WO2018107389A1 - 语音联合协助的实现方法、装置及机器人 - Google Patents

语音联合协助的实现方法、装置及机器人 Download PDF

Info

Publication number
WO2018107389A1
WO2018107389A1 PCT/CN2016/109902 CN2016109902W WO2018107389A1 WO 2018107389 A1 WO2018107389 A1 WO 2018107389A1 CN 2016109902 W CN2016109902 W CN 2016109902W WO 2018107389 A1 WO2018107389 A1 WO 2018107389A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
voice
collected
ontology
environmental
Prior art date
Application number
PCT/CN2016/109902
Other languages
English (en)
French (fr)
Inventor
骆磊
Original Assignee
深圳前海达闼云端智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳前海达闼云端智能科技有限公司 filed Critical 深圳前海达闼云端智能科技有限公司
Priority to CN201680002711.XA priority Critical patent/CN107077844B/zh
Priority to PCT/CN2016/109902 priority patent/WO2018107389A1/zh
Publication of WO2018107389A1 publication Critical patent/WO2018107389A1/zh

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
    • 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 disclosure relates to the field of information processing, and in particular, to a method, an apparatus, and a robot for implementing voice joint assistance.
  • a voice can be issued to interact with the robot having the corresponding function, thereby enabling the robot with the corresponding function to complete the transaction assigned by the user.
  • the user sends a voice for waking up the wiping robot in a room by touching a glass of water.
  • the wiping robot wipes the water sprinkled on the ground without the user having to wipe it by hand. Dry water on the ground. It can be seen that the robot brings great convenience to the user.
  • the main purpose of the present disclosure is to provide a method, a device and a robot for implementing voice joint assistance to assist the user's use of the robot by using other robots to assist the voice interaction between the user and the target robot.
  • a first aspect of the present disclosure provides a method for implementing voice joint assistance, where the method includes:
  • the collected environmental voice is sent to other robots;
  • the setting condition is used to indicate that the collected ambient voice is not used to wake up the ontology robot.
  • the method further includes:
  • the received environmental voice After receiving the environmental voice sent by other robots, the received environmental voice is recognized.
  • the setting condition includes: the collected environmental voice cannot be recognized by the ontology robot;
  • the collected ambient speech is broadcast in the network in which the ontology robot is located.
  • the setting condition includes: the body robot recognizes that the collected robot corresponds to the target voice, and the target robot is not the ontology robot;
  • the collected environmental voice is sent to the target robot.
  • the method further includes:
  • the collected environmental voice is broadcasted in the network where the body robot is located, receiving an identity confirmation response, where the identity confirmation response is used to indicate the robot corresponding to the collected environmental voice;
  • the association relationship between the collected environmental speech and the corresponding robot is recorded in the speech recognition library of the ontology robot.
  • the method further includes:
  • the identity confirmation response is sent to the robot that sent the broadcast.
  • the method further includes:
  • the location information of the user is also sent. Give it to other robots.
  • the second aspect of the present disclosure provides an apparatus for implementing voice joint assistance, including:
  • the environment voice sending module is configured to send the collected environment voice to other robots when the environment voice collected by the body robot meets the set condition;
  • the setting condition is used to indicate that the collected ambient voice is not used to wake up the ontology robot.
  • the device further includes:
  • the first voice recognition module is configured to identify the received ambient voice after receiving the environmental voice sent by the other robot.
  • the setting condition includes: the collected environmental voice cannot be recognized by the ontology robot;
  • the environmental voice sending module is configured to:
  • the collected ambient speech is broadcast in the network in which the ontology robot is located.
  • the setting condition includes: the body robot recognizes that the collected robot corresponds to the target voice, and the target robot is not the ontology robot;
  • the environmental voice sending module is configured to:
  • the collected environmental voice is sent to the target robot.
  • the device further includes:
  • a determining module configured to determine, according to the voice recognition library of the ontology robot, whether the collected ambient voice is a voice that wakes up the ontology robot;
  • a receiving module configured to receive an identity confirmation response after the collected environment voice is broadcasted in the network where the body robot is located, where the identity confirmation response is used to indicate the robot corresponding to the collected environment voice;
  • the recording module is configured to record the association relationship between the collected environmental voice and the corresponding robot in the voice recognition library of the ontology robot.
  • the device further includes:
  • a second voice recognition module configured to: after receiving the environment voice sent by the robot transmitting the broadcast in a broadcast manner, identify the received ambient voice;
  • the response sending module is configured to send the identity confirmation response to the robot that sends the broadcast when the received ambient voice is used to wake up the ontology robot.
  • the device further includes:
  • a positioning module configured to locate a location of the user according to the collected ambient voice
  • the location information sending module is configured to send the location information of the user to other robots when the collected environment voice satisfies the setting condition.
  • a third aspect of the present disclosure provides a computer program product comprising a computer program executable by a programmable device, the computer program having the above-described voice joint assistance when executed by the programmable device The code part of the implementation method.
  • a fourth aspect of the present disclosure provides a non-transitory computer readable storage medium, wherein the non-transitory computer readable storage medium includes one or more programs, the one or more programs for performing the above The implementation of voice joint assistance.
  • a fifth aspect of the present disclosure provides a robot comprising: a voice collection device, a non-transitory computer readable storage medium; and one or more processors for executing a program in the non-transitory computer readable storage medium;
  • the non-transitory computer readable storage medium stores instructions for implementing the above-described implementation method of voice joint assistance.
  • the robot in order to make the target robot hear the voice emitted by the user, the robot is used by the robot.
  • Other robots in the group jointly assist in the voice interaction between the user and the target robot. That is to say, by means of other robots in the robot group, the interaction channel between the user and the target robot is constructed, so that the voice interaction between the robot and the target robot is no longer limited by the maximum propagation distance of the voice emitted by the user, or Limited by the ambient noise of the target robot. Increased the probability of the target robot responding to the voice emitted by the user, and improved The experience of using the robot.
  • FIG. 1 is a schematic diagram of a group of robots, according to an exemplary embodiment.
  • FIG. 2 is a flowchart of a method for implementing voice joint assistance according to an exemplary embodiment.
  • FIG. 3 is another schematic diagram of a method for implementing voice joint assistance according to an exemplary embodiment.
  • FIG. 4 is a block diagram of an apparatus for implementing voice joint assistance according to an exemplary embodiment.
  • FIG. 5 is another block diagram of a voice joint assistance implementation apparatus 1000, according to an exemplary embodiment.
  • the robot brings great convenience to the user, provided that the robot hears the voice from the user. In some scenarios, the robot may not be able to hear the voice from the user.
  • the robot is far from the user. Since the voice of the user has the loudest voice, the user The emitted voice has the maximum propagation distance. In the case where the distance between the robot and the user is greater than the maximum propagation distance, the robot cannot hear the voice from the user.
  • Another possible scenario is that the robot is in an unsteady noise environment. Since the robot is disturbed by unsteady noise, the user's voice may not be heard.
  • the present disclosure proposes a method for implementing voice joint assistance, which is applicable to a group of robots composed of a plurality of robots, each of which is typically distributed at a different location.
  • the voice sent by the user is a certain robot for waking up the robot group (hereinafter referred to as the target robot)
  • the target robot in order to make the target robot hear the voice emitted by the user, proposes to assist by other robots in the robot group. Voice interaction between the user and the target robot.
  • the interaction channel between the user and the target robot is constructed, so that the voice interaction between the robot and the target robot is no longer limited by the maximum propagation distance of the voice emitted by the user, or Limited by the ambient noise of the target robot.
  • FIG. 1 is a schematic diagram of a group of robots according to an exemplary embodiment.
  • FIG. 1 takes a robot group including three robots as an example.
  • the robot group includes: a robot A, a robot B, and a robot C.
  • the three are respectively distributed in different rooms, wherein the robot A is closest to the user, and the user is in the same room, and the robot B is far away from the user.
  • Robot C is farthest from the user.
  • the interaction channel between the user and the robot C is established by the robot A and the robot B by using the implementation method of the voice joint assistance provided by the present disclosure, and the robot A and the robot B are constructed.
  • the relay of the voice sent by the user is relayed, so that the robot C responds to the voice sent by the user.
  • the robot A is closer to the user, so the robot A first hears the voice, and then forwards the voice to the robot B, and the robot B forwards the received environmental voice to the robot C to realize the joint. Voice assistance.
  • FIG. 2 is a schematic embodiment according to an exemplary embodiment.
  • a flow chart of a method of implementing voice joint assistance is shown. As shown in FIG. 2, the method includes the following steps:
  • Step S21 when the environmental voice collected by the body robot meets the set condition, the collected environmental voice is sent to other robots;
  • the setting condition is used to indicate that the collected ambient voice is not used to wake up the ontology robot.
  • the ontology robot does not specifically refer to a certain robot, but is a relative concept, and is a robot that performs the method, and may be any robot in the robot group.
  • the ontology robot is configured with a voice joint assistance implementation device, and the voice joint assistance implementation device performs the above steps.
