CN112820290A - Household appliance and voice control method, voice device and computer storage medium thereof - Google Patents
Household appliance and voice control method, voice device and computer storage medium thereof Download PDFInfo
- Publication number
- CN112820290A CN112820290A CN202011645138.9A CN202011645138A CN112820290A CN 112820290 A CN112820290 A CN 112820290A CN 202011645138 A CN202011645138 A CN 202011645138A CN 112820290 A CN112820290 A CN 112820290A
- Authority
- CN
- China
- Prior art keywords
- voice
- instruction
- full
- control method
- duplex mode
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000007613 environmental effect Effects 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 description 28
- 238000010586 diagram Methods 0.000 description 12
- 230000003993 interaction Effects 0.000 description 11
- 230000001276 controlling effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 3
- 238000010408 sweeping Methods 0.000 description 3
- 238000004378 air conditioning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/282—Controlling appliance services of a home automation network by calling their functionalities based on user interaction within the home
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses a voice control method of household electrical appliance, which carries out voice control on the household electrical appliance through a voice device; the voice control method comprises the following steps: receiving a voice awakening instruction, and awakening the voice device according to the voice awakening instruction; and collecting and identifying voice information of the surrounding environment, and switching the voice modes according to the type of the voice instruction when the voice instruction is identified. The invention also discloses household electrical appliance equipment, a voice device and a computer storage medium. Compared with the voice control scheme in the prior art, the method and the device have the advantages that the full-duplex mode and the non-full-duplex mode are automatically switched according to the type of the voice, so that the requirements of different use scenes are met, the voice mode is simply switched, and the voice control is smoother.
Description
Technical Field
The present invention relates to the field of home appliances, and in particular, to a home appliance, a voice control method thereof, a voice device, and a computer storage medium.
Background
Along with the intelligent development of household appliances, people have higher and higher intelligent requirements on the household appliances, for example, people hope that voice communication with the household appliances can be smoother and even reach natural communication between people through voice control of the household appliances.
However, the current voice control technology of the home appliance still needs to be improved in terms of fluency of voice interaction.
Disclosure of Invention
The embodiment of the application solves the technical problem of fluency of voice interaction of household appliances in the prior art by providing the household appliance and the voice control method, the voice device and the computer storage medium thereof.
The embodiment of the application provides a voice control method of household electrical appliances, which carries out voice control on the household electrical appliances through a voice device; the voice control method comprises the following steps:
receiving a voice awakening instruction, and awakening the voice device according to the voice awakening instruction;
collecting and recognizing voice information of surrounding environment, and switching voice modes according to the type of a voice instruction when the voice instruction is recognized; the voice modes include a full duplex mode and a non-full duplex mode.
In an embodiment of the present application, the collecting and recognizing voice information of the surrounding environment includes:
picking up surrounding environmental voices according to a current voice mode, and processing the picked-up environmental voices to obtain voice characteristic information;
and matching the obtained voice characteristic information with the voice characteristic information corresponding to the type of the voice command, and judging the type of the voice command of the environmental voice according to a matching result.
In an embodiment of the present application, before performing speech recognition on the picked-up environmental speech, the method further includes:
and carrying out segmentation processing on the collected environmental voice, and carrying out voice recognition on the segmented environmental voice at the same time.
In an embodiment of the present application, the voice control method further includes:
if the voice command is not recognized within a preset time, exiting the current voice mode and exiting the awakening state.
In an embodiment of the present application, the voice control method further includes:
and under the non-full-duplex mode, controlling the household appliance to execute the recognized voice command, and determining whether to exit the awakening state according to the type of the non-full-duplex mode.
In an embodiment of the present application, the voice control method further includes:
and when an instruction of entering the full duplex mode sent by the mobile terminal is received, entering the full duplex mode.
In an embodiment of the present application, the voice control method further includes:
and if the picked-up environmental voice is recognized as a voice command, stopping the current voice broadcasting and controlling the household appliance to execute the voice control command.
The embodiment of the present application further provides a speech device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the speech control method of the foregoing embodiment, and performs speech control on a home appliance.
The embodiment of the present application further provides a home appliance device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the voice control method of the foregoing embodiment, and performs voice control on the home appliance device.
