WO2018077149A1 - 基于声源定位的语音识别方法和系统、及智能家电设备 - Google Patents

基于声源定位的语音识别方法和系统、及智能家电设备 Download PDF

Info

Publication number
WO2018077149A1
WO2018077149A1 PCT/CN2017/107389 CN2017107389W WO2018077149A1 WO 2018077149 A1 WO2018077149 A1 WO 2018077149A1 CN 2017107389 W CN2017107389 W CN 2017107389W WO 2018077149 A1 WO2018077149 A1 WO 2018077149A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice
voice signal
sound source
voice recognition
location information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2017/107389
Other languages
English (en)
French (fr)
Inventor
万玉洋
唐军
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.)
Hefei Hualing Co Ltd
Hefei Midea Refrigerator Co Ltd
Hefei Midea Intelligent Technologies Co Ltd
Original Assignee
Hefei Hualing Co Ltd
Hefei Midea Refrigerator Co Ltd
Hefei Midea Intelligent Technologies 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 Hefei Hualing Co Ltd, Hefei Midea Refrigerator Co Ltd, Hefei Midea Intelligent Technologies Co Ltd filed Critical Hefei Hualing Co Ltd
Publication of WO2018077149A1 publication Critical patent/WO2018077149A1/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
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • 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 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

  • the present invention relates to the field of voice recognition technology, and in particular, to a voice recognition method and system based on sound source localization, and a smart home appliance.
  • the voice recognition system will receive a lot of pseudo instructions, and the recognition system will treat each speaker's voice as a command source, and it is not actual.
  • the speaker who wants to control the home appliance generates an interaction, which seriously affects the recognition rate and interactive experience of the voice recognition system.
  • the technical problem to be solved by the present invention is to provide a voice recognition method and system based on sound source localization and a smart home appliance according to the deficiencies of the prior art.
  • a voice recognition method based on sound source localization comprising the following steps:
  • Step 1 When the smart home appliance enters the voice recognition state, collect a voice signal, and control the timer to start timing;
  • Step 2 When the timing of the timer is less than or equal to a preset time, the voice signal is collected, and then positioning is performed according to the voice signal to determine location information of a sound source corresponding to the voice signal.
  • Step 3 Determine, according to the location information and the pre-stored voice recognition area information, whether to control the smart home device to perform the identification of the voice signal.
  • the beneficial effects of the present invention are: when the smart home appliance enters the voice recognition state, the control timer starts counting, and when the time of the timer is less than or equal to the preset time, the voice signal is collected, and then the positioning is performed according to the voice signal, and the The position information of the sound source corresponding to the voice signal, and determining whether to control the smart home device to perform the voice signal identification according to the position information and the pre-stored voice recognition area information, thereby eliminating the interference voice signal and effectively improving the recognition rate of the voice recognition system To enhance the user's interactive experience.
  • the present invention can also be improved as follows.
  • step 31 when the location corresponding to the location information is in the voice recognition zone corresponding to the voice recognition zone information, determining to control the smart home device to perform the voice signal identification;
  • step 32 when the location corresponding to the location information is outside the voice recognition zone corresponding to the voice recognition zone information, it is determined to acquire the next voice signal.
  • the beneficial effect of adopting the above further solution is: controlling the smart home appliance when the sound source position is in the voice recognition area
  • the device performs the recognition of the voice signal.
  • the next voice signal is collected, which can effectively eliminate the interference of the voice source of the pseudo instruction.
  • the voice recognition method further includes:
  • Step 4 When the voice signal recognition fails, the next voice signal is collected; or,
  • Step 5 When the voice signal is successfully identified, the sound source corresponding to the voice signal is again positioned to determine current position information of the sound source;
  • Step 6 updating the location information according to the current location information to determine voice recognition region information corresponding to the new voice recognition region;
  • Step 7. Reset the timer, restart the timer, and collect the next voice signal.
  • the voice recognition method further includes:
  • Step 8 When the timing of the timer is greater than a preset time, the smart home appliance is controlled to enter a sleep state.
  • controlling the smart household electrical appliance to enter the sleep state can prevent the voice recognition system from being in the voice recognition state all the time, thereby reducing the false recognition situation.
  • the voice recognition method further includes:
  • Step 9 Acquire a first voice signal, where the first voice signal is used to enable the smart home appliance to enter the voice recognition state from the sleep state;
  • Step 10 Perform positioning according to the first voice signal, and determine first location information of a sound source corresponding to the first voice signal;
  • Step 11 Determine the voice recognition area information according to the first location information.
  • the advantage of adopting the above further solution is that the sound source is determined according to the first voice signal that causes the smart home appliance to enter the voice recognition state from the sleep state to determine the voice recognition area information, so as to locate the sound source according to the subsequently collected voice signal.
  • the location information and the voice recognition area information determine whether to control the smart home device to identify the voice signal, thereby eliminating the interference voice signal, effectively improving the recognition rate of the voice recognition system, and improving the user interaction experience.
  • Also provided in some embodiments of the present invention is a computer readable storage medium having stored thereon a computer program that, when executed by a processor, implements the sound source localization based speech recognition method described above.
  • Also disclosed in some embodiments of the present invention is a computer application that, when executed on a processor of a computer device, performs the sound source localization based speech recognition method described above.
  • a smart home appliance comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor executing the program A sound recognition method based on sound source localization is implemented.
  • a voice recognition system based on sound source localization include:
  • a voice collector configured to collect a voice signal when the smart home appliance enters a voice recognition state
  • a controller configured to control a timer to start timing when the smart home appliance enters a voice recognition state
  • a processor configured to: when the timing of the timer is less than or equal to a preset time, collect the voice signal, perform positioning according to the voice signal collected by the voice collector, and determine a sound corresponding to the voice signal The location information of the source, and determining, according to the location information and the pre-stored voice recognition area information, whether to control the smart home device to perform the identification of the voice signal.
  • the beneficial effects of the present invention are: when the smart home appliance enters the voice recognition state, the controller controls the timer to start timing, and when the timer count is less than or equal to the preset time, the voice collector collects the voice signal, and the processor according to the voice The signal is positioned to determine the position information of the sound source corresponding to the voice signal, and according to the position information and the pre-stored voice recognition area information, determine whether to control the smart home device to identify the voice signal, thereby eliminating the interference voice signal and effectively improving the voice. Identify the recognition rate of the system and enhance the user's interactive experience.