  • the ontology robot has a built-in voice acquisition module for collecting ambient speech.
  • the environmental voice refers to the voice in the environment where the ontology robot is located. According to the positional relationship between the ontology robot and the user, the environmental voice may include the voice sent by the user, and the voice collection module converts the voice sent by the user into a voice signal for the voice.
  • the joint assisted implementation device further processes the speech signal.
  • the voice joint assistance implementation device packs the voice signal into a voice data packet and transmits the voice signal to other robots when the voice signal satisfies the set condition.
  • the voice collection module of one or more robots in the robot group may collect the voices sent by the user, and then respectively trigger the voice joint assistance with the communication.
  • the implementation device implements the method of implementing voice joint assistance provided by the present disclosure.
  • the voice collection module may be a component built into the voice joint assistance implementation device, and may also be independent of the voice joint assistance device.
  • the voice acquisition module can communicate with the voice-assisted implementation device. When the voice collection module collects the ambient voice, the voice collection module notifies the event to the voice joint assistance implementation device, and the voice joint assistance implementation device responds to the event.
  • the target robot Since the voice emitted by the user is random, that is, the robot that the user needs to wake up (hereinafter referred to as the target robot) is random, which may be an ontology robot, or may be a body group in addition to the body. Other robots outside the robot.
  • the target robot is the ontology robot
  • the voice sent by the user is directly heard by the ontology robot itself, and the implementation method of the voice joint assistance provided by the present disclosure is not needed; for the case where the target robot is not the ontology robot, the voice provided by the present disclosure may be used.
  • the ontology robot forwards the collected environmental voice to other robots in the robot group, and the other robots that receive the environmental voice act as the ontology robot, and equate the received environmental speech with the environment collected by itself.
  • Voice the implementation of the voice joint assistance provided by the present disclosure is performed until the target robot receives the ambient voice.
  • the present disclosure proposes a setting condition to indicate that the collected ambient voice is not used to wake up the ontology robot. Therefore, the voice joint assistance implementation device responds to the event that the voice collection module collects the ambient voice: the environment voice collected by the voice collection module is compared with the set condition, and the collected environment voice satisfies the setting. When the condition is met, the collected environmental voice is sent to other robots in the robot group.
  • the user issues a voice for waking up the wiping robot (illustrated by the robot C in FIG. 1) in a room by touching a glass of water, and the voice emitted by the user is transmitted as an environmental voice in the air due to the robot group.
  • the relative positional relationship between each robot in the group and the user, the voice acquisition module in the ontology robot (illustrated by the robot A in Fig. 1) collects the environmental voice, thereby triggering the implementation of the voice joint assistance in the ontology robot
  • the ambient voice is compared with the set condition, and when the ambient voice satisfies the set condition, that is, when the ambient voice is not used to wake up the ontology robot, the ambient voice is sent to other robots (illustrated in FIG.
  • the robot A will The ambient voice is sent to the robot B).
  • the other robots that receive the environmental voice (illustrated by the robot B in FIG. 1) are used as the ontology robot, and the received environmental speech is equated with the environmental voice collected by itself, and the implementation method of the voice joint assistance provided by the present disclosure is implemented. Until the target robot receives the ambient voice.
  • the implementation method of the voice joint assistance provided by the present disclosure can be implemented by means of a robot
  • Other robots in the group build the interaction channel between the user and the target robot, so that the voice interaction between the robot and the target robot is no longer limited by the maximum propagation distance of the voice emitted by the user, or limited by the target robot.
  • Environmental noise The probability of response of the target robot to the voice emitted by the user is increased, and the experience of the robot is improved.
  • the method for implementing voice joint assistance provided by the disclosure includes the following steps in addition to step S21.
  • Step S22 After receiving the environmental voice sent by the other robot, the received environmental voice is identified.
  • the voice collection module in the ontology robot collects the environmental voice
  • the implementation device for triggering the voice joint assistance in the body robot performs the above steps. S21; on the other hand, since the ontology robot is in the robot group, it may receive the environmental speech sent by other robots, and trigger the realization of the voice joint assistance in the ontology robot after the ontology robot receives the environmental speech sent by other robots. The device performs the above step S22.
  • the ontology robot recognizes the received ambient speech and first requires the ontology robot to have a speech recognition function.
  • the ontology robot has the function of voice recognition, when the voice sent by the user is used to wake up the ontology robot itself, a response to the voice sent by the user is generated; when the voice sent by the user is recognized, the user does not wake up the ontology robot itself.
  • the voice sent by the user is sent to other robots in the robot group.
  • each robot as a body robot in the robot group recognizes the received environmental voice, thereby ensuring that at least one robot in the robot group recognizes that the voice emitted by the user is used to wake up itself.
  • a response to the voice sent by the user is generated, so that the user can obtain the response of the target robot in time, and the response efficiency of the target robot is improved. It avoids the repeated voices sent by the user between the robots in the robot group.
  • the network transmission resources and the power consumption of each robot in the robot group are approximated.
  • FIG. 3 is another schematic diagram of a method for implementing voice joint assistance according to an exemplary embodiment. As shown in FIG. 3, the method for implementing voice joint assistance provided by the present disclosure includes the following steps in addition to step S21.
  • Step S23 locating the location of the user according to the collected environmental voice
  • Step S24 When the collected environmental voice satisfies the setting condition, the location information of the user is also sent to other robots.
  • step S23 and step S21 are in no particular order, and the two may be executed sequentially or in parallel.
  • FIG. 3 is exemplified by the step S21 being performed before the step S24.
  • the ontology robot can locate the location of the user according to the collected ambient voice.
  • each robot in the robot group can determine the direction from which the user's voice comes according to one or more robots that can obtain their own position information, and the voices of the same user are collected in the robot group. Therefore, a possible situation is: in the case where two or more robots collect voices from the same user, two or more collected environmental voice robots determine the direction in which the user's voice comes from, thereby determining the user. Location information. Another possibility is that in the case where only one robot collects the voice sent by the user, it can be known that the user can determine the location information of the user on a certain line in combination with the map.
  • the body robot After the body robot determines the location information of the user, when the collected environment voice satisfies the set condition, the body robot can send the location information of the user to other robots in addition to the collected environment voice.
  • the target robot Since the user's location information is sent to other robots, and the target robot may be among other robots, it is convenient for the target robot to quickly travel to the user according to the user's location information, shortening the time for the user to wait for the target robot to respond, and improving the time. The response efficiency of the target robot.
  • the ontology robot sends the collected environment voice differently.
  • the setting conditions include: the collected environment voice cannot be recognized by the body robot; and the collected environment voice is sent to other robots.
  • the method includes: broadcasting the collected environmental voice in a network where the ontology robot is located.
  • the voice joint assistance implementation device in the body robot broadcasts the environment voice to the network where the voice is located. Other robots in the middle.
  • the robot A, the robot B, and the robot C in the robot group shown in FIG. 1 are in the same network.
  • the voice joint assistance implementation device in the robot A broadcasts the environmental voice c to the robot B and Robot C.
  • the setting condition includes: the body robot recognizes that the collected robot corresponding to the environment voice is the target robot, and the target robot It is not an ontology robot; sending the collected environmental voice to other robots includes: transmitting the collected environmental voice to the target robot.
  • the ontology robot can recognize the environmental speech collected by itself, the ontology robot can obtain the recognition result.
  • the recognition result is: the robot corresponding to the collected environmental voice is the target robot, and the target robot is not the ontology robot, since the ontology robot has recognized that the robot corresponding to the collected environmental voice is the target robot, the voice joint in the ontology robot
  • the assisted implementation device sends the ambient voice to the target robot.
  • the robot group shown in FIG. 1 is taken as an example.
  • Voice acquisition module in robot A The acquired environmental voice c is not used to wake up the robot A itself, and the robot A recognizes that the robot corresponding to the environmental voice c is the robot C, and the voice joint assistance implementing means in the robot A transmits the environmental voice c to the robot C.
  • the above two different ways of transmitting the collected ambient voice can be applied to a robot without voice recognition function, a robot with partial voice recognition function (a robot capable of recognizing each voice in its own voice recognition library) ), and a robot with full speech recognition (a robot that can recognize any speech).
  • the robot group may include both a robot that does not have a voice recognition function, a robot that has a partial voice recognition function, and a robot that has a full recognition function. Therefore, a robot having different functions can be used as a body robot to perform the present disclosure.