The embodiment of the present application further provides a computer storage medium, where a voice control application program is stored in the readable storage medium, and the voice control application program is executed by the processor to implement the steps of the voice control method for the home appliance according to any one of the above embodiments, so as to implement voice control on the home appliance.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
(1) according to the embodiment of the invention, the full duplex mode and the non-full duplex mode are automatically switched according to the type of the voice, so that the requirements of different use scenes are met, the simple switching of the modes is realized, and the voice control is smoother;
(2) in the full-duplex voice mode, the voice pickup function and the voice broadcasting function work in parallel, so that the voice control of a user on the household appliance is smoother, the voice broadcasting can be interrupted according to personal conditions to perform voice control, and the voice control operation is simpler, quicker and more flexible;
(3) through the voice processing of the embodiment of the application, the voice is collected and recognized at the same time, the voice control instruction can be recognized quickly, and the current voice broadcast is interrupted, so that the mistaken interruption of noise is avoided, the intention of a user can be known in time, and the voice recognition efficiency is improved;
(4) in the embodiment of the invention, the collected voice information is segmented, so that the segmented voice information can be subjected to voice recognition in advance, and the voice recognition efficiency is improved;
(5) through the time setting of voice control, not only can realize effectual voice control, avoided user's privacy safety again.
Drawings
Fig. 1 is a flowchart illustrating a voice control method of a home appliance according to an embodiment of the present invention;
fig. 2 is a diagram illustrating a working example of a voice pick-up function and a voice broadcast function when entering a full duplex mode according to an embodiment of the present invention;
fig. 3 is a schematic flowchart illustrating a detailed process of performing speech recognition on the collected environmental speech in the speech control method of the home appliance device according to an embodiment of the present invention;
fig. 4 is a diagram illustrating a working example of a voice pick-up function and a voice broadcast function when entering a full duplex mode according to an embodiment of the present invention;
FIG. 5 is an exemplary application of the voice control method of the present invention;
fig. 6 is an application example of the voice control method according to the embodiment of the present invention.
Detailed Description
For a better understanding of the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In the prior art, when voice control is performed on a home appliance, a user needs to speak a wakeup word meeting requirements, such as "tianmaoling", "xiaoai classmates", and the like, to wake up the home appliance, so as to perform voice control on the home appliance, such as "turn on an air conditioner", "play a song", and the like. The voice control can accurately realize the voice control, but the voice control instruction can be sent only once, if the voice control instruction needs to be sent again, for example, the temperature of an air conditioner is regulated, the household appliance needs to be awakened again, and therefore the voice control operation is complicated. Therefore, a new voice control mode appears in the prior art, that is, after being awakened, the household electrical appliance performs alternate voice pickup and voice broadcast, so that after being awakened, the household electrical appliance does not need to be awakened repeatedly, and the household electrical appliance can continue to be controlled by voice by sending a new voice control instruction after the voice broadcast is finished. Compared with the former voice control mode, the voice control mode solves the problem of multiple awakening of the household appliance, but the fluency of the voice control still needs to be improved.
The technical scheme of the invention mainly provides a voice control scheme of household electrical appliances, which comprises a full duplex mode and a non-full duplex mode, wherein in the full duplex mode, voice pickup and voice broadcast of the household electrical appliances can work in parallel, like natural conversation between people, so that the voice control of the household electrical appliances is smoother; and the user can also interrupt voice broadcast according to the condition, carries out voice control, so make the voice control to the household electrical appliances simple and convenient more swiftly and nimble. In addition, the full-duplex mode and the non-full-duplex mode are automatically switched according to the type of the sent voice, so that the requirements of different use scenes are met, the mode is simply switched, and the voice control is smoother.
As shown in fig. 1, fig. 1 is a flowchart illustrating a voice control method of a home appliance according to an embodiment of the present invention. The voice control method of the household appliance in the embodiment comprises the following steps:
step S110, receiving a voice awakening instruction, and awakening the voice device according to the voice awakening instruction;
and step S120, acquiring and recognizing voice information of the surrounding environment, and switching the voice mode according to the type of the voice instruction when the voice instruction is recognized.
The voice wake-up command in step S110 may include a default wake-up word, such as "xiaomeimei", and of course, the personalized setting of the wake-up word may also be performed through the control terminal of the home appliance. The voice device can be a functional component arranged on the household appliance; the voice control system can also be a voice device independent of the household appliance device, realize the voice pickup function and the voice broadcast function, and certainly have a network communication function, such as communicating with a household appliance device network, performing voice recognition on the collected voice information, converting the voice information into a voice instruction, and then transmitting the voice instruction to the household appliance device, so as to realize the voice control of the household appliance device.