  • the present invention can also be improved as follows.
  • the processor is specifically configured to: when the location corresponding to the location information is in the voice recognition area corresponding to the voice recognition area information, determine to control the smart home device to perform the voice signal identification; or When the location corresponding to the location information is outside the voice recognition zone corresponding to the voice recognition zone information, it is determined to acquire the next voice signal.
  • the voice collector is further configured to: when the voice signal recognition fails, acquire a next voice signal;
  • the processor is further configured to: when the voice signal is successfully identified, locate the sound source corresponding to the voice signal, determine current location information of the sound source, and according to the current location information Updating the location information to determine voice recognition area information corresponding to the new voice recognition area; the controller is further configured to reset the timer to restart the timer; the voice collector further Used to acquire the next voice signal.
  • controller is further configured to control the smart home appliance to enter a sleep state when a timing of the timer is greater than a preset time.
  • the voice collector is further configured to: collect a first voice signal, where the first voice signal is used to enable the smart home appliance to enter the voice recognition state from the sleep state;
  • the processor is further configured to: perform positioning according to the first voice signal, and determine first location information of a sound source corresponding to the first voice signal, and determine the voice recognition according to the first location information Regional information.
  • the voice collector employs a microphone array.
  • a smart home appliance comprising: a sound source localization based speech recognition system according to any of the above embodiments.
  • the smart home appliance includes: a smart refrigerator, a smart air conditioner, and a smart air purifier.
  • FIG. 1 is a schematic flowchart of a method for voice recognition based on sound source localization according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a method for voice recognition based on sound source localization according to another embodiment of the present invention
  • FIG. 3 is a schematic flowchart of a method for voice recognition based on sound source localization according to another embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of a method for voice recognition based on sound source localization according to another embodiment of the present invention.
  • FIG. 5 is a schematic structural block diagram of a voice recognition system based voice recognition system according to an embodiment of the present invention.
  • the sound source is located by waking up the voice signal of the home appliance, and then the interaction with the home appliance is realized by the subsequent voice signal, and the position of the sound source is updated.
  • Information only the voice signal of the location is identified, and the interference of the source of the pseudo instruction can be excluded.
  • the execution body of the sound source localization-based voice recognition method 100 as shown in FIG. 1 may be a voice recognition system or a smart home appliance.
  • the voice recognition method 100 includes:
  • the voice signal is collected, and the timer is controlled to start timing.
  • the voice signal is collected, and then the positioning is performed according to the voice signal, and the location information of the sound source corresponding to the voice signal is determined.
  • the voice recognition method 100 may further include: Step 125, when the timer is greater than the preset time, the smart home appliance may be controlled to enter a sleep state.
  • the control timer starts to count, and the time is determined.
  • the timing of the timer is less than or equal to the preset time
  • the voice signal is collected, the positioning is performed according to the voice signal, the position information of the sound source corresponding to the voice signal is determined, and the location information and the pre-stored voice recognition area information are used to determine whether The smart home appliance is controlled to recognize the voice signal, thereby eliminating the interference voice signal, effectively improving the recognition rate of the voice recognition system, and improving the user's interactive experience.
  • the smart home appliance is controlled to enter the sleep state, which can prevent the voice recognition system from being in the voice recognition state all the time, thereby reducing the false recognition situation.
  • the step 130 shown in FIG. 2 may include:
  • Step 131 When the location corresponding to the location information is in the voice recognition zone corresponding to the voice recognition zone information, determine to control the smart home appliance to perform voice signal identification.
  • step 132 when the location corresponding to the location information is outside the voice recognition zone corresponding to the voice recognition zone information, it is determined to acquire the next voice signal.
  • the smart home appliance when the sound source position is in the voice recognition area, the smart home appliance is controlled to recognize the voice signal, and when the sound source position is outside the voice recognition area, the next voice signal is collected, and the pseudo command can be effectively excluded. Sound source interference.
  • the voice recognition method 100 may further include:
  • step 132 is performed; if yes, step 141 is performed.
  • the sound source corresponding to the voice signal needs to be further positioned again, the current location information of the sound source is determined, and the location information is updated according to the current location information to determine The speech recognition area information corresponding to the new speech recognition area.
  • the voice recognition method 100 may further include:
  • the location information of the sound source that is located according to the subsequently collected voice signal is determined by performing positioning according to the first voice signal that causes the smart home appliance to enter the voice recognition state from the sleep state to determine the voice recognition area information.
  • the voice recognition area information determines whether to control the smart home appliance to identify the voice signal, thereby eliminating the interference voice signal, effectively improving the recognition rate of the voice recognition system, and improving the user interaction experience.
  • a speech recognition method 200 as shown in FIG. 4 includes:
  • the smart home device is in a sleep state that can not interact with the user, whether the first voice signal for awakening the smart home device to enter the voice recognition state can be collected, if the first voice signal is collected, step 220 is performed; Otherwise, the smart home appliance continues to sleep.
  • step 250 the smart home appliance enters a sleep state.
  • the preset time may be 10 s, that is, when the first voice signal for awakening the smart home device to enter the voice recognition state is collected, the timer may be timed if at 10s. If the voice signal is collected, step 250 is performed; if the voice signal is not collected for more than 10 seconds, the smart home device enters a sleep state. 250: Perform positioning according to the voice signal, and determine location information of the sound source corresponding to the voice signal.
  • step 260 Determine, according to the location information and the voice recognition area information, that the location corresponding to the location information is in the voice recognition area corresponding to the voice recognition area information, and if yes, perform step 270; otherwise, perform step 240.
  • step 280 Determine whether the recognition of the voice signal is successful. If yes, execute 290; otherwise, perform step 240.
  • the preset time may be 10 s
