技有限公司 语音交互装置及方法、语音交互式led异步控制系统终端

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030130852A1 (en) * 2002-01-07 2003-07-10 Kabushiki Kaisha Toshiba Headset with radio communication function for speech processing system using speech recognition
US20090132256A1 (en) * 2007-11-16 2009-05-21 Embarq Holdings Company, Llc Command and control of devices and applications by voice using a communication base system
CN102138337A (zh) * 2008-08-13 2011-07-27 W·W·格雷林 具有自包含的语音反馈和语音命令的佩戴型头戴式耳机
CN103811003A (zh) * 2012-11-13 2014-05-21 联想(北京)有限公司 一种语音识别方法以及电子设备
CN105009202A (zh) * 2013-01-04 2015-10-28 寇平公司 分为两部分的语音识别
CN104410883A (zh) * 2014-11-29 2015-03-11 华南理工大学 一种移动可穿戴非接触式交互系统与方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112118610A (zh) * 2019-06-19 2020-12-22 杭州萤石软件有限公司 无线智能设备配网方法及系统
CN112118610B (zh) * 2019-06-19 2023-08-22 杭州萤石软件有限公司 无线智能设备配网方法及系统

Also Published As

Publication number Publication date
CN105976814B (zh) 2020-04-10
US20170169820A1 (en) 2017-06-15
CN105976814A (zh) 2016-09-28

Similar Documents

Publication Publication Date Title
WO2017096843A1 (zh) 头戴设备的控制方法和装置
US20250117063A1 (en) Methods and apparatus to improve user experience on computing devices
KR102346302B1 (ko) 전자 장치 및 음성 인식 기능 운용 방법
CN107103906B (zh) 一种唤醒智能设备进行语音识别的方法、智能设备和介质
CN108320744B (zh) 语音处理方法和装置、电子设备、计算机可读存储介质
WO2017012511A1 (zh) 语音控制方法、装置及投影仪设备
CN107025906A (zh) 扩展语音识别的周期的方法和产品以及信息处理设备
EP3826005A1 (en) Method of providing voice command and electronic device supporting the same
WO2021218600A1 (zh) 语音唤醒方法和设备
WO2020244257A1 (zh) 语音唤醒方法、系统、电子设备及计算机可读存储介质
US20220230468A1 (en) Login Method Based on Fingerprint Recognition and Device
KR20200095719A (ko) 전자 장치 및 그 제어 방법
CN113671846B (zh) 智能设备控制方法、装置、可穿戴设备及存储介质
TWI831902B (zh) 聲控方法及終端裝置
US20190147890A1 (en) Audio peripheral device
CN111177453A (zh) 控制音频播放的方法、装置、设备及计算机可读存储介质
CN109101517B (zh) 信息处理方法、信息处理设备以及介质
US20240386893A1 (en) Smart glasses, system and control method based on generative artificial intelligence large language models
CN112084478A (zh) 多用户账户的切换方法、装置、电子设备以及存储介质
CN104615641A (zh) 股票资讯推送方法及可佩带耳机
CN112233676A (zh) 智能设备唤醒方法、装置、电子设备及存储介质
US11922970B2 (en) Electronic apparatus and controlling method thereof
US20200234707A1 (en) Voice interaction processing method and apparatus
CN114647300B (zh) 系统控制方法、装置、可穿戴设备和存储介质
WO2020001172A1 (zh) 一种音频处理方法和电子设备

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: 16872045

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16872045

Country of ref document: EP

Kind code of ref document: A1