CN107704275B - Intelligent device awakening method and device, server and intelligent device - Google Patents

Intelligent device awakening method and device, server and intelligent device Download PDF

Info

Publication number
CN107704275B
CN107704275B CN201710786739.3A CN201710786739A CN107704275B CN 107704275 B CN107704275 B CN 107704275B CN 201710786739 A CN201710786739 A CN 201710786739A CN 107704275 B CN107704275 B CN 107704275B
Authority
CN
China
Prior art keywords
wake
awakening
word
intelligent
voice signal
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.)
Active
Application number
CN201710786739.3A
Other languages
Chinese (zh)
Other versions
CN107704275A (en
Inventor
谢波
孙杨
谢延
钱胜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201710786739.3A priority Critical patent/CN107704275B/en
Publication of CN107704275A publication Critical patent/CN107704275A/en
Application granted granted Critical
Publication of CN107704275B publication Critical patent/CN107704275B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/4401—Bootstrapping
    • G06F9/4418—Suspend and resume; Hibernate and awake
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • 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
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • 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
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • 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)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Theoretical Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Security & Cryptography (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The invention provides an intelligent device awakening method, an intelligent device awakening device, a server and an intelligent device, wherein the method comprises the following steps: acquiring a voice signal sent by intelligent equipment; recognizing the voice signal and determining a recognition result corresponding to the voice signal; and issuing a wake-up instruction to the intelligent equipment when the matching degree of any wake-up word model corresponding to the intelligent equipment in the identification result is determined to be greater than a threshold value. Therefore, the server is used for identifying the voice signals and controlling the intelligent device to wake up, so that the consumption of hardware performance in the wake-up process is reduced, the user can wake up the intelligent device by using the self-defined wake-up words, the wake-up words are enriched, the flexibility of wake-up is improved, the individual requirements of the user can be better met, and the user experience is improved.

Description

Intelligent device awakening method and device, server and intelligent device
Technical Field
The invention relates to the technical field of intelligent equipment management, in particular to an intelligent equipment awakening method, an intelligent equipment awakening device, a server and intelligent equipment.
Background
At present, with the development of science and technology and the improvement of living standard of people, intelligent devices such as intelligent sound boxes are widely applied to life, study and work of people.
In the prior art, when the intelligent device is controlled, the intelligent device needs to be awakened by utilizing an awakening word first, and then the intelligent device is controlled by a control instruction. When the intelligent device is awakened, an offline awakening mode is usually adopted, and the intelligent device is awakened by using a preset single fixed awakening word or a plurality of fixed awakening words.
The above manner of waking up the smart device is single in wake-up word, inflexible in update, unable to meet the personalized requirements of the user, and the wake-up process may consume more hardware performance, and the user experience is poor.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, the invention provides the intelligent device awakening method, which utilizes the server to identify the voice signal and carry out awakening control on the intelligent device, so that the consumption of hardware performance in the awakening process is reduced, the user can awaken the intelligent device by utilizing the self-defined awakening word, the awakening word is enriched, the awakening flexibility is improved, the personalized requirements of the user can be better met, and the user experience is improved.
The invention also provides another intelligent device awakening method.
The invention also provides an intelligent equipment awakening device.
The invention also provides another intelligent equipment awakening device.
The invention also provides a server.
The invention further provides the intelligent equipment.
The invention also provides a computer readable storage medium.
The invention also provides another computer readable storage medium.
An embodiment of a first aspect of the present invention provides a method for waking up an intelligent device, including: acquiring a voice signal sent by intelligent equipment; recognizing the voice signal and determining a recognition result corresponding to the voice signal; and issuing a wake-up instruction to the intelligent equipment when the matching degree of any wake-up word model corresponding to the intelligent equipment in the identification result is determined to be greater than a threshold value.
The intelligent equipment awakening method comprises the steps of firstly obtaining a voice signal sent by intelligent equipment, then identifying the voice signal, determining an identification result corresponding to the voice signal, and issuing an awakening instruction to the intelligent equipment when the matching degree of the identification result and any awakening word model corresponding to the intelligent equipment is larger than a threshold value. Therefore, the server is used for identifying the voice signals and controlling the intelligent device to wake up, so that the consumption of hardware performance in the wake-up process is reduced, the user can wake up the intelligent device by using the self-defined wake-up words, the wake-up words are enriched, the flexibility of wake-up is improved, the individual requirements of the user can be better met, and the user experience is improved.
An embodiment of a second aspect of the present invention provides a method for waking up an intelligent device, including: identifying the acquired voice signal to acquire an identification result; when the matching degree of the recognition result and the preset N awakening word models is smaller than a threshold value, sending the voice signal to a server so that the server recognizes the voice signal, wherein N is a positive integer greater than or equal to 1; and if the awakening instruction returned by the server is acquired, awakening the intelligent equipment.
According to the intelligent device awakening method, after the obtained voice signal is recognized and the recognition result is obtained, if the matching degree of the recognition result and the preset N awakening word models is smaller than the threshold value, the voice signal is sent to the server so that the server can recognize the voice signal, and if the awakening instruction returned by the server is obtained, the intelligent device is awakened. Therefore, the intelligent equipment is awakened and controlled in an off-line awakening mode, the voice signals are identified by the server, the intelligent equipment is awakened and controlled, consumption of hardware performance in the awakening process is reduced, the user can awaken the intelligent equipment by utilizing the user-defined awakening words, the awakening words are enriched, awakening flexibility is improved, personalized requirements of the user can be better met, and user experience is improved.
An embodiment of a third aspect of the present invention provides an apparatus for waking up an intelligent device, including: the first acquisition module is used for acquiring a voice signal sent by the intelligent equipment; the first determining module is used for identifying the voice signal and determining an identification result corresponding to the voice signal; and the first sending module is used for issuing a wake-up instruction to the intelligent equipment when the matching degree of any wake-up word model corresponding to the intelligent equipment in the identification result is determined to be greater than a threshold value.
The intelligent equipment awakening device of the embodiment of the invention firstly obtains a voice signal sent by intelligent equipment, then identifies the voice signal, determines an identification result corresponding to the voice signal, and issues an awakening instruction to the intelligent equipment when the matching degree of the identification result and any awakening word model corresponding to the intelligent equipment is determined to be greater than a threshold value. Therefore, the server is used for identifying the voice signals and controlling the intelligent device to wake up, so that the consumption of hardware performance in the wake-up process is reduced, the user can wake up the intelligent device by using the self-defined wake-up words, the wake-up words are enriched, the flexibility of wake-up is improved, the individual requirements of the user can be better met, and the user experience is improved.
An embodiment of a fourth aspect of the present invention provides an apparatus for waking up an intelligent device, including: the second acquisition module