  • the implementation method of the voice joint assistance provided extends the scope of application of the voice joint assistance method provided by the present disclosure.
  • the implementation method of the voice joint assistance provided by the disclosure may further include the following steps:
  • the collected environmental voice is broadcasted in the network where the body robot is located, receiving an identity confirmation response, where the identity confirmation response is used to indicate the robot corresponding to the collected environmental voice;
  • the association relationship between the collected environmental speech and the corresponding robot is recorded in the speech recognition library of the ontology robot.
  • the implementation method of the voice joint assistance provided by the disclosure may further include the following steps:
  • the identity confirmation response is sent to the robot that sent the broadcast.
  • the present disclosure proposes an identity confirmation response to update the speech recognition library of the ontology robot.
  • the identity confirmation response is a response sent by a certain robot to another robot when it recognizes that the robot corresponding to the environmental voice collected by another robot is itself.
  • the speech recognition library of the ontology robot includes the relationship between different environmental voices collected by the ontology robot and the corresponding robot, and the association relationship may be an association relationship between a certain voice and the ontology robot itself, or may be a certain voice.
  • the relationship with other robots For example, the two records in the voice recognition library of the robot A are: the robot corresponding to the environmental voice a collected by the robot A is the robot A; the robot corresponding to the environmental voice c collected by the robot A is the robot C.
  • the ontology robot When the ontology robot collects the environmental voice in its own voice collection module, it triggers its own voice joint assistance implementation device, and sequentially matches the collected environmental voice with each voice in the voice recognition library of the ontology robot to determine the collected voice. Whether the ambient voice is the voice of the wake-up robot, if the collected ambient voice is the voice of the wake-up robot, the ambient voice collected by the ontology robot does not satisfy the set condition; if the collected ambient voice is not the voice of the wake-up robot, Then, the ambient voice collected by the ontology robot satisfies the set condition, and then the collected voice is broadcast to other robots in the network where the ontology robot itself is located.
  • the ontology robot After the ontology robot broadcasts the collected voice to the remaining robots in the network where the ontology robot itself is located, the remaining robots in the same network as the ontology robot can receive the environmental voice transmitted by the broadcast transmitting robot in a broadcast manner, and then The received ambient voice is identified, and there may be a case where one or some of the remaining robots recognize that the received ambient voice is used to wake up itself, and then send an identity confirmation response to the robot that sent the broadcast. Therefore, the ontology robot can receive an identity confirmation response sent by one or some robots in the network where the ontology robot itself is located, thereby triggering the ontology robot to recognize the speech itself.
  • the library is updated, that is, according to the received identity confirmation response, the association relationship between the collected environmental voice and the corresponding robot is recorded in the voice recognition library of the ontology robot.
  • the ontology robot can learn the robot corresponding to the collected environmental speech, so that the next time the same environmental speech is collected, according to the updated speech recognition library, the fast The robot corresponding to the environmental voice is determined, and the environmental voice is directly sent to the corresponding robot. In this way, the time for the user to wait for the target robot to respond is shortened, and the response efficiency of the target robot is improved.
  • the voice joint assistance implementation in the robot A broadcasts the environmental voice c to the robot B and the robot C.
  • the robot B and the robot C respectively recognize the received environmental voice.
  • the robot C recognizes that the robot corresponding to the environmental voice c is itself, it sends an identity confirmation response to the robot A to indicate that the robot corresponding to the environmental voice c is the robot C. Since the robot B recognizes that the robot corresponding to the environmental voice c is not itself, it does not transmit an identity confirmation response to the robot A.
  • the robot A can record the association relationship between the environmental voice c and the robot C in the voice recognition library of the robot A.
  • the robot A collects the environmental voice c, it can determine that the robot corresponding to the environmental voice c is the robot C according to its own speech recognition library, and then directly sends the environmental voice c to the robot C, shortening the user waiting for the robot C to do
  • the response time increases the response efficiency of the robot C.
  • FIG. 4 is a block diagram of an apparatus for implementing voice joint assistance according to an exemplary embodiment.
  • the device 1000 includes:
  • the environment voice sending module 401 is configured to: when the environment voice collected by the body robot meets the set condition, send the collected environment voice to other robots;
  • the setting condition is used to indicate that the collected ambient voice is not used to wake up the ontology robot.
  • the apparatus further includes:
  • the first voice recognition module 402 is configured to identify the received ambient voice after receiving the environmental voice sent by the other robot.
  • the setting condition includes: the collected environmental voice cannot be recognized by the ontology robot;
  • the environmental voice sending module is configured to:
  • the collected ambient speech is broadcast in the network in which the ontology robot is located.
  • the setting condition includes: the body robot recognizes that the collected robot corresponds to the target voice, and the target robot is not the ontology robot;
  • the environmental voice sending module is configured to:
  • the collected environmental voice is sent to the target robot.
  • the device further includes:
  • a determining module configured to determine, according to the voice recognition library of the ontology robot, whether the collected ambient voice is a voice that wakes up the ontology robot;
  • a receiving module configured to receive an identity confirmation response after the collected environment voice is broadcasted in the network where the body robot is located, where the identity confirmation response is used to indicate the robot corresponding to the collected environment voice;
  • the recording module is configured to record the association relationship between the collected environmental voice and the corresponding robot in the voice recognition library of the ontology robot.
  • the device further includes:
  • a second voice recognition module configured to: after receiving the environment voice sent by the robot transmitting the broadcast in a broadcast manner, identify the received ambient voice;
  • the response sending module is configured to send the identity confirmation response to the robot that sends the broadcast when the received ambient voice is used to wake up the ontology robot.
  • the device further includes:
  • a positioning module configured to locate a location of the user according to the collected ambient voice
  • the location information sending module is configured to send the location information of the user to other robots when the collected environment voice satisfies the setting condition.
  • FIG. 5 is another block diagram of a voice joint assistance implementation apparatus 1000, which may be configured in a robot, according to an exemplary embodiment.
  • the apparatus 1000 can include a processor 1001, a memory 1002, a multimedia component 1003, an input/output (I/O) interface 1004, and a communication component 1005.
  • the processor 1001 is configured to control the overall operation of the apparatus 1000 to complete all or part of the steps of implementing the voice joint assistance described above.
  • the memory 1002 is for storing various types of data to support operations at the device 1000, such as may include instructions for any application or method operating on the device 1000, as well as application related data, such as Contact data, sent and received messages, pictures, audio, video, and more.
  • the memory 1002 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read only memory ( Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read Only Read-Only Memory (ROM), magnetic memory, flash memory, disk or optical disk.
  • the multimedia component 1003 can include a screen and an audio component.
  • the screen may be, for example, a touch screen, and the audio component is used to output and/or input an audio signal.
  • the audio component can include a microphone for receiving an external audio signal.
  • the received audio signal may be further stored in memory 1002 or transmitted via communication component 1005.
  • the audio component also includes at least one speaker for outputting an audio signal.
  • the I/O interface 1004 provides an interface between the processor 1001 and other interface modules.
  • the other interface modules described above may be a keyboard, a mouse, a button, or the like. These buttons can be virtual buttons or physical buttons.
  • Communication component 1005 is used for wired or wireless communication between the device 1000 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 1005 can include: Wi-Fi module, Bluetooth module, NFC module.
  • the device 1000 may be configured by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), and digital signal processing devices (Digital Signal Processors).
  • ASICs Application Specific Integrated Circuits
  • DSPs Digital Signal Processors
  • Digital Signal Processors Digital Signal Processors
  • DSPD Processing Device
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • controller microcontroller
  • microprocessor or other electronic components The method for implementing the above-described voice joint assistance.
  • a computer program product comprising a computer program executable by a programmable device, the computer program having when executed by the programmable device A code portion of an implementation method for performing the above-described voice joint assistance.
  • non-transitory computer readable storage medium comprising instructions, such as a memory 1002 comprising instructions executable by processor 1001 of apparatus 1000 to perform the voice joint assistance described above Implementation method.
  • the non-transitory computer readable storage medium can be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.
  • a robot comprising: a voice collection device, a non-transitory computer readable storage medium; and one or more processors for performing the non-transitory computer readable a program in a storage medium; the non-transitory computer readable storage Instructions for executing the above method of controlling the robot are stored in the storage medium.
  • the voice collection device may be the above-mentioned environment voice collection module to collect environment voice.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Manipulator (AREA)