In step S120, the voice mode includes a full duplex mode and a non-full duplex mode, and the corresponding voice mode is entered according to different voice commands. The full-duplex mode is set according to the characteristics of continuous conversation between people, and the voice device can simultaneously pick up voice and broadcast voice, so that in the full-duplex mode, a user only needs to wake up once, namely, voice instructions can be continuously sent out, and meanwhile, voice broadcasting and instruction execution results are fed back. For example, the voice device comprises two functional modules, namely a voice pickup module and a voice broadcast module, and the two functional modules operate independently and do not interfere with each other. Through voice pickup module and voice broadcast module make speech device realize gathering the pronunciation in the surrounding environment simultaneously, report the voice content that needs to be reported simultaneously.
As shown in fig. 2, fig. 2 is a diagram illustrating an operation example of the voice pickup function and the voice broadcast function when entering the full duplex mode according to the embodiment of the present invention. The voice pickup module acquires and recognizes a voice awakening instruction, and then determines whether to enter a full-duplex mode, and determines to enter the full-duplex mode when the condition for entering the full-duplex mode is met, wherein in the full-duplex mode, the voice pickup function and the voice broadcast function are both in working states. In fig. 2, when the voice pickup module collects and recognizes the voice control instruction 1, the household electrical appliance is controlled to execute the voice control instruction 1, and then the voice broadcast module broadcasts the execution result or the execution state by voice. When voice broadcast module carries out voice broadcast, the voice pick up the voice message that the module can gather all ring edge borders, and the function is picked up to pronunciation promptly and the voice broadcast function does not conflict, and both can move simultaneously.
The non-full-duplex mode includes, for example, a single-round interaction mode, a multi-round interaction mode, and the like, wherein in the non-full-duplex mode, the voice pickup module and the voice broadcast module both run alternately, that is, after the voice pickup module collects and recognizes a voice control instruction, the recognition result needs to be fed back in time, that is, the recognition result is fed back through voice broadcast; the main difference between the voice broadcasting module and the voice picking module is that the single-round interaction mode needs to be awakened before each voice control instruction is sent, and the multi-round interaction mode can send a plurality of voice control instructions after being awakened once, but the voice broadcasting module needs to stop broadcasting, and the voice picking module works.
In the embodiment of the invention, the full duplex mode and the non-full duplex mode are automatically switched according to the type of the voice, so that the requirements of different use scenes are met, the voice mode is simply switched, and the voice control is smoother. In addition, through the full duplex mode, the voice picking function and the voice broadcasting function work in parallel, so that the voice control of the user on the household appliance is smoother.
Further, as shown in fig. 3, fig. 3 is a schematic view of a detailed flow of performing voice recognition on the collected environmental voice in the voice control method of the home appliance device in an embodiment of the present invention. The determination of the type of the voice command in step S120 of the above embodiment may include the following steps:
step S121, picking up surrounding environment voice according to the current voice mode, and processing the picked-up environment voice to obtain voice characteristic information;
and step S122, matching the obtained voice characteristic information with the voice characteristic information corresponding to the type of the voice command, and judging the type of the voice command of the environmental voice according to the matching result.
Specifically, in the speech apparatus, the speech pickup module picks up a speech signal of a surrounding environment, and performs speech recognition on the picked-up speech signal. The voice pickup module includes, for example, a microphone and related components for voice recognition. The microphone can be one, two or more, voice information can be collected from multiple directions by arranging two or more microphones, and a processing algorithm for eliminating noise by difference is adopted, so that the quality of voice collection is improved, and the voice recognition rate is improved.
In an embodiment, the voice pickup module performs acquisition and recognition on the voice signal of the surrounding environment, for example, the voice pickup module adopts at least two running processes, one process is used for acquiring the voice signal of the surrounding environment, and the other process is used for performing voice recognition on the acquired voice signal. Therefore, the voice pickup module can quickly recognize and timely acquire the intention of the user. In another embodiment, the voice pickup module can be communicated with the cloud server, the voice pickup module collects voice signals of the surrounding environment and sends the collected voice signals to the cloud server, and the cloud server performs voice recognition on the received voice signals.
After the voice information of the surrounding environment is collected by the voice pickup module, the collected environment voice can be subjected to noise reduction processing, then the collected environment voice is subjected to semantic recognition processing, and voice characteristic information is extracted. In an embodiment, a database of voice features may be preset, and the feature words recognized by semantics are compared with the preset database and screened to obtain final voice feature information.