  • the voice signal is collected at the 6th s, and the voice signal is located and recognized, and the voice recognition is successful, and the timer needs to be reset to re-time. ,which is, Whether the voice signal can be collected in the next 10s, if it can be collected, continue and locate and identify the voice signal; if it is more than 10s, the smart home device enters the sleep state.
  • the first voice signal of the wake-up home appliance is used for sound source localization, and then the voice signal is used to realize interaction with the home appliance, and the position information of the sound source is updated, and only the voice signal of the position is recognized. It can effectively eliminate the interference of the source of the directive.
  • the preset time may be set according to the actual situation, which is not limited by the embodiment of the present invention.
  • the preset time is 10s, which is only an example to illustrate the technical solution of the embodiment of the present invention. It is not intended to limit the embodiments of the present invention.
  • the size of the sequence numbers of the above processes does not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not be implemented by the present invention.
  • the implementation of the examples constitutes any limitation.
  • a voice recognition method based on sound source localization provided by an embodiment of the present invention is described in detail above with reference to FIG. 1 to FIG.
  • Also provided in some embodiments of the present invention is a computer readable storage medium having stored thereon a computer program that, when executed by a processor, implements the sound source localization based speech recognition method of the above embodiments.
  • Also disclosed in some embodiments of the present invention is a computer application that, when executed on a processor of a computer device, performs the sound source localization based speech recognition method of the above embodiments.
  • a smart home appliance comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor executing the program A sound source localization based speech recognition method of the above embodiment is implemented.
  • a voice recognition system based voice recognition system is described in detail below with reference to FIG.
  • a sound source localization-based speech recognition system 500 includes a voice collector 510, a controller 520, and a processor 530. among them,
  • the voice collector 510 is configured to collect a voice signal when the smart home appliance enters a voice recognition state.
  • the controller 520 is configured to control the timer to start timing when the smart home appliance enters the voice recognition state.
  • the processor 530 is configured to: when the timing of the timer is less than or equal to the preset time, the voice signal is collected, and then the voice signal collected by the voice collector 510 is used for positioning, determining the location information of the sound source corresponding to the voice signal, and according to the location information. And pre-stored voice recognition area information, determining whether to control the smart home device to perform voice signal recognition.
  • the controller 520 is further configured to control the smart household electrical appliance to enter a sleep state when the timing of the timer is greater than a preset time.
  • the controller controls the timer to start counting.
  • the voice collector collects the voice signal
  • the processor performs the voice signal according to the voice signal. Positioning, determining the position information of the sound source corresponding to the voice signal, and determining whether to control the smart home device to perform the voice signal identification according to the position information and the pre-stored voice recognition area information, thereby eliminating the interference voice signal and effectively improving the voice recognition system
  • the recognition rate enhances the user's interactive experience.
  • the controller controls the smart home appliance to enter the sleep state, which can prevent the voice recognition system from being in the voice recognition state all the time, thereby reducing the false recognition situation.
  • speech recognition system 500 may correspond to an execution subject of a speech recognition method in accordance with an embodiment of the present invention, and that the above and other operations and/or functions of the various modules in speech recognition system 500 are respectively implemented The corresponding processes of the respective methods in FIG. 1 to FIG. 4 are not described herein again for the sake of brevity.
  • the voice collector 510 can employ a microphone array for meeting the positioning requirements of the planar position.
  • the voice collector 510 can adopt a horizontal array of 2 mic or 4 mic; when the smart home appliance is a small home appliance such as an air cleaner, the voice logger 510 can adopt a circular array of 5 mic.
  • the processor 530 performs normal audio processing on the voice signal before performing positioning according to the voice signal collected by the voice collector 510 to determine the location information of the sound source corresponding to the voice signal, for example, : A/D conversion, noise reduction, etc., but the embodiment of the present invention does not limit this.
  • the processor 530 is specifically configured to: when the location corresponding to the location information is in the voice recognition region corresponding to the voice recognition region information, determine to control the smart home device to perform voice signal identification. Alternatively, when the location corresponding to the location information is outside the voice recognition zone corresponding to the voice recognition zone information, it is determined to acquire the next voice signal.
  • the voice collector 510 is further configured to: when the voice signal recognition fails, acquire the next voice signal.
  • the processor 530 is further configured to: when the voice signal is successfully identified, locate the sound source corresponding to the voice signal, determine the current location information of the sound source, and update the location information according to the current location information to determine a new voice recognition.
  • the voice recognition area information corresponding to the area.
  • the controller 520 is also used to reset the timer to cause the timer to restart timing.
  • the voice collector is also used to acquire the next voice signal.
  • the voice collector 510 is further configured to collect a first voice signal, where the first voice signal is used to enter the smart home device from the sleep state to the voice recognition state.
  • the processor 530 is further configured to perform positioning according to the first voice signal, determine first location information of the sound source corresponding to the first voice signal, and determine voice recognition region information according to the first location information.
  • the embodiment of the present invention further provides a smart home appliance comprising the voice source localization based voice recognition system 500 in any of the above embodiments.
  • the smart home appliance may include a smart refrigerator, a smart air conditioner, and a smart air purifier, or may include other smart home appliances, which is not limited in this embodiment of the present invention.
  • the voice signal collected by the voice recognition system is used for positioning, the location information of the sound source corresponding to the voice signal is determined, and the location information and the pre-stored voice recognition zone information are determined. Whether to control the smart home appliance to identify the voice signal, thereby eliminating the interference voice signal, effectively improving the recognition rate of the voice recognition system, and improving the user's interactive experience.
  • the disclosed systems, devices, and methods may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of cells is only a logical function division.
  • multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed.
  • 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, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • An integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, can be stored in a computer readable storage medium.
  • the technical solution of the present invention contributes in essence or to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Telephonic Communication Services (AREA)
  • Telephone Function (AREA)