Abstract

本公开是关于一种语音联合协助的实现方法、装置及机器人。在用户发出的语音是用于唤醒机器人群组中的目标机器人的情况下，为了使得目标机器人听到用户发出的语音，本公开提出由机器人群组中的其他机器人联合协助用户与目标机器人之间的语音交互，使得机器人与目标机器人之间的语音交互不再受限于用户发出的语音的最大传播距离，或者受限于目标机器人所处的环境噪音。

Description

语音联合协助的实现方法、装置及机器人 技术领域
本公开涉及信息处理领域，特别涉及一种语音联合协助的实现方法、装置及机器人。
背景技术
随着机器人的普及，越来越多的用户开始使用机器人作为个人助理。为最大化地给用户提供便利，用户与机器人之间通常进行语音交互。如果用户需要借助于某个机器人完成某项事务，则可以发出语音，以与具有相应功能的机器人交互，进而使得具有相应功能的机器人完成用户为其分配的事务。例如：用户在一个房间中因碰洒了一杯水而发出用于唤醒擦地机器人的语音，擦地机器人在听到用户发出的语音后，将洒在地上的水擦干，无需用户亲自动手擦干地上的水。可见，机器人给用户带来了极大的便利。
发明内容
本公开的主要目的是提供一种语音联合协助的实现方法、装置及机器人，以通过其他机器人协助用户与目标机器人之间的语音交互，优化了机器人的使用体验。
为了达到上述目的，本公开第一方面提供一种语音联合协助的实现方法，所述方法包括：
在本体机器人采集到的环境语音满足设定条件时，将采集到的环境语音发送给其他机器人；
其中，所述设定条件用于指示采集到的环境语音不是用于唤醒本体机器人。
可选地，所述方法还包括：
在接收到其他机器人发送的环境语音后，对接收到的环境语音进行识别。
可选地，所述设定条件包括：采集到的环境语音无法被本体机器人识别；
将采集到的环境语音发送给其他机器人，包括：
在本体机器人所处的网络中广播采集到的环境语音。
可选地，所述设定条件包括：本体机器人识别出采集到的环境语音对应的机器人是目标机器人，且所述目标机器人不是本体机器人；
将采集到的环境语音发送给其他机器人，包括：
将采集到的环境语音发送给所述目标机器人。
可选地，所述方法还包括：
根据本体机器人的语音识别库，确定采集到的环境语音是否为唤醒本体机器人的语音；
在本体机器人所处的网络中广播采集到的环境语音之后，接收身份确认应答，所述身份确认应答用于指示所述采集到的环境语音对应的机器人；
在本体机器人的语音识别库中记录采集到的环境语音与对应的机器人之间的关联关系。
可选地，所述方法还包括：
在接收到发送广播的机器人以广播方式发送的环境语音之后，对接收到的环境语音进行识别；
在识别出接收到的环境语音用于唤醒本体机器人时，向发送广播的机器人发送所述身份确认应答。
可选地，所述方法还包括：
根据采集到的环境语音，对用户的位置进行定位；
在采集到的环境语音满足所述设定条件时，还将所述用户的位置信息发 送给其他机器人。
本公开第二方面提供一种语音联合协助的实现装置，包括：
环境语音发送模块，用于在本体机器人采集到的环境语音满足设定条件时，将采集到的环境语音发送给其他机器人；
其中，所述设定条件用于指示采集到的环境语音不是用于唤醒本体机器人。
可选地，所述装置还包括：
第一语音识别模块，用于在接收到其他机器人发送的环境语音后，对接收到的环境语音进行识别。
可选地，所述设定条件包括：采集到的环境语音无法被本体机器人识别；
所述环境语音发送模块用于：
在本体机器人所处的网络中广播采集到的环境语音。
可选地，所述设定条件包括：本体机器人识别出采集到的环境语音对应的机器人是目标机器人，且所述目标机器人不是本体机器人；
所述环境语音发送模块用于：
将采集到的环境语音发送给所述目标机器人。
可选地，所述装置还包括：
确定模块，用于根据本体机器人的语音识别库，确定采集到的环境语音是否为唤醒本体机器人的语音；
接收模块，用于在本体机器人所处的网络中广播采集到的环境语音之后，接收身份确认应答，所述身份确认应答用于指示所述采集到的环境语音对应的机器人；
记录模块，用于在本体机器人的语音识别库中记录采集到的环境语音与对应的机器人之间的关联关系。
可选地，所述装置还包括：
第二语音识别模块，用于在接收到发送广播的机器人以广播方式发送的环境语音之后，对接收到的环境语音进行识别；
应答发送模块，用于在识别出接收到的环境语音用于唤醒本体机器人时，向发送广播的机器人发送所述身份确认应答。
可选地，所述装置还包括：
定位模块，用于根据采集到的环境语音，对用户的位置进行定位；
位置信息发送模块，用于在采集到的环境语音满足所述设定条件时，还将所述用户的位置信息发送给其他机器人。
本公开第三方面提供一种计算机程序产品，所述计算机程序产品包含能够由可编程的装置执行的计算机程序，所述计算机程序具有当由所述可编程的装置执行时用于上述语音联合协助的实现方法的代码部分。
本公开第四方面提供一种非临时性计算机可读存储介质，其特征在于，所述非临时性计算机可读存储介质中包括一个或多个程序，所述一个或多个程序用于执行上述语音联合协助的实现方法。
本公开第五方面提供一种机器人，包括：语音采集装置、非临时性计算机可读存储介质；以及一个或者多个处理器，用于执行所述非临时性计算机可读存储介质中的程序；所述非临时性计算机可读存储介质中存储有用于执行上述语音联合协助的实现方法的指令。
采用本公开提供的语音联合协助的实现方法，在用户发出的语音是用于唤醒机器人群组的某一个机器人(即目标机器人)的情况下，为了使得目标机器人听到用户发出的语音，由机器人群组中的其他机器人联合协助用户与目标机器人之间的语音交互。也就是说，借助于机器人群组中的其他机器人，搭建用户与目标机器人之间的交互通道，使得机器人与目标机器人之间的语音交互不再受限于用户发出的语音的最大传播距离，或者受限于目标机器人所处的环境噪音。增加了目标机器人对用户发出的语音的响应概率，提高了 机器人的使用体验。
本公开的其他特征和优点将在随后的具体实施方式部分予以详细说明。
附图说明
附图是用来提供对本公开的进一步理解，并且构成说明书的一部分，与下面的具体实施方式一起用于解释本公开，但并不构成对本公开的限制。在附图中：
图1是根据一示例性实施例示出的机器人群组的示意图。
图2是根据一示例性实施例示出的一种语音联合协助的实现方法的流程图。
图3是根据一示例性实施例示出的一种语音联合协助的实现方法的另一示意图。
图4是根据一示例性实施例示出的一种语音联合协助的实现装置的框图。
图5是根据一示例性实施例示出的一种语音联合协助的实现装置1000的另一框图。
具体实施方式
以下结合附图对本公开的具体实施方式进行详细说明。应当理解的是，此处所描述的具体实施方式仅用于说明和解释本公开，并不用于限制本公开。
机器人给用户带来极大的便利，前提条件是机器人听到用户发出的语音。在某些场景下，机器人可能无法听到用户发出的语音。一种可能的场景是：机器人距离用户较远。由于用户发出的语音的具有最大响度，因而用户 发出的语音具有最大传播距离。在机器人与用户之间的距离大于该最大传播距离的情况下，机器人无法听到用户发出的语音。另一种可能的场景是：机器人处于非稳态噪音环境下。由于机器人受到非稳态噪音的干扰，所以可能无法听到用户发出的语音。
为此，本公开提出一种语音联合协助的实现方法，该方法适用于由多个机器人组成的机器人群组，机器人群组中的各个机器人通常分布在不同的位置上。在用户发出的语音是用于唤醒机器人群组的某一个机器人(以下简称目标机器人)的情况下，为了使得目标机器人听到用户发出的语音，本公开提出由机器人群组中的其他机器人联合协助用户与目标机器人之间的语音交互。也就是说，借助于机器人群组中的其他机器人，搭建用户与目标机器人之间的交互通道，使得机器人与目标机器人之间的语音交互不再受限于用户发出的语音的最大传播距离，或者受限于目标机器人所处的环境噪音。
示例地，请参考图1，图1是根据一示例性实施例示出的机器人群组的示意图。图1以机器人群组包括三个机器人为例。如图1所示，机器人群组包括：机器人A、机器人B以及机器人C，三者分别分布于不同的房间中，其中机器人A距离用户最近，与用户在同一房间内，机器人B距离用户较远，机器人C距离用户最远。
在用户发出的语音是用于唤醒机器人C的情况下，采用本公开提供的语音联合协助的实现方法，通过机器人A和机器人B搭建用户与机器人C之间的交互通道，由机器人A和机器人B对用户发出的语音进行接力，进而使得机器人C对用户发出的语音进行响应。如图1所示，机器人A距离用户较近，所以机器人A最先听到该语音，然后将该语音转发给机器人B，机器人B再将接收到的环境语音转发给机器人C，以此实现联合语音协助。
接下来，对本公开提供的语音联合协助的实现方法进行说明。该方法适用于机器人群组中的任一机器人。请参考图2，图2是根据一示例性实施例 示出的一种语音联合协助的实现方法的流程图。如图2所示，该方法包括以下步骤：
步骤S21：在本体机器人采集到的环境语音满足设定条件时，将采集到的环境语音发送给其他机器人；
其中，所述设定条件用于指示采集到的环境语音不是用于唤醒本体机器人。
本公开中，本体机器人不是特指某一机器人，而是一个相对的概念，是执行该方法的机器人，可以是机器人群组中的任一机器人。本体机器人配置有语音联合协助的实现装置，由语音联合协助的实现装置执行上述步骤。
本体机器人内置有语音采集模块，用于采集环境语音。环境语音是指本体机器人所处的环境中的语音，根据本体机器人与用户之间的位置关系，环境语音可能包括用户发出的语音，语音采集模块将用户发出的语音转换为语音信号，以供语音联合协助的实现装置对该语音信号进行进一步处理。语音联合协助的实现装置在该语音信号满足设定条件时，将该语音信号打包成语音数据包发送给其他机器人。