In an embodiment of the present invention, the voice command in the full duplex mode (full duplex command) includes a command word (voice feature information) of a control type, and the voice command is fed back according to an execution result of the voice command without performing an instant feedback according to an input voice command word. The instruction word has a corresponding grammatical structure, for example, "close the device", which is specifically as follows:
the voice command in the non-full-duplex mode (non-full-duplex command) includes a command word (voice feature information) of a natural conversation type, and a recognition result needs to be fed back in real time according to the input voice command, for example, if the recognition is possible, a voice response is given back, and if the recognition is not possible, the voice feedback cannot be recognized. The instruction word is not like a voice instruction in a full duplex mode, has a corresponding grammar structure, and can be more random and flexible. Specific examples are as follows:
recognizing the voice characteristic information obtained in the step S121 according to the voice characteristic information corresponding to the full-duplex instruction and the non-full-duplex instruction, and entering a full-duplex mode when the picked environmental voice is recognized as the full-duplex instruction; and when the picked-up environmental voice is recognized as a non-full-duplex instruction, entering a non-full-duplex mode.
In another embodiment, the full-duplex instruction and the non-full-duplex instruction can be judged according to the historical voice instruction. The historical voice command comprises a default voice control command, a voice control command recognized through machine learning during use, a voice control command manually added by a user, an updated voice control command and the like. Each historical voice command comprises voice characteristic information corresponding to the full-duplex command and the non-full-duplex command. The related voice control instructions in the full-duplex mode and the non-full-duplex mode can be obtained according to the historical voice instruction, so that whether the voice characteristic information is the voice control instruction in the full-duplex mode or not can be judged. Through the judgment of the historical voice command, the judgment of the full-duplex command and the non-full-duplex command can be more accurate.
In the above embodiment, the voice mode is switched according to the type of the voice instruction, for example, after the voice device is awakened, if the currently recognized voice instruction is a full duplex instruction, the voice device enters the full duplex mode, in the full duplex mode, the voice pickup module of the voice device and the voice broadcast module work in parallel, the voice pickup module performs recognition while picking up, and when the full duplex instruction is recognized, the full duplex instruction is executed, and the instruction result is subjected to voice broadcast. And when the non-full-duplex instruction is identified, exiting the full-duplex mode, entering the non-full-duplex mode, controlling the household appliance to execute the identified non-full-duplex instruction, determining whether to exit the awakening state according to the specific non-full-duplex mode, exiting the awakening state if the single-round interaction mode is adopted, and not exiting the awakening state if the multi-round interaction mode is adopted.
For another example, after the voice device is woken up, if the currently recognized voice command is a non-full duplex command, the voice device enters a non-full duplex mode, and in the non-full duplex mode, the home appliance is controlled to execute the recognized non-full duplex command, and whether to exit from the woken-up state is determined according to the specific non-full duplex mode, and if a single-round interaction mode is adopted, the woken-up state is exited, and if a multi-round interaction mode is adopted, the woken-up state is not exited. And when the full-duplex instruction is recognized in the multi-round interaction mode, the voice device exits the non-full-duplex mode and enters the full-duplex mode.
Further, a plurality of voice dialog scenarios, such as "air conditioning control", "sleep control", and the like, may be included in the full-duplex command. Taking a voice conversation scene as an example of "air conditioning control", the related voice instructions in the scene include, for example, "temperature is set to 26 ℃", "wind speed is set to middle gear", "wind direction is set to sweep up and down", "humidity is set to 60%", "cooling mode is turned on", and the like. If the obtained voice feature information is "middle-gear wind", "wind speed middle gear", "wind speed adjustment to middle gear", etc., it is determined that the voice feature information is a voice control instruction in the dialog scene, that is, "wind speed is set to middle gear". If the obtained voice characteristic information is 'wind sweeping up and down', 'wind sweeping' and the like, the voice characteristic information is judged to be a voice control instruction under the conversation scene, namely 'the wind direction is set to be wind sweeping up and down'. When voice recognition is carried out, instruction recognition can be carried out according to historical voice instructions in the current scene, and therefore recognition can be carried out more quickly. And if the voice instruction cannot be recognized in the current scene, performing instruction recognition according to historical voice instructions in other scenes until the voice instruction cannot be recognized, and determining that the acquired voice information is noise.
Furthermore, after the voice pickup module collects surrounding environment voice, the voice pickup module also carries out segmentation processing on the collected environment voice, and carries out voice recognition on the segmented environment voice. Through carrying out segmentation processing on the collected voice information, voice recognition can be carried out on segmented voice information in advance, and therefore voice recognition efficiency is improved.