Abstract

一种基于声源定位的语音识别方法和系统及智能家电设备，该语音识别方法包括：当智能家电设备进入语音识别状态时，采集语音信号，并控制定时器开始计时（110）；当定时器的计时小于或者等于预设时间时，采集到语音信号，则根据语音信号进行定位，确定语音信号所对应声源的位置信息（120）；根据位置信息和预存的语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别（130），从而可以排除干扰语音信号，有效的提高语音识别系统的识别率，提升用户的交互体验。

Description

基于声源定位的语音识别方法和系统、及智能家电设备 技术领域
本发明涉及语音识别技术领域，尤其涉及一种基于声源定位的语音识别方法和系统、及智能家电设备。
背景技术
在家电设备的使用环境中，经常存在多说话人的场景，在此场景下语音识别系统会接受到很多伪指令，识别系统会将各说话人的语音都当作指令源进行处理，与并非实际想要控制家电设备的说话人产生交互，严重影响到语音识别系统的识别率和交互体验。
发明内容
本发明所要解决的技术问题是针对现有技术的不足，提供一种基于声源定位的语音识别方法和系统、及智能家电设备。
本发明解决上述技术问题的技术方案如下：一种基于声源定位的语音识别方法，包括以下步骤：
步骤1、当智能家电设备进入语音识别状态时，采集语音信号，并控制定时器开始计时；
步骤2、当所述定时器的计时小于或者等于预设时间时采集到所述语音信号，则根据所述语音信号进行定位，确定所述语音信号所对应声源的位置信息；
步骤3、根据所述位置信息和预存的语音识别区域信息，确定是否控制所述智能家电设备进行所述语音信号的识别。
本发明的有益效果是：当智能家电设备进入语音识别状态时，控制定时器开始计时，当定时器的计时小于或者等于预设时间时采集到语音信号，则根据该语音信号进行定位，确定该语音信号所对应声源的位置信息，并根据位置信息和预存的语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别，从而可以排除干扰语音信号，有效的提高语音识别系统的识别率，提升用户的交互体验。
在上述技术方案的基础上，本发明还可以做如下改进。
进一步地，步骤31、当所述位置信息对应的位置处于所述语音识别区域信息对应的语音识别区域内时，确定控制所述智能家电设备进行所述语音信号的识别；
或者，步骤32、当所述位置信息对应的位置处于所述语音识别区域信息对应的语音识别区域外时，确定采集下一次的语音信号。
采用上述进一步方案的有益效果是：当声源位置处于语音识别区域内时，控制智能家电 设备进行语音信号的识别，当声源位置处于语音识别区域外时，采集下一次的语音信号，可以有效的排除伪指令声源的干扰。
进一步地，在步骤31之后，所述语音识别方法还包括：
步骤4、当所述语音信号识别失败时，采集下一次的语音信号；或者，
步骤5、当所述语音信号识别成功时，对所述语音信号所对应的声源再次进行定位，确定所述声源的当前位置信息；
步骤6、根据所述当前位置信息更新所述位置信息，以确定新的语音识别区域所对应的语音识别区域信息；
步骤7、重置所述定时器，使所述定时器重新开始计时，并采集下一次的语音信号。
进一步地，所述语音识别方法还包括：
步骤8、当所述定时器的计时大于预设时间时，控制所述智能家电设备进入休眠状态。
采用上述进一步方案的有益效果是：当时间t超出预设时间时，控制智能家电设备进入休眠状态，可以避免语音识别系统一直处于语音识别状态，从而减少误识别的情况。
进一步地，在步骤1之前，所述语音识别方法还包括：
步骤9、采集第一语音信号，所述第一语音信号用于使所述智能家电设备从所述休眠状态进入所述语音识别状态；
步骤10、根据所述第一语音信号进行定位，并确定所述第一语音信号所对应声源的第一位置信息；
步骤11、根据所述第一位置信息，确定所述语音识别区域信息。
采用上述进一步方案的有益效果是：通过根据使智能家电设备从休眠状态进入语音识别状态的第一语音信号进行定位，以确定语音识别区域信息，以便根据后续采集到的语音信号进行定位的声源的位置信息和该语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别，从而可以排除干扰语音信号，有效的提高语音识别系统的识别率，提升用户的交互体验。
在本发明的一些实施例中还提出一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现上面所述的基于声源定位的语音识别方法。
在本发明的一些实施例中还提出一种计算机应用程序，当其在计算机设备的处理器上执行时，执行上面所述的基于声源定位的语音识别方法。
在本发明的一些实施例中还提出一种智能家电设备，该智能家电设备包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时，实现上面所述的基于声源定位的语音识别方法。
本发明解决上述技术问题的另一种技术方案如下：一种基于声源定位的语音识别系统， 包括：
语音采集器，用于当智能家电设备进入语音识别状态时，采集语音信号；
控制器，用于当智能家电设备进入语音识别状态时，控制定时器开始计时；
处理器，用于当所述定时器的计时小于或者等于预设时间时采集到所述语音信号，则根据所述语音采集器采集的所述语音信号进行定位，确定所述语音信号所对应声源的位置信息，并根据所述位置信息和预存的语音识别区域信息，确定是否控制所述智能家电设备进行所述语音信号的识别。
本发明的有益效果是：当智能家电设备进入语音识别状态时，控制器控制定时器开始计时，当定时器的计时小于或者等于预设时间时语音采集器采集到语音信号，处理器根据该语音信号进行定位，确定语音信号所对应声源的位置信息，并根据位置信息和预存的语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别，从而可以排除干扰语音信号，有效的提高语音识别系统的识别率，提升用户的交互体验。
在上述技术方案的基础上，本发明还可以做如下改进。
进一步地，所述处理器具体用于当所述位置信息对应的位置处于所述语音识别区域信息对应的语音识别区域内时，确定控制所述智能家电设备进行所述语音信号的识别；或者，当所述位置信息对应的位置处于所述语音识别区域信息对应的语音识别区域外时，确定采集下一次的语音信号。
进一步地，所述语音采集器还用于当所述语音信号识别失败时，采集下一次的语音信号；
或者，所述处理器还用于：当所述语音信号识别成功时，对所述语音信号所对应的声源再次进行定位，确定所述声源的当前位置信息，并根据所述当前位置信息更新所述位置信息，以确定新的语音识别区域所对应的语音识别区域信息；所述控制器还用于重置所述定时器，使所述定时器重新开始计时；所述语音采集器还用于采集下一次的语音信号。
进一步地，所述控制器还用于当所述定时器的计时大于预设时间时，控制所述智能家电设备进入休眠状态。