根据机器人群组中的各个机器人与用户之间的相对位置关系，机器人群组中可能有一个或多个机器人的语音采集模块均采集到用户发出的语音，进而各自触发与之通信的语音联合协助的实现装置执行本公开提供的语音联合协助的实现方法。
语音采集模块可以是内置于语音联合协助的实现装置的组件，还可以独立于语音联合协助装置。语音采集模块与语音联合协助的实现装置之间可以进行通信。在语音采集模块采集到环境语音时，语音采集模块将该事件通知给语音联合协助的实现装置，语音联合协助的实现装置对该事件做出响应。
由于用户发出的语音具有随机性，即用户需要唤醒的机器人(下文简称目标机器人)是随机的，可能是本体机器人，也可能是机器人群组中除本体 机器人外的其他机器人。对于目标机器人是本体机器人的情况，由本体机器人自身直接听到用户发出的语音，无需采用本公开提供的语音联合协助的实现方法；对于目标机器人不是本体机器人的情况，可以采用本公开提供的语音联合协助的实现方法，本体机器人将采集到的环境语音转发给机器人群组中的其他机器人，接收到环境语音的其他机器人再作为本体机器人，并将接收到的环境语音等同于自身采集到的环境语音，执行本公开提供的语音联合协助的实现方法，直到目标机器人接收到环境语音为止。
由于在目标机器人不是本体机器人的情况下，可以采用本公开提供的语音联合协助的实现方法，所以本公开提出设定条件，以指示采集到的环境语音不是用于唤醒本体机器人。因而语音联合协助的实现装置对语音采集模块采集到环境语音这一事件做出的响应是：将语音采集模块采集到的环境语音与该设定条件进行比较，在采集到的环境语音满足设定条件时，将采集到的环境语音发送给机器人群组中的其他机器人。
示例地，用户在一个房间中因碰洒了一杯水而发出用于唤醒擦地机器人(以图1中的机器人C示意)的语音，用户发出的语音作为环境语音在空气中传播，由于机器人群组中的各个机器人与用户之间的相对位置关系，本体机器人(以图1中的机器人A示意)中的语音采集模块采集到该环境语音，因而触发本体机器人中的语音联合协助的实现装置将该环境语音与设定条件进行比较，在该环境语音满足设定条件时，也即该环境语音不是用于唤醒本体机器人时，将该环境语音发送给其他机器人(以图1示意，机器人A将该环境语音发送给机器人B)。接收到该环境语音的其他机器人(以图1中的机器人B示意)再作为本体机器人，并将接收到的环境语音等同于自身采集到的环境语音，执行本公开提供的语音联合协助的实现方法，直到目标机器人接收到该环境语音为止。
可见，采用本公开提供的语音联合协助的实现方法，可以借助于机器人 群组中的其他机器人，搭建用户与目标机器人之间的交互通道，使得机器人与目标机器人之间的语音交互不再受限于用户发出的语音的最大传播距离，或者受限于目标机器人所处的环境噪音。增加了目标机器人对用户发出的语音的响应概率，提高了机器人的使用体验。
可选地，如图2所示，本公开提供的语音联合协助的实现方法除包括步骤S21外，还包括以下步骤：
步骤S22：在接收到其他机器人发送的环境语音后，对接收到的环境语音进行识别。
对于本体机器人来说，一方面，本体机器人内的语音采集模块对环境语音进行采集，在本体机器人内的语音采集模块采集到环境语音时，触发本体机器人内的语音联合协助的实现装置执行上述步骤S21；另一方面，由于本体机器人处于机器人群组中，所以可能会收到其他机器人发送的环境语音，在本体机器人接收到其他机器人发送的环境语音后，触发本体机器人内的语音联合协助的实现装置执行上述步骤S22。
本体机器人对接收到的环境语音进行识别，首先要求本体机器人具有语音识别功能。在本体机器人具有语音识别功能的前提下，在识别出用户发出的语音是用于唤醒本体机器人自身的时，生成针对用户发出的语音的应答；在识别出用户发出的语音不是用户唤醒本体机器人自身的时，也即在用户发出的语音不满足设定条件时，将用户发出的语音发送给机器人群组中的其他机器人。
采用以上技术方案，机器人群组中每个作为本体机器人的机器人，都会对接收到的环境语音进行识别，进而保证机器人群组中至少有一个机器人识别出用户发出的语音是用于唤醒自身的，进而生成针对用户发出的语音的应答，以使用户及时获得目标机器人的应答，提高了目标机器人的响应效率。避免了用户发出的语音反复在机器人群组中的各个机器人之间相互转发，节 约了网络传输资源以及机器人群组中的各个机器人的功耗。
可选地，请参考图3，图3是根据一示例性实施例示出的一种语音联合协助的实现方法的另一示意图。如图3所示，本公开提供的语音联合协助的实现方法除包括步骤S21外，还包括以下步骤：
步骤S23：根据采集到的环境语音对用户的位置进行定位；
步骤S24：在采集到的环境语音满足所述设定条件时，还将所述用户的位置信息发送给其他机器人。
其中，步骤S23与步骤S21的执行顺序不分先后，两者可以先后执行或者并行执行。图3以步骤S21先于步骤S24执行为例。
可选地，本体机器人可以根据采集到的环境语音，对用户的位置进行定位。一种可能的定位方法是：机器人群组中的各个机器人根据能够获得自身的位置信息，并且机器人群组中采集到同一用户发出的语音的一个或多个机器人还可以判断出用户声音来自的方向，因此，一种可能的情况是：在有两个或多个机器人采集到同一用户发出的语音的情况下，两个或多个采集到环境语音机器人判断出用户声音来自的方向，进而确定用户的位置信息。另一种可能的情况是：在仅有一个机器人采集到用户发出的语音的情况下，可以知道用户在某一条线上，结合地图，可以确定用户的位置信息。
在本体机器人确定用户的位置信息之后，在采集到的环境语音满足设定条件时，本体机器人除将采集到的环境语音发送给其他机器人外，还可以将用户的位置信息发送给其他机器人。
由于将用户的位置信息发送给其他机器人，而目标机器人可能是其他机器人中的，所以便于目标机器人根据用户的位置信息快速行进到用户身边，缩短了用户等待目标机器人做出响应的时间，提高了目标机器人的响应效率。
可选地，根据机器人群组中每个作为本体机器人是否能够识别本体机器 人自身采集到的环境语音，本体机器人对采集到的环境语音的发送方式不同。
在本体机器人不能识别本体机器人自身内的语音采集模块采集到的环境语音的前提下，所述设定条件包括：采集到的环境语音无法被本体机器人识别；将采集到的环境语音发送给其他机器人，包括：在本体机器人所处的网络中广播采集到的环境语音。
由于本体机器人内的语音采集模块采集到的环境语音无法被本体机器人自身识别，所以为了节省本体机器人的功耗，本体机器人内的语音联合协助的实现装置将该环境语音广播给自身所处的网络中的其他机器人。
示例地，以图1所示的机器人群组为例，假设图1所示的机器人群组中的机器人A、机器人B以及机器人C处于同一网络中。在机器人A内的语音采集模块采集到的环境语音c不是用于唤醒机器人A自身，且无法被机器人A自身识别时，机器人A内的语音联合协助的实现装置将环境语音c广播给机器人B和机器人C。
在本体机器人能够识别本体机器人自身内的语音采集模块采集到的环境语音的前提下，所述设定条件包括：本体机器人识别出采集到的环境语音对应的机器人是目标机器人，且所述目标机器人不是本体机器人；将采集到的环境语音发送给其他机器人，包括：将采集到的环境语音发送给所述目标机器人。
由于本体机器人能够识别自身采集到的环境语音，所以本体机器人可以得到识别结果。在识别结果为：采集到的环境语音对应的机器人是目标机器人，且目标机器人不是本体机器人时，由于本体机器人已经识别出采集到的环境语音对应的机器人是目标机器人，所以本体机器人内的语音联合协助的实现装置将该环境语音发送给目标机器人。
示例地，以图1所示的机器人群组为例。在机器人A内的语音采集模块 采集到的环境语音c不是用于唤醒机器人A自身，且机器人A识别出环境语音c对应的机器人是机器人C时，机器人A内的语音联合协助的实现装置将环境语音c发送给机器人C。
上述两种不同的对采集到的环境语音的发送方式，可以适用于不具有语音识别功能的机器人、具有部分语音识别功能的机器人(仅能够对自身的语音识别库中的各个语音进行识别的机器人)、以及具有完全语音识别功能的机器人(能够对任何语音进行识别的机器人)。
机器人群组可能既包括不具有语音识别功能的机器人，也包括具有部分语音识别功能的机器人，还包括具有完全识别功能的机器人，因此，具有不同功能的机器人均可以作为本体机器人，以执行本公开提供的语音联合协助的实现方法，拓展了本公开提供的语音联合协助的实现方法的适用范围。
可选地，在本体机器人以广播方式对采集到的环境语音进行发送的情况下，本公开提供的语音联合协助的实现方法还可以包括以下步骤：
根据本体机器人的语音识别库，确定采集到的环境语音是否为唤醒本体机器人的语音；
在本体机器人所处的网络中广播采集到的环境语音之后，接收身份确认应答，所述身份确认应答用于指示所述采集到的环境语音对应的机器人；
在本体机器人的语音识别库中记录采集到的环境语音与对应的机器人之间的关联关系。
可选地，在本体机器人以广播方式对采集到的环境语音进行发送的情况下，本公开提供的语音联合协助的实现方法还可以包括以下步骤：
在接收到发送广播的机器人以广播方式发送的环境语音之后，对接收到的环境语音进行识别；
在识别出接收到的环境语音用于唤醒本体机器人时，向发送广播的机器人发送所述身份确认应答。
在本体机器人是上述具有部分语音识别功能的机器人的情况下，以及在本体机器人是上述具有完全语音识别功能的机器人的情况下，本公开提出身份确认应答，以对本体机器人的语音识别库进行更新，其中，身份确认应答是某一机器人在识别出另一机器人采集到的环境语音对应的机器人是自身时，发送给另一机器人的应答。
本体机器人的语音识别库中包括本体机器人采集到的不同环境语音与对应的机器人之间的关联关系，该关联关系可能是某一语音与本体机器人自身之间的关联关系，也可能是某一语音与其他机器人之间的关联关系。示例地，机器人A的语音识别库中的两条记录分别为：机器人A采集到的环境语音a对应的机器人是机器人A；机器人A采集到的环境语音c对应的机器人是机器人C。
本体机器人在自身的语音采集模块采集到环境语音时，触发自身的语音联合协助的实现装置，将采集到的环境语音与本体机器人的语音识别库中的各个语音依次进行匹配，以确定采集到的环境语音是否为唤醒本体机器人的语音，如果采集到的环境语音是唤醒本体机器人的语音，则本体机器人采集到的环境语音不满足设定条件；如果采集到的环境语音不是唤醒本体机器人的语音，则本体机器人采集到的环境语音满足设定条件，进而将采集到的语音广播给本体机器人自身所处网络中的其他机器人。
在本体机器人将采集到的语音广播给本体机器人自身所处网络中的剩余机器人之后，与本体机器人处于同一网络中的剩余机器人均可以接收到发送广播的机器人以广播方式发送的环境语音，进而对接收到的环境语音进行识别，可能存在的情况是：剩余机器人中的某个或某些机器人识别出接收到的环境语音是用于唤醒自身的，进而向发送广播的机器人发送身份确认应答。因而，本体机器人可以接收到来自于本体机器人自身所处网络中的某个或某些机器人发送的身份确认应答，进而触发本体机器人对自身的语音识别 库进行更新，即：根据接收到的身份确认应答，在本体机器人的语音识别库中记录采集到的环境语音与对应的机器人之间的关联关系。
采用上述对本体机器人的语音识别库进行更新的方法，本体机器人可以对采集到的环境语音对应的机器人进行学习，以便于在下次采集到相同的环境语音时，根据更新后的语音识别库，快速确定出该环境语音对应的机器人，进而直接将该环境语音发送给对应的机器人。以此缩短用户等待目标机器人做出响应的时间，提高了目标机器人的响应效率。
继续沿用上述例子，机器人A内的语音联合协助的实现装置将环境语音c广播给机器人B和机器人C。机器人B和机器人C分别对接收到的环境语音进行识别，在机器人C识别出环境语音c对应的机器人是自身时，向机器人A发送身份确认应答，以指示环境语音c对应的机器人是机器人C，由于机器人B识别出环境语音c对应的机器人不是自身，所以不向机器人A发送身份确认应答。机器人A在接收到机器人C发送的身份确认应答之后，即可在机器人A的语音识别库中记录环境语音c与机器人C之间的关联关系。这样，下一次机器人A采集到环境语音c时，即可根据自身的语音识别库确定环境语音c对应的机器人是机器人C，进而直接将环境语音c发送给机器人C，缩短了用户等待机器人C做出响应的时间，提高了机器人C的响应效率。
基于同一发明构思，本公开还提供一种语音联合协助的实现装置。请参考图4，图4是根据一示例性实施例示出的一种语音联合协助的实现装置的框图。如图4所示，该装置1000包括：
环境语音发送模块401，用于在本体机器人采集到的环境语音满足设定条件时，将采集到的环境语音发送给其他机器人；
其中，所述设定条件用于指示采集到的环境语音不是用于唤醒本体机器人。
可选地，如图4所示，所述装置还包括：
第一语音识别模块402，用于在接收到其他机器人发送的环境语音后，对接收到的环境语音进行识别。
可选地，所述设定条件包括：采集到的环境语音无法被本体机器人识别；
所述环境语音发送模块用于：
在本体机器人所处的网络中广播采集到的环境语音。
可选地，所述设定条件包括：本体机器人识别出采集到的环境语音对应的机器人是目标机器人，且所述目标机器人不是本体机器人；
所述环境语音发送模块用于：
将采集到的环境语音发送给所述目标机器人。
可选地，所述装置还包括：
确定模块，用于根据本体机器人的语音识别库，确定采集到的环境语音是否为唤醒本体机器人的语音；
接收模块，用于在本体机器人所处的网络中广播采集到的环境语音之后，接收身份确认应答，所述身份确认应答用于指示所述采集到的环境语音对应的机器人；
记录模块，用于在本体机器人的语音识别库中记录采集到的环境语音与对应的机器人之间的关联关系。
可选地，所述装置还包括：
第二语音识别模块，用于在接收到发送广播的机器人以广播方式发送的环境语音之后，对接收到的环境语音进行识别；
应答发送模块，用于在识别出接收到的环境语音用于唤醒本体机器人时，向发送广播的机器人发送所述身份确认应答。
可选地，所述装置还包括：
定位模块，用于根据采集到的环境语音，对用户的位置进行定位；
位置信息发送模块，用于在采集到的环境语音满足所述设定条件时，还将所述用户的位置信息发送给其他机器人。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图5是根据一示例性实施例示出的一种语音联合协助的实现装置1000的另一框图，该装置1000可以配置于机器人中。如图5所示，该装置1000可以包括：处理器1001，存储器1002，多媒体组件1003，输入/输出(I/O)接口1004，以及通信组件1005。
其中，处理器1001用于控制该装置1000的整体操作，以完成上述的语音联合协助的实现方法中的全部或部分步骤。存储器1002用于存储各种类型的数据以支持在该装置1000的操作，这些数据的例如可以包括用于在该装置1000上操作的任何应用程序或方法的指令，以及应用程序相关的数据，例如联系人数据、收发的消息、图片、音频、视频等等。该存储器1002可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，例如静态随机存取存储器(Static Random Access Memory，简称SRAM)，电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory，简称EEPROM)，可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，简称EPROM)，可编程只读存储器(Programmable Read-Only Memory，简称PROM)，只读存储器(Read-Only Memory，简称ROM)，磁存储器，快闪存储器，磁盘或光盘。多媒体组件1003可以包括屏幕和音频组件。其中屏幕例如可以是触摸屏，音频组件用于输出和/或输入音频信号。例如，音频组件可以包括一个麦克风，麦克风用于接收外部音频信号。所接收的音频信号可以被进一步存储在存储器1002或通过通信组件1005发送。音频组件还包括至少一个扬声器，用于输出音频信号。I/O接口1004为处理器1001和其他接口模块之间提供接口， 上述其他接口模块可以是键盘，鼠标，按钮等。这些按钮可以是虚拟按钮或者实体按钮。通信组件1005用于该装置1000与其他设备之间进行有线或无线通信。无线通信，例如Wi-Fi，蓝牙，近场通信(Near Field Communication，简称NFC)，2G、3G或4G，或它们中的一种或几种的组合，因此相应的该通信组件1005可以包括：Wi-Fi模块，蓝牙模块，NFC模块。
在一示例性实施例中，装置1000可以被一个或多个应用专用集成电路(Application Specific Integrated Circuit，简称ASIC)、数字信号处理器(Digital Signal Processor，简称DSP)、数字信号处理设备(Digital Signal Processing Device，简称DSPD)、可编程逻辑器件(Programmable Logic Device，简称PLD)、现场可编程门阵列(Field Programmable Gate Array，简称FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述的语音联合协助的实现方法。
在另一示例性实施例中，还提供了一种计算机程序产品，所述计算机程序产品包含能够由可编程的装置执行的计算机程序，所述计算机程序具有当由所述可编程的装置执行时用于执行上述的语音联合协助的实现方法的代码部分。
在另一示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器1002，上述指令可由装置1000的处理器1001执行以完成上述的语音联合协助的实现方法。示例地，该非临时性计算机可读存储介质可以是ROM、随机存取存储器(Random Access Memory，简称RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在另一示例性实施例中，还提供了一种机器人，包括：语音采集装置、非临时性计算机可读存储介质；以及一个或者多个处理器，用于执行所述非临时性计算机可读存储介质中的程序；所述非临时性计算机可读存 储介质中存储有用于执行上述控制机器人的方法的指令。其中，语音采集装置可以是上述环境语音采集模块，以采集环境语音。
以上结合附图详细描述了本公开的优选实施方式，但是，本公开并不限于上述实施方式中的具体细节，在本公开的技术构思范围内，可以对本公开的技术方案进行多种简单变型，这些简单变型均属于本公开的保护范围。
另外需要说明的是，在上述具体实施方式中所描述的各个具体技术特征，在不矛盾的情况下，可以通过任何合适的方式进行组合。为了避免不必要的重复，本公开对各种可能的组合方式不再另行说明。

Claims (17)

  1. 一种语音联合协助的实现方法，其特征在于，所述方法包括：
    在本体机器人采集到的环境语音满足设定条件时，将采集到的环境语音发送给其他机器人；
    其中，所述设定条件用于指示采集到的环境语音不是用于唤醒本体机器人。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在接收到其他机器人发送的环境语音后，对接收到的环境语音进行识别。
  3. 根据权利要求1所述的方法，其特征在于，所述设定条件包括：采集到的环境语音无法被本体机器人识别；
    将采集到的环境语音发送给其他机器人，包括：
    在本体机器人所处的网络中广播采集到的环境语音。
  4. 根据权利要求1所述的方法，其特征在于，所述设定条件包括：本体机器人识别出采集到的环境语音对应的机器人是目标机器人，且所述目标机器人不是本体机器人；
    将采集到的环境语音发送给其他机器人，包括：
    将采集到的环境语音发送给所述目标机器人。
  5. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    根据本体机器人的语音识别库，确定采集到的环境语音是否为唤醒本体机器人的语音；
    在本体机器人所处的网络中广播采集到的环境语音之后，接收身份确认应答，所述身份确认应答用于指示所述采集到的环境语音对应的机器人；
    在本体机器人的语音识别库中记录采集到的环境语音与对应的机器人之间的关联关系。
  6. 根据权利要求5所述的方法，其特征在于，所述方法还包括：
    在接收到发送广播的机器人以广播方式发送的环境语音之后，对接收到的环境语音进行识别；
    在识别出接收到的环境语音用于唤醒本体机器人时，向发送广播的机器人发送所述身份确认应答。
  7. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    根据采集到的环境语音，对用户的位置进行定位；
    在采集到的环境语音满足所述设定条件时，还将所述用户的位置信息发送给其他机器人。
  8. 一种语音联合协助的实现装置，其特征在于，包括：
    环境语音发送模块，用于在本体机器人采集到的环境语音满足设定条件时，将采集到的环境语音发送给其他机器人；
    其中，所述设定条件用于指示采集到的环境语音不是用于唤醒本体机器人。
  9. 根据权利要求8所述的装置，其特征在于，所述装置还包括：
    第一语音识别模块，用于在接收到其他机器人发送的环境语音后，对接收到的环境语音进行识别。
  10. 根据权利要求8所述的装置，其特征在于，所述设定条件包括：采集到的环境语音无法被本体机器人识别；
    所述环境语音发送模块用于：
    在本体机器人所处的网络中广播采集到的环境语音。
  11. 根据权利要求8所述的装置，其特征在于，所述设定条件包括：本体机器人识别出采集到的环境语音对应的机器人是目标机器人，且所述目标机器人不是本体机器人；
    所述环境语音发送模块用于：
    将采集到的环境语音发送给所述目标机器人。
  12. 根据权利要求8所述的装置，其特征在于，所述装置还包括：
    确定模块，用于根据本体机器人的语音识别库，确定采集到的环境语音是否为唤醒本体机器人的语音；
    接收模块，用于在本体机器人所处的网络中广播采集到的环境语音之后，接收身份确认应答，所述身份确认应答用于指示所述采集到的环境语音对应的机器人；
    记录模块，用于在本体机器人的语音识别库中记录采集到的环境语音与对应的机器人之间的关联关系。
  13. 根据权利要求12所述的装置，其特征在于，所述装置还包括：
    第二语音识别模块，用于在接收到发送广播的机器人以广播方式发送的环境语音之后，对接收到的环境语音进行识别；
    应答发送模块，用于在识别出接收到的环境语音用于唤醒本体机器人时，向发送广播的机器人发送所述身份确认应答。
  14. 根据权利要求8所述的装置，其特征在于，所述装置还包括：
    定位模块，用于根据采集到的环境语音，对用户的位置进行定位；
    位置信息发送模块，用于在采集到的环境语音满足所述设定条件时，还将所述用户的位置信息发送给其他机器人。
  15. 一种计算机程序产品，其特征在于，所述计算机程序产品包含能够由可编程的装置执行的计算机程序，所述计算机程序具有当由所述可编程的装置执行时用于执行权利要求1至7中任一项所述的方法的代码部分。
  16. 一种非临时性计算机可读存储介质，其特征在于，所述非临时性计算机可读存储介质中包括一个或多个程序，所述一个或多个程序用于执行权利要求1至7中任一项所述的方法。
  17. 一种机器人，其特征在于，包括：语音采集装置、非临时性计算机可读存储介质；以及
    一个或者多个处理器，用于执行所述非临时性计算机可读存储介质中的程序；所述非临时性计算机可读存储介质中存储有用于执行如权利要求1-7任一项所述的方法的指令。
PCT/CN2016/109902 2016-12-14 2016-12-14 语音联合协助的实现方法、装置及机器人 WO2018107389A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201680002711.XA CN107077844B (zh) 2016-12-14 2016-12-14 语音联合协助的实现方法、装置及机器人
PCT/CN2016/109902 WO2018107389A1 (zh) 2016-12-14 2016-12-14 语音联合协助的实现方法、装置及机器人