Specifically, in an embodiment, the segmentation processing may be performed according to the volume of the voice information, and when performing voice acquisition, the acquired voice information is split into a plurality of voice segments. For example, a volume threshold (e.g. 3000) is set, and the voice information below the volume threshold is determined as unvoiced, so that according to the volume threshold, when the volume of the collected voice information is below the volume threshold, the voice information is segmented, and the segmented voice information is subjected to voice recognition. In another embodiment, the voice information may be segmented according to a pause time between voice information, and when the voice is collected, the collected voice information is split into a plurality of voice segments. For example, a time threshold (0.5 second) is set, and the voice information with the pause time higher than the time threshold is judged as not speaking, so that according to the time threshold, if the pause time between the collected voice information is higher than the time threshold, the voice information is segmented, and the segmented voice information is subjected to voice recognition.
Furthermore, when speech recognition is performed on the speech information after the segmentation processing, the speech control instruction is also determined by combining the recognition results of the speech information of the preceding and following segments. Because the voice information is subjected to segmentation processing, corresponding voice control instructions can be accurately analyzed only by combining the voice information of a plurality of continuous sections before and after the voice information is subjected to segmentation processing, for example, a user says that the temperature is good cold.
Further, the entry into the full-duplex mode may be performed in other manners besides the manner of voice command through full duplex: and controlling to enter a full duplex mode through a third-party control device provided with the relevant plug-in. Namely, when receiving an instruction of entering the full duplex mode sent by the mobile terminal, determining to enter the full duplex mode. The mobile terminal can be provided with a plug-in/application program for controlling the voice device, and the plug-in can be used for realizing configuration management of the voice device and starting functions of the voice device.
Further, the exit from the full-duplex mode may be performed by other means than the non-full-duplex command: in one embodiment, the full duplex mode is exited by means of a voice command to exit full duplex, such as "close full duplex mode", "exit full duplex mode", and the like; in another embodiment, after entering the full duplex mode, if the voice control command is not recognized within a preset time, the full duplex mode is exited, and the wakeup state is exited.
After entering the full-duplex mode or the non-full-duplex mode, although the voice command can be collected, the non-voice command issued in the surrounding environment can also be collected by the voice device, especially the full-duplex mode, the voice pickup device is in a continuous voice pickup state, and the user often does not want the voice information of the non-voice command issued by the user to be collected for the safety of personal privacy, so in this embodiment, a preset time is set, for example, 30 seconds, and within the preset time, if the voice control command is not recognized, the current voice mode is exited, and the awake state is exited.
In the embodiment of the invention, through the time setting of the voice mode, not only can the effective voice control be realized, but also the privacy safety of a user is avoided.
Further, when the step S120 enters the full duplex mode, the method further includes: and if the picked voice information is identified as a voice command, stopping the current voice broadcast and controlling the household appliance to execute the voice control command.
The two functional modules of the voice pickup module and the voice broadcast module of the voice device are also controlled by the processor of the voice device, and the processor can send out a control instruction at any time to control the voice pickup module and the voice broadcast module to stop working. For example, when the voice broadcasting module broadcasts voice, the processor can control the voice broadcasting module to stop broadcasting according to the collected content of the voice pickup module, and the processor can select to listen to the speech of the other party according to the speech content of the other party or interrupt the speech of the other party according to the speech content of the other party when people and people communicate.
Specifically, since the voice signal of the surrounding environment is collected and recognized, the voice intention of the user can be predicted before the complete voice signal is not collected, so as to determine whether the voice signal is a voice control instruction, and if so, the voice broadcasting is stopped and the household appliance is controlled to execute the voice control instruction. Because voice broadcast is stopped, the voice pickup module can more accurately pick up the voice information sent by the user, and therefore the household appliance can be controlled to execute the voice control instruction after the voice control instruction is confirmed again after the complete voice signal is collected.
In the above embodiment, if it is recognized that the environmental voice is a non-voice command, that is, neither a full duplex command nor a non-full duplex command, that is, it is determined that the environmental voice is noise, the voice device still maintains the current voice mode, and if the current voice broadcast module is in the voice broadcast state, the voice broadcast is continued, so that the mistaken interruption of the noise is avoided.
As shown in fig. 4, fig. 4 is a diagram illustrating an operation example of the voice pickup function and the voice broadcast function when the full duplex mode is entered in the embodiment of the present invention. In this full duplex mode, the voice pick-up function and the voice broadcast function are both in an operating state. In fig. 4, when voice control instruction 2 is collected and recognized by the voice pickup module, the household electrical appliance is controlled to execute the voice control instruction 2, and then the voice broadcast module broadcasts the execution result or the execution state by voice. When the voice broadcasting module carries out voice broadcasting, when the voice pickup module collects and recognizes the voice control command 3, the voice broadcasting module is controlled to stop broadcasting. And in fig. 2, when the voice broadcasting module carries out voice broadcasting, and the voice pickup module collects and recognizes that the voice control command is not (namely, noise), the voice broadcasting module continues to broadcast.