进一步地，所述语音采集器还用于：采集第一语音信号，所述第一语音信号用于使所述智能家电设备从所述休眠状态进入所述语音识别状态；
所述处理器还用于：根据所述第一语音信号进行定位，并确定所述第一语音信号所对应声源的第一位置信息，并根据所述第一位置信息，确定所述语音识别区域信息。
进一步地，所述语音采集器采用麦克风阵列。
本发明解决上述技术问题的另一种技术方案如下：一种智能家电设备，包括：如上述任一项实施例所述的基于声源定位的语音识别系统。
进一步地，所述智能家电设备包括：智能冰箱、智能空调和智能空气净化器。
本发明附加的方面的优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明实践了解到。
附图说明
图1为本发明实施例提供的一种基于声源定位的语音识别方法的示意性流程图；
图2为本发明另一实施例提供的一种基于声源定位的语音识别方法的示意性流程图；
图3为本发明另一实施例提供的一种基于声源定位的语音识别方法的示意性流程图；
图4为本发明另一实施例提供的一种基于声源定位的语音识别方法的示意性流程图；
图5为本发明实施例提供的一种基于声源定位的语音识别系统的示意性结构框图。
具体实施方式
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本发明，而不能理解为对本发明的限制。
在家庭环境中，经常存在多人对话场景。在此环境下，如果语音识别系统正在工作状态，需要处理各种语音。由于一直存在语音输入，语音识别系统会很难进入休眠状态，一直处于语音识别状态，进行语音信号的识别，而此时识别的语音大多是不相关的干扰语音，容易出现误识别的情况。
而本发明实施例中，假定声源的位置不会发生快速的变化，通过唤醒家电设备的语音信号进行声源定位，再通过之后的语音信号实现与家电设备的交互，并更新声源的位置信息，只对该位置的语音信号进行识别，可以排除伪指令源的干扰。
如图1所示的一种基于声源定位的语音识别方法100的执行主体可以是语音识别系统，也可以是智能家电设备，该语音识别方法100包括：
110，当智能家电设备进入语音识别状态时，采集语音信号，并控制定时器开始计时。
120，当定时器的计时小于或者等于预设时间时采集到语音信号，则根据该语音信号进行定位，确定该语音信号所对应声源的位置信息。
130，根据位置信息和预存的语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别。
具体的，在该实施例中，如图1所示，语音识别方法100还可以包括：步骤125，当定时器的计时大于预设时间时，则可以控制智能家电设备进入休眠状态。
上述实施例中，当智能家电设备进入语音识别状态时，控制定时器开始计时，当定 时器的计时小于或者等于预设时间时采集到语音信号，则根据该语音信号进行定位，确定该语音信号所对应声源的位置信息，并根据位置信息和预存的语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别，从而可以排除干扰语音信号，有效的提高语音识别系统的识别率，提升用户的交互体验。
同时，当定时器的计时大于预设时间时，控制智能家电设备进入休眠状态，可以避免语音识别系统一直处于语音识别状态，从而减少误识别的情况。
可选地，作为本发明的一个实施例，如图2所示步骤130可以包括：
步骤131，当位置信息对应的位置处于语音识别区域信息对应的语音识别区域内时，确定控制智能家电设备进行语音信号的识别。
或者，步骤132，当位置信息对应的位置处于语音识别区域信息对应的语音识别区域外时，确定采集下一次的语音信号。
上述实施例中，当声源位置处于语音识别区域内时，控制智能家电设备进行语音信号的识别，当声源位置处于语音识别区域外时，采集下一次的语音信号，可以有效的排除伪指令声源的干扰。
可选地，作为本发明的另一个实施例，如图2所示，在步骤131之后，语音识别方法100还可以包括：
140，语音信号识别是否成功，若否，则执行步骤132；若是，则执行步骤141。
141，对语音信号所对应的声源再次进行定位，确定声源的当前位置信息。
142，根据当前位置信息更新位置信息，以确定新的语音识别区域所对应的语音识别区域信息。
143，重置定时器，使定时器重新开始计时，并执行步骤132。
具体的，在该实施例中，当语音信号识别成功时，还需要进一步对语音信号所对应的声源再次进行定位，确定声源的当前位置信息，并根据当前位置信息更新位置信息，以确定新的语音识别区域所对应的语音识别区域信息。同时，需要重置定时器，使得定时器重新开始计时，并采集下一次语音信号。
可选地，作为本发明的另一个实施例，如图3所示，在步骤110之前，语音识别方法100还可以包括：
150，采集第一语音信号，第一语音信号用于使智能家电设备从休眠状态进入语音识别状态。
160，根据第一语音信号进行定位，并确定第一语音信号所对应声源的第一位置信 息。
170，根据第一位置信息，确定语音识别区域信息。
上述实施例中，通过根据使智能家电设备从休眠状态进入语音识别状态的第一语音信号进行定位，以确定语音识别区域信息，以便根据后续采集到的语音信号进行定位的声源的位置信息和该语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别，从而可以排除干扰语音信号，有效的提高语音识别系统的识别率，提升用户的交互体验。
下面结合图4，对本发明实施例提供的语音识别方法进行详细的描述。如图4所示的一种语音识别方法200包括：
210，智能家电设备处于不能与用户交互的休眠状态，是否可以采集到用于将智能家电设备唤醒使其进入语音识别状态的第一语音信号，若采集到了第一语音信号，则执行步骤220；否则，智能家电设备继续处于休眠状态。
220，根据第一语音信号进行定位，并确定该第一语音信号所对应声源的第一位置信息。同时，可以启动定时器开始计时。
230，根据第一位置信息，确定语音识别区域信息。
240，是否在预设时间内采集到了语音信号，若是，则执行步骤250；否则，智能家电设备进入休眠状态。
例如：在该实施例中，预设时间可以为10s，也就是说，当采集到用于将智能家电设备唤醒使其进入语音识别状态的第一语音信号时，定时器可以计时，如果在10s内，采集到语音信号，则执行步骤250；如果超过10s，未采集到语音信号，则智能家电设备进入休眠状态。250，根据语音信号进行定位，确定该语音信号所对应声源的位置信息。
260，根据位置信息和语音识别区域信息，确定该位置信息对应的位置处于语音识别区域信息对应的语音识别区域内，若是，则执行步骤270，否则，执行步骤240。
270，控制智能家电设备进行该语音信号的识别。
280，确定对该语音信号的识别是否成功，若是，则执行290；否则，执行步骤240。
290，对语音信号所对应的声源再次进行定位，确定声源的当前位置信息。
295，根据当前位置信息更新位置信息，以确定新的语音识别区域所对应的语音识别区域信息，同时，重置定时器，使定时器重新开始计时，并执行步骤240。
例如：在该实施例中，预设时间可以为10s，而在第6s时采集到了语音信号，并对语音信号进行定位和识别，且语音识别成功，此时需要重置定时器使其重新计时，即， 在下一个10s内是否可以采集到语音信号，若可以采集到，则继续并对语音信号进行定位和识别；若超过10s无论是否采集到，智能家电设备进入休眠状态。
上述实施例中，过唤醒家电设备的第一语音信号进行声源定位，再通过之后的语音信号实现与家电设备的交互，并更新声源的位置信息，只对该位置的语音信号进行识别，可以有效的排除伪指令源的干扰。
应理解，在该实施例中，预设时间可以根据实际的情况进行设置，本发明实施例对此并不做任何限定，预设时间为10s仅是举例用以说明本发明实施例的技术方案，并不对本发明实施例构成任何限定。
还应理解，在本发明的上述各实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本发明实施例的实施过程构成任何限定。
上文结合图1至图4，对本发明实施例提供的一种基于声源定位的语音识别方法进行了详细的描述。
在本发明的一些实施例中还提出一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现上面实施例的基于声源定位的语音识别方法。
在本发明的一些实施例中还提出一种计算机应用程序，当其在计算机设备的处理器上执行时，执行上面实施例的基于声源定位的语音识别方法。
在本发明的一些实施例中还提出一种智能家电设备，该智能家电设备包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时，实现上面实施例的基于声源定位的语音识别方法。
下面结合图5对本发明实施例提供的一种基于声源定位的语音识别系统进行详细的描述。
如图5所示的一种基于声源定位的语音识别系统500，包括：语音采集器510、控制器520和处理器530。其中，
语音采集器510用于当智能家电设备进入语音识别状态时，采集语音信号。控制器520用于当智能家电设备进入语音识别状态时，控制定时器开始计时。处理器530用于当定时器的计时小于或者等于预设时间时采集到语音信号，则根据语音采集器510采集的语音信号进行定位，确定语音信号所对应声源的位置信息，并根据位置信息和预存的语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别。
具体的，在该实施例中，控制器520还用于当定时器的计时大于预设时间时，控制智能家电设备进入休眠状态。
上述实施例中，当智能家电设备进入语音识别状态时，控制器控制定时器开始计时，当定时器的计时小于或者等于预设时间时语音采集器采集到语音信号，处理器根据该语音信号进行定位，确定语音信号所对应声源的位置信息，并根据位置信息和预存的语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别，从而可以排除干扰语音信号，有效的提高语音识别系统的识别率，提升用户的交互体验。
同时，当定时器的计时大于预设时间时，控制器控制智能家电设备进入休眠状态，可以避免语音识别系统一直处于语音识别状态，从而减少误识别的情况。
应理解，在该实施例中，语音识别系统500可对应于根据本发明实施例的语音识别方法的执行主体，并且语音识别系统500中的各个模块的上述和其它操作和/或功能分别为了实现图1至图4中的各个方法的相应流程，为了简洁，在此不再赘述。
还应理解，在该实施例中，语音采集器510可以采用麦克风阵列，用于满足平面位置的定位需求。当智能家电设备为智能冰箱时，语音采集器510可以采用2mic或4mic的横向阵列；当智能家电设备为空气净化器之类的小家电时，语音采集器510可以采用5mic的圆阵列。
需要说明的是，在该实施例中，处理器530在根据语音采集器510采集的语音信号进行定位，确定语音信号所对应声源的位置信息之前，可以对语音信号进行常规的音频处理，例如：A/D转换、降噪等，但本发明实施例对此并不做限定。
可选地，作为本发明的一个实施例，处理器530具体用于当位置信息对应的位置处于语音识别区域信息对应的语音识别区域内时，确定控制智能家电设备进行语音信号的识别。或者，当位置信息对应的位置处于语音识别区域信息对应的语音识别区域外时，确定采集下一次的语音信号。
可选地，作为本发明的一个实施例，语音采集器510还用于当语音信号识别失败时，采集下一次的语音信号。
或者，处理器530还用于当语音信号识别成功时，对语音信号所对应的声源再次进行定位，确定声源的当前位置信息，并根据当前位置信息更新位置信息，以确定新的语音识别区域所对应的语音识别区域信息。控制器520还用于重置定时器，使定时器重新开始计时。语音采集器还用于采集下一次的语音信号。
可选地，作为本发明的另一个实施例，语音采集器510还用于采集第一语音信号，第一语音信号用于使智能家电设备从休眠状态进入语音识别状态。处理器530还用于根据第一语音信号进行定位，并确定第一语音信号所对应声源的第一位置信息，并根据第一位置信息，确定语音识别区域信息。
本发明实施例还提供一种智能家电设备，该智能家电设备包括如上述任一实施例中的基于声源定位的语音识别系统500。具体的，智能家电设备可以包括智能冰箱、智能空调和智能空气净化器，或者，也可以包括其他的智能家电，本发明实施例对此并不做任何限定。
上述实施例中，当智能家电设备进入语音识别状态时，根据语音识别系统采集的语音信号进行定位，确定语音信号所对应声源的位置信息，并根据位置信息和预存的语音识别区域信息，确定是否控制智能家电设备进行语音信号的识别，从而可以排除干扰语音信号，有效的提高语音识别系统的识别率，提升用户的交互体验。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。
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单元来实现本发明实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以是两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分，或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，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)执行本发明各个实施例方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到各种等效的修改或替 换，这些修改或替换都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。

Claims (16)

  1. 一种基于声源定位的语音识别方法，其特征在于，包括以下步骤：
    步骤1、当智能家电设备进入语音识别状态时，采集语音信号，并控制定时器开始计时；
    步骤2、当所述定时器的计时小于或者等于预设时间时采集到所述语音信号，则根据所述语音信号进行定位，确定所述语音信号所对应声源的位置信息；
    步骤3、根据所述位置信息和预存的语音识别区域信息，确定是否控制所述智能家电设备进行所述语音信号的识别。
  2. 根据权利要求1所述的基于声源定位的语音识别方法，其特征在于，步骤3包括：
    步骤31、当所述位置信息对应的位置处于所述语音识别区域信息对应的语音识别区域内时，确定控制所述智能家电设备进行所述语音信号的识别；
    或者，步骤32、当所述位置信息对应的位置处于所述语音识别区域信息对应的语音识别区域外时，确定采集下一次的语音信号。
  3. 根据权利要求2所述的基于声源定位的语音识别方法，其特征在于，在步骤31之后，所述语音识别方法还包括：
    步骤4、当所述语音信号识别失败时，采集下一次的语音信号；
    或者，步骤5、当所述语音信号识别成功时，对所述语音信号所对应的声源再次进行定位，确定所述声源的当前位置信息；
    步骤6、根据所述当前位置信息更新所述位置信息，以确定新的语音识别区域所对应的语音识别区域信息；
    步骤7、重置所述定时器，使所述定时器重新开始计时，并采集下一次的语音信号。
  4. 根据权利要求1至3中任一项所述的基于声源定位的语音识别方法，其特征在于，所述语音识别方法还包括：
    步骤8、当所述定时器的计时大于预设时间时，控制所述智能家电设备进入休眠状态。
  5. 根据权利要求4所述的基于声源定位的语音识别方法，其特征在于，在步骤1之前，所述语音识别方法还包括：
    步骤9、采集第一语音信号，所述第一语音信号用于使所述智能家电设备从所述休眠状态进入所述语音识别状态；
    步骤10、根据所述第一语音信号进行定位，并确定所述第一语音信号所对应声源的第一位置信息；
    步骤11、根据所述第一位置信息，确定所述语音识别区域信息。
  6. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如权利要求1-5任一项所述的基于声源定位的语音识别方法。
  7. 一种计算机应用程序，当其在计算机设备的处理器上执行时，执行如权利要求1-5任一项所述的基于声源定位的语音识别方法。
  8. 一种智能家电设备，该智能家电设备包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时，实现如权利要求1-5任一项所述的基于声源定位的语音识别方法。
  9. 一种基于声源定位的语音识别系统，其特征在于，包括：
    语音采集器，用于当智能家电设备进入语音识别状态时，采集语音信号；
    控制器，用于当智能家电设备进入语音识别状态时，控制定时器开始计时；
    处理器，用于当所述定时器的计时小于或者等于预设时间时采集到所述语音信号，则根据所述语音采集器采集的所述语音信号进行定位，确定所述语音信号所对应声源的位置信息，并根据所述位置信息和预存的语音识别区域信息，确定是否控制所述智能家电设备进行所述语音信号的识别。
  10. 根据权利要求9所述的基于声源定位的语音识别系统，其特征在于，所述处理器具体用于当所述位置信息对应的位置处于所述语音识别区域信息对应的语音识别区域内时，确定控制所述智能家电设备进行所述语音信号的识别；或者，当所述位置信息对应的位置处于所述语音识别区域信息对应的语音识别区域外时，确定采集下一次的语音信号。
  11. 根据权利要求10所述的基于声源定位的语音识别系统，其特征在于，所述语音采集器还用于当所述语音信号识别失败时，采集下一次的语音信号；
    或者，所述处理器还用于：当所述语音信号识别成功时，对所述语音信号所对应的声源再次进行定位，确定所述声源的当前位置信息，并根据所述当前位置信息更新所述位置信息，以确定新的语音识别区域所对应的语音识别区域信息；所述控制器还用于重置所述定时器，使所述定时器重新开始计时；所述语音采集器还用于采集下一次的语音信号。
  12. 根据权利要求9至11中任一项所述的基于声源定位的语音识别系统，其特征在于，所述控制器还用于当所述定时器的计时大于预设时间时，控制所述智能家电设备进入休眠状态。
  13. 根据权利要求12所述的基于声源定位的语音识别系统，其特征在于，所述语音采集器还用于：采集第一语音信号，所述第一语音信号用于使所述智能家电设备从所述休眠状态进入所述语音识别状态；
    所述处理器还用于：根据所述第一语音信号进行定位，并确定所述第一语音信号所对应 声源的第一位置信息，并根据所述第一位置信息，确定所述语音识别区域信息。
  14. 根据权利要求12所述的基于声源定位的语音识别系统，其特征在于，所述语音采集器采用麦克风阵列。
  15. 一种智能家电设备，其特征在于，包括：如权利要求9至14中任一项所述的基于声源定位的语音识别系统。
  16. 根据权利要求15所述的智能家电设备，其特征在于，所述智能家电设备包括：智能冰箱、智能空调和智能空气净化器。
PCT/CN2017/107389 2016-10-24 2017-10-23 基于声源定位的语音识别方法和系统、及智能家电设备 Ceased WO2018077149A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610925742.4 2016-10-24
CN201610925742.4A CN106356061A (zh) 2016-10-24 2016-10-24 基于声源定位的语音识别方法和系统、及智能家电设备

Publications (1)

Publication Number Publication Date
WO2018077149A1 true WO2018077149A1 (zh) 2018-05-03

Family

ID=57864738

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/107389 Ceased WO2018077149A1 (zh) 2016-10-24 2017-10-23 基于声源定位的语音识别方法和系统、及智能家电设备

Country Status (2)

Country Link
CN (1) CN106356061A (zh)
WO (1) WO2018077149A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111739533A (zh) * 2020-07-28 2020-10-02 睿住科技有限公司 语音控制系统、方法与装置以及存储介质、语音设备
CN112687295A (zh) * 2020-12-22 2021-04-20 联想(北京)有限公司 一种输入控制方法及电子设备
EP3816549A1 (en) 2019-11-01 2021-05-05 Arçelik Anonim Sirketi A refrigerator having voice recognition feature