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/109902 WO2018107389A1 (zh) 2016-12-14 2016-12-14 语音联合协助的实现方法、装置及机器人

Publications (1)

Publication Number Publication Date
WO2018107389A1 true WO2018107389A1 (zh) 2018-06-21

Family

ID=59623435

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/109902 WO2018107389A1 (zh) 2016-12-14 2016-12-14 语音联合协助的实现方法、装置及机器人

Country Status (2)

Country Link
CN (1) CN107077844B (zh)
WO (1) WO2018107389A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112235733A (zh) * 2020-09-29 2021-01-15 北京海益同展信息科技有限公司 一种多设备协作方法、装置、系统及介质
US20220157305A1 (en) * 2019-03-29 2022-05-19 Sony Group Corporation Information processing apparatus, information processing method, and program

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107919119A (zh) * 2017-11-16 2018-04-17 百度在线网络技术（北京）有限公司 多设备交互协同的方法、装置、设备及计算机可读介质
CN109215658A (zh) * 2018-11-30 2019-01-15 广东美的制冷设备有限公司 设备的语音唤醒方法、装置和家电设备
CN109767772A (zh) * 2019-03-14 2019-05-17 百度在线网络技术（北京）有限公司 分布式语音交互方法和系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014002500A (ja) * 2012-06-18 2014-01-09 Hochiki Corp 警報システム
CN103916299A (zh) * 2013-01-02 2014-07-09 Lg电子株式会社 家用电器及其操作方法
CN104605793A (zh) * 2014-09-23 2015-05-13 东莞市万锦电子科技有限公司 地面清洁机器人系统及智能家电系统
CN105723635A (zh) * 2013-09-16 2016-06-29 Lg电子株式会社 家用电器及移动终端
CN105788599A (zh) * 2016-04-14 2016-07-20 北京小米移动软件有限公司 语音处理方法、路由器及智能语音控制系统
CN105929827A (zh) * 2016-05-20 2016-09-07 北京地平线机器人技术研发有限公司 移动机器人及其定位方法

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006243555A (ja) * 2005-03-04 2006-09-14 Nec Corp 対応決定システム、ロボット、イベント出力サーバ、および対応決定方法
JP2007160473A (ja) * 2005-12-15 2007-06-28 Fujitsu Ltd ロボットにおける対話相手識別方法およびロボット
KR20080090034A (ko) * 2007-04-03 2008-10-08 삼성전자주식회사 음성 화자 인식 방법 및 시스템
CN101227503B (zh) * 2008-01-29 2012-08-08 浙江大学 智能微小型地面机器人与无线传感器节点间的通信方法
WO2014089778A1 (zh) * 2012-12-12 2014-06-19 华为技术有限公司 一种在线状态信息交互方法、机器人及系统
CN105206275A (zh) * 2015-08-31 2015-12-30 小米科技有限责任公司 一种设备控制方法、装置及终端
CN105563484B (zh) * 2015-12-08 2018-04-10 深圳达闼科技控股有限公司 一种云机器人系统、机器人和机器人云平台

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014002500A (ja) * 2012-06-18 2014-01-09 Hochiki Corp 警報システム
CN103916299A (zh) * 2013-01-02 2014-07-09 Lg电子株式会社 家用电器及其操作方法
CN105723635A (zh) * 2013-09-16 2016-06-29 Lg电子株式会社 家用电器及移动终端
CN104605793A (zh) * 2014-09-23 2015-05-13 东莞市万锦电子科技有限公司 地面清洁机器人系统及智能家电系统
CN105788599A (zh) * 2016-04-14 2016-07-20 北京小米移动软件有限公司 语音处理方法、路由器及智能语音控制系统
CN105929827A (zh) * 2016-05-20 2016-09-07 北京地平线机器人技术研发有限公司 移动机器人及其定位方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220157305A1 (en) * 2019-03-29 2022-05-19 Sony Group Corporation Information processing apparatus, information processing method, and program
EP3950236A4 (en) * 2019-03-29 2022-07-06 Sony Group Corporation INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD AND PROGRAM
CN112235733A (zh) * 2020-09-29 2021-01-15 北京海益同展信息科技有限公司 一种多设备协作方法、装置、系统及介质
CN112235733B (zh) * 2020-09-29 2023-06-23 京东科技信息技术有限公司 一种多移动机器人协作方法、装置、系统及介质

Also Published As

Publication number Publication date
CN107077844A (zh) 2017-08-18
CN107077844B (zh) 2020-07-31

Similar Documents

Publication Publication Date Title
WO2018107389A1 (zh) 语音联合协助的实现方法、装置及机器人
CN112272819B (zh) 被动唤醒用户交互设备的方法和系统
US20210065716A1 (en) Voice processing method and electronic device supporting the same
CN107026943B (zh) 语音交互方法及系统
CN106910500B (zh) 对带麦克风阵列的设备进行语音控制的方法及设备
US20190207777A1 (en) Voice command processing in low power devices
EP3062309A2 (en) Low power detection of an activation phrase
JP2019117623A (ja) 音声対話方法、装置、デバイス及び記憶媒体
US9936355B2 (en) Information processing apparatus, information processing method, and computer program
CN110709930B (zh) 用于提供有关检测到的事件的信息的方法、系统和介质
CN105976821B (zh) 动物语言识别方法和装置
US20210144498A1 (en) Method for Detecting Blocking of Microphone and Related Products
US20210383806A1 (en) User input processing method and electronic device supporting same
US11636867B2 (en) Electronic device supporting improved speech recognition
US11874876B2 (en) Electronic device and method for predicting an intention of a user
JP2019040602A (ja) 人工知能機器における連続会話機能
WO2021212388A1 (zh) 一种交互沟通实现方法、设备和存储介质
US20200034112A1 (en) Electronic device for performing operation according to user input after partial landing
EP3493200B1 (en) Voice-controllable device and method of voice control
CN110958348B (zh) 语音处理方法、装置、用户设备及智能音箱
CN115691498A (zh) 语音交互方法、电子设备及介质
CN113889116A (zh) 语音信息的处理方法和装置、存储介质及电子装置
WO2024055831A1 (zh) 一种语音交互方法、装置及终端
KR20190092168A (ko) 보이스 리스폰스를 제공하는 방법 및 그 장치
CN108322852B (zh) 一种智能音箱的语音播放方法、装置及存储介质

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: 16924105

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 08/11/2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16924105

Country of ref document: EP

Kind code of ref document: A1