Through the speech recognition processing in this embodiment, the speech control instruction of full duplex mode can be discerned fast to interrupt current voice broadcast, not only promoted speech recognition efficiency, make speech control more smooth and easy, but also avoided the mistake of noise to interrupt.
Further, the voice broadcast module of the above embodiment analyzes the voice broadcast content to be broadcast when receiving the voice content to be broadcast, and selects the corresponding voice broadcast mode according to the analysis result to perform voice broadcast.
In an embodiment, the voice broadcast module analyzes the voice broadcast content to be played, for example, performs word segmentation and sentence segmentation on the voice broadcast content, determines the broadcast key information, and controls the volume, the speech speed and the pause time between words during voice broadcast, so that the voice broadcast effect is better, and the use experience is improved.
Further, the voice broadcast module of the above embodiment can also broadcast the voice according to the voice mode suitable for the user according to the broadcast control when receiving the voice content to be broadcast. For example, after the voice pickup module collects the voice information of the surrounding environment, voice recognition is performed on the voice information to recognize the user type of the current user, such as the old, children, men and women, so that the corresponding voice mode can be selected for voice broadcasting according to the recognized user type, and the use experience is further improved.
The voice control process of the embodiment of the present invention will be exemplified by voice control of the air conditioner.
As shown in fig. 5, fig. 5 is an application example of the voice control method according to the embodiment of the present invention. The user sends out pronunciation "beautiful and beautiful", and voice device gathers and discerns this environment pronunciation and be awaken up the instruction, then carries out voice feedback "I is at woollen" through voice broadcast. For example, other feedback voices, "please indicate" and the like may be set. The user sends out voice again to open natural conversation, and the voice device collects and recognizes the environment voice as a full duplex instruction, and then the voice device enters a full duplex mode, and carries out voice feedback through voice broadcast, and the user can talk freely at present. Under this full duplex mode, the user need not repeat again and awaken up, and speech pickup function and the semantic broadcast function of speech device start and parallel operation "open the air conditioner" when the user sends pronunciation, "open the air conditioner" this moment speech device gathers and discerns this environment pronunciation and be full duplex instruction, then control the air conditioner and open to carry out voice feedback "the air conditioner has started through voice broadcast," the refrigeration mode, 26 ℃, natural wind ". When this voice broadcast, the user can send out voice command again, for example "the temperature is transferred to 24 ℃, strong wind", and this environmental voice of this moment speech device collection and discernment is full duplex instruction, continues to keep full duplex mode, controls air conditioner regulation target temperature and wind speed promptly, and carries out voice feedback "the temperature has been transferred to 24 ℃, and the wind speed has been transferred to strong wind" through voice broadcast. At the moment, if a user sends a voice instruction of playing a relaxed song, and the voice device collects and recognizes that the environment voice is a non-full-duplex instruction, the user exits from the full-duplex mode, enters the non-full-duplex mode, feeds back a recognition result through voice broadcasting, the recognition result is good and is played immediately for the host, and then the voice device is controlled to play the selected song. If the non-full duplex mode adopts a single-round interactive mode, the non-full duplex mode exits the awakening state, and if voice control needs to be carried out again, the non-full duplex mode needs to be awakened again; if the non-full-duplex mode adopts a multi-round interactive mode, the voice control is carried out in a multi-round interactive mode without exiting the awakening state.
As shown in fig. 6, fig. 6 is an application example of the voice control method according to the embodiment of the present invention. The user sends out pronunciation "beautiful and beautiful", and voice device gathers and discerns this environment pronunciation and be awaken up the instruction, then carries out voice feedback "I is at woollen" through voice broadcast. For example, other feedback voices, "please indicate" and the like may be set. When a user sends voice to turn on the air conditioner, the voice device collects and recognizes that the environmental voice is a full-duplex instruction, the air conditioner enters a full-duplex mode, the air conditioner is controlled to be turned on, and then voice feedback is carried out through voice broadcasting, namely the air conditioner is turned on, the refrigeration mode is at 26 ℃ and natural wind is generated. When the voice broadcasting is performed, the user can send out the voice command again, if the user does not send out any voice command within the preset time (for example, 30 seconds), and the voice device does not collect the voice command at this time, the voice broadcasting is used for performing voice feedback, namely quitting and cheering first and remembering to wake up me later, and then quitting the current voice mode and quitting the wake-up state.