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106356061A (zh) * 2016-10-24 2017-01-25 合肥华凌股份有限公司 基于声源定位的语音识别方法和系统、及智能家电设备
CN106910505B (zh) * 2017-02-09 2021-08-10 惠州Tcl移动通信有限公司 一种基于移动终端的语音应答方法及系统
CN107230481A (zh) * 2017-05-31 2017-10-03 宇龙计算机通信科技(深圳)有限公司 噪音处理方法及终端
CN107516526B (zh) * 2017-08-25 2022-09-06 百度在线网络技术（北京）有限公司 一种声源跟踪定位方法、装置、设备和计算机可读存储介质
KR102418952B1 (ko) 2017-08-31 2022-07-08 삼성전자주식회사 음성인식 기능을 갖는 가전제품
CN109994123A (zh) * 2017-12-29 2019-07-09 宁波方太厨具有限公司 一种吸油烟机的语音筛选方法
CN108364643A (zh) * 2017-12-29 2018-08-03 潍坊歌尔电子有限公司 用于智能设备的声源定位性能的测试方法和系统
CN109994124A (zh) * 2017-12-29 2019-07-09 宁波方太厨具有限公司 一种吸油烟机的语音筛选方法
CN110097877A (zh) * 2018-01-29 2019-08-06 阿里巴巴集团控股有限公司 权限识别的方法和装置
CN108109623A (zh) * 2018-01-31 2018-06-01 广东美的厨房电器制造有限公司 控制方法、控制装置和烹饪设备
CN108597164B (zh) * 2018-04-28 2021-11-12 侯苏华 一种防盗方法、装置、终端及计算机可读介质
CN108932942A (zh) * 2018-06-26 2018-12-04 四川斐讯信息技术有限公司 一种实现智能音箱人机对话的系统及其方法
CN108800473A (zh) * 2018-07-20 2018-11-13 珠海格力电器股份有限公司 设备的控制方法及装置、存储介质和电子装置
CN108917113A (zh) * 2018-08-01 2018-11-30 珠海格力电器股份有限公司 辅助语音控制方法、装置以及空调
CN110858488A (zh) * 2018-08-24 2020-03-03 阿里巴巴集团控股有限公司 语音活动检测方法、装置、设备及存储介质
CN109298642B (zh) * 2018-09-20 2021-08-27 三星电子（中国）研发中心 采用智能音箱进行监控的方法及装置
CN109274562B (zh) * 2018-09-27 2020-08-04 珠海格力电器股份有限公司 一种语音指令执行的方法、装置、智能家电设备及介质
CN109147787A (zh) * 2018-09-30 2019-01-04 深圳北极鸥半导体有限公司 一种智能电视声控识别系统及其识别方法
CN109920404A (zh) * 2019-01-31 2019-06-21 安徽智佳信息科技有限公司 拥有智能感知作用的自助售货广告管理系统的信息采集装置及采集方法
CN110021298A (zh) * 2019-04-23 2019-07-16 广州小鹏汽车科技有限公司 一种汽车语音控制系统
CN110176233A (zh) * 2019-04-28 2019-08-27 青岛海尔空调器有限总公司 空调语音控制的方法、装置及计算机存储介质
CN113494795B (zh) * 2020-04-02 2023-04-18 青岛海尔电冰箱有限公司 冰箱、传声单元的控制方法和存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102905094A (zh) * 2012-10-26 2013-01-30 鸿富锦精密工业（深圳）有限公司 声控电视机及其提高语音接收效果的方法
CN102945672A (zh) * 2012-09-29 2013-02-27 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
CN104103274A (zh) * 2013-04-11 2014-10-15 纬创资通股份有限公司 语音处理装置和语音处理方法
CN104200817A (zh) * 2014-07-31 2014-12-10 广东美的制冷设备有限公司 语音控制方法和系统
CN104267618A (zh) * 2014-07-31 2015-01-07 广东美的制冷设备有限公司 基于红外定位的语音控制方法和系统
CN106028102A (zh) * 2016-05-24 2016-10-12 李达航 一种电视机语音控制方法及控制系统
CN106356061A (zh) * 2016-10-24 2017-01-25 合肥华凌股份有限公司 基于声源定位的语音识别方法和系统、及智能家电设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102945672A (zh) * 2012-09-29 2013-02-27 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
CN102905094A (zh) * 2012-10-26 2013-01-30 鸿富锦精密工业（深圳）有限公司 声控电视机及其提高语音接收效果的方法
CN104103274A (zh) * 2013-04-11 2014-10-15 纬创资通股份有限公司 语音处理装置和语音处理方法
CN104200817A (zh) * 2014-07-31 2014-12-10 广东美的制冷设备有限公司 语音控制方法和系统
CN104267618A (zh) * 2014-07-31 2015-01-07 广东美的制冷设备有限公司 基于红外定位的语音控制方法和系统
CN106028102A (zh) * 2016-05-24 2016-10-12 李达航 一种电视机语音控制方法及控制系统
CN106356061A (zh) * 2016-10-24 2017-01-25 合肥华凌股份有限公司 基于声源定位的语音识别方法和系统、及智能家电设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3816549A1 (en) 2019-11-01 2021-05-05 Arçelik Anonim Sirketi A refrigerator having voice recognition feature
CN111739533A (zh) * 2020-07-28 2020-10-02 睿住科技有限公司 语音控制系统、方法与装置以及存储介质、语音设备
CN112687295A (zh) * 2020-12-22 2021-04-20 联想(北京)有限公司 一种输入控制方法及电子设备

Also Published As

Publication number Publication date
CN106356061A (zh) 2017-01-25

Similar Documents

Publication Publication Date Title
WO2018077149A1 (zh) 基于声源定位的语音识别方法和系统、及智能家电设备
EP3517849B1 (en) Household appliance control method, device and system, and intelligent air conditioner
CN110085233B (zh) 语音控制方法及其装置、电子设备和计算机可读存储介质
CN107465974B (zh) 声音信号检测器
US9477217B2 (en) Using visual cues to improve appliance audio recognition
JP7202075B2 (ja) 複数の音声認識装置間の調整
CN105868827B (zh) 一种智能机器人多模态交互方法和智能机器人
WO2020244257A1 (zh) 语音唤醒方法、系统、电子设备及计算机可读存储介质
CN109326289A (zh) 免唤醒语音交互方法、装置、设备及存储介质
EP3574500A1 (en) Audio device filter modification
CN104538030A (zh) 一种可以通过语音控制家电的控制系统与方法
CN106898348A (zh) 一种出声设备的去混响控制方法和装置
CN110716444A (zh) 一种基于智能家居的声音控制方法、装置和存储介质
US9936355B2 (en) Information processing apparatus, information processing method, and computer program
CN112311635B (zh) 语音打断唤醒方法、装置及计算机可读存储介质
CN111028831B (zh) 一种语音唤醒方法及装置
EP4004907B1 (en) Multi-device wakeword detection
WO2018068422A1 (zh) 一种提高油烟机语音识别率的方法及系统
WO2015131550A1 (zh) 一种控制播放器进入睡眠模式的方法、装置及终端设备
WO2016155362A1 (zh) 一种播放控制方法及终端
WO2018090252A1 (zh) 机器人语音指令识别的方法及相关机器人装置
CN110910878A (zh) 语音唤醒控制方法、装置、存储介质及家电设备
CN117672188A (zh) 音频流处理方法及装置、存储介质及电子装置
CN114743542A (zh) 语音处理的方法、装置、存储介质及电子装置
CN110610706A (zh) 声音信号采集方法、装置、电器设备控制方法及电器设备

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: 17864798

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: 17864798

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 08.01.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 17864798

Country of ref document: EP

Kind code of ref document: A1