The home appliance and the voice device may each include a processor, a memory, and a communication module. Moreover, the memory may be used as a computer storage medium, and the memory may include an operating system and a voice control program of the home appliance. The voice control program is called by a processor of the home appliance to execute the steps of the voice control method of the home appliance in the above embodiment. Or the voice control program is called by a processor of the voice device to execute the steps of the voice control method of the household appliance in the above embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A voice control method of household electrical appliance is characterized in that the voice control is carried out on the household electrical appliance through a voice device; the voice control method comprises the following steps:
receiving a voice awakening instruction, and awakening the voice device according to the voice awakening instruction;
collecting and recognizing voice information of surrounding environment, and switching voice modes according to the type of a voice instruction when the voice instruction is recognized; the voice modes include a full duplex mode and a non-full duplex mode.
2. The voice control method for home appliances of claim 1, wherein the collecting and recognizing voice information of the surrounding environment comprises:
picking up surrounding environmental voices according to a current voice mode, and processing the picked-up environmental voices to obtain voice characteristic information;
and matching the obtained voice characteristic information with the voice characteristic information corresponding to the type of the voice command, and judging the type of the voice command of the environmental voice according to a matching result.
3. The voice control method of a home appliance according to claim 2, further comprising, before performing voice recognition on the picked-up environmental voice:
and carrying out segmentation processing on the collected environmental voice, and carrying out voice recognition on the segmented environmental voice at the same time.
4. The voice control method of an electric home appliance according to any one of claims 1 to 3, further comprising:
if the voice command is not recognized within a preset time, exiting the current voice mode and exiting the awakening state.
5. The voice control method of an electric home appliance according to any one of claims 1 to 3, further comprising:
and under the non-full-duplex mode, controlling the household appliance to execute the recognized voice command, and determining whether to exit the awakening state according to the type of the non-full-duplex mode.
6. The voice control method of a home appliance according to claim 1, further comprising:
and when an instruction of entering the full duplex mode sent by the mobile terminal is received, entering the full duplex mode.
7. The voice control method of a home appliance according to claim 1, further comprising:
and if the picked-up environmental voice is recognized as a voice command, stopping the current voice broadcasting and controlling the household appliance to execute the voice command.
8. A speech apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for speech control of an electrical home device according to any one of claims 1 to 7, for speech control of an electrical home device.
9. An appliance device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method of voice control of an appliance device as claimed in any one of claims 1 to 7.
10. A computer storage medium having a voice control program stored thereon, the voice control program being executed by a processor to implement the voice control method of the home appliance according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011645138.9A CN112820290A (en) | 2020-12-31 | 2020-12-31 | Household appliance and voice control method, voice device and computer storage medium thereof |
| PCT/CN2021/090041 WO2022141990A1 (en) | 2020-12-31 | 2021-04-26 | Household appliance and voice control method therefor, voice device, and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011645138.9A CN112820290A (en) | 2020-12-31 | 2020-12-31 | Household appliance and voice control method, voice device and computer storage medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112820290A true CN112820290A (en) | 2021-05-18 |
Family
ID=75856699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011645138.9A Pending CN112820290A (en) | 2020-12-31 | 2020-12-31 | Household appliance and voice control method, voice device and computer storage medium thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112820290A (en) |
| WO (1) | WO2022141990A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113539263A (en) * | 2021-07-09 | 2021-10-22 | 广东金鸿星智能科技有限公司 | Voice control method and system for electric door |
| CN113707143A (en) * | 2021-08-20 | 2021-11-26 | 珠海格力电器股份有限公司 | Voice processing method, device, electronic equipment and storage medium |
| CN114400001A (en) * | 2021-12-20 | 2022-04-26 | 上海华兴数字科技有限公司 | Voice interaction method and system for operation machine and operation machine |
| CN115631752A (en) * | 2022-12-19 | 2023-01-20 | 深圳慢云智能科技有限公司 | Intelligent equipment AI voice control method and system supporting machine learning |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679472A (en) * | 2015-02-13 | 2015-06-03 | 百度在线网络技术（北京）有限公司 | Man-machine voice interactive method and device |
| US10778826B1 (en) * | 2015-05-18 | 2020-09-15 | Amazon Technologies, Inc. | System to facilitate communication |
| CN107424607B (en) * | 2017-07-04 | 2023-06-06 | 珠海格力电器股份有限公司 | Voice control mode switching method and device and equipment with device |
| CN109994108B (en) * | 2017-12-29 | 2023-08-29 | 微软技术许可有限责任公司 | Full duplex communication techniques for conversational conversations between chat robots and people |
| US11150866B2 (en) * | 2018-11-13 | 2021-10-19 | Synervoz Communications Inc. | Systems and methods for contextual audio detection and communication mode transactions |
| CN109712621B (en) * | 2018-12-27 | 2021-03-16 | 维沃移动通信有限公司 | Voice interaction control method and terminal |
| CN109657091B (en) * | 2019-01-02 | 2021-06-22 | 百度在线网络技术（北京）有限公司 | State presentation method, device and equipment of voice interaction equipment and storage medium |
| CN111508474B (en) * | 2019-08-08 | 2021-04-06 | 马上消费金融股份有限公司 | Voice interruption method, electronic equipment and storage device |
| CN110557451B (en) * | 2019-08-30 | 2021-02-05 | 北京百度网讯科技有限公司 | Dialogue interaction processing method and device, electronic equipment and storage medium |
| CN110618613A (en) * | 2019-09-03 | 2019-12-27 | 珠海格力电器股份有限公司 | Linkage control method and device for intelligent equipment |
| CN112735398B (en) * | 2019-10-28 | 2022-09-06 | 思必驰科技股份有限公司 | Man-machine conversation mode switching method and system |
| CN112002315B (en) * | 2020-07-28 | 2023-12-29 | 珠海格力节能环保制冷技术研究中心有限公司 | Voice control method and device, electrical equipment, storage medium and processor |
-
2020
- 2020-12-31 CN CN202011645138.9A patent/CN112820290A/en active Pending
-
2021
- 2021-04-26 WO PCT/CN2021/090041 patent/WO2022141990A1/en unknown
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113539263A (en) * | 2021-07-09 | 2021-10-22 | 广东金鸿星智能科技有限公司 | Voice control method and system for electric door |
| CN113539263B (en) * | 2021-07-09 | 2023-11-14 | 广东金鸿星智能科技有限公司 | Voice control method and system for electric door |
| CN113707143A (en) * | 2021-08-20 | 2021-11-26 | 珠海格力电器股份有限公司 | Voice processing method, device, electronic equipment and storage medium |
| CN114400001A (en) * | 2021-12-20 | 2022-04-26 | 上海华兴数字科技有限公司 | Voice interaction method and system for operation machine and operation machine |
| CN115631752A (en) * | 2022-12-19 | 2023-01-20 | 深圳慢云智能科技有限公司 | Intelligent equipment AI voice control method and system supporting machine learning |
| CN115631752B (en) * | 2022-12-19 | 2023-02-28 | 深圳慢云智能科技有限公司 | Intelligent equipment AI voice control method and system supporting machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022141990A1 (en) | 2022-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112820290A (en) | Household appliance and voice control method, voice device and computer storage medium thereof | |
| CN110211580B (en) | Multi-intelligent-device response method, device, system and storage medium | |
| CN107424607A (en) | Voice command mode switching method, device and the equipment with the device | |
| CN109166575A (en) | Exchange method, device, smart machine and the storage medium of smart machine | |
| CN110751948A (en) | Voice recognition method, device, storage medium and voice equipment | |
| CN109473095A (en) | A kind of intelligent home control system and control method | |
| CN109377995B (en) | Method and device for controlling equipment | |
| CN110767225B (en) | Voice interaction method, device and system | |
| CN110347367A (en) | Volume adjusting method, terminal device, storage medium and electronic equipment | |
| CN113345433A (en) | Voice interaction system outside vehicle | |
| CN108932947B (en) | Voice control method and household appliance | |
| CN112002315B (en) | Voice control method and device, electrical equipment, storage medium and processor | |
| CN114172757A (en) | Server, intelligent home system and multi-device voice awakening method | |
| CN108758989A (en) | A kind of air-conditioning and its application method | |
| CN112133296B (en) | Full duplex voice control method and device, storage medium and voice equipment | |
| CN113205807B (en) | Voice equipment control method and device, storage medium and voice equipment | |
| CN110109377A (en) | The control system and method for household appliance, air conditioner | |
| CN111768604B (en) | Remote controller control method, remote controller and electrical equipment | |
| CN115567336B (en) | Wake-free voice control system and method based on smart home | |
| CN109147783A (en) | Audio recognition method, medium and system based on K song system | |
| CN108663942B (en) | Voice recognition equipment control method, voice recognition equipment and central control server | |
| CN112992137B (en) | Voice interaction method and device, storage medium and electronic device | |
| CN110534124A (en) | A kind of intelligent speech interactive system and method for WebRTC noise suppression algorithm | |
| US11917386B2 (en) | Estimating user location in a system including smart audio devices | |
| RU2818982C2 (en) | Acoustic echo cancellation control for distributed audio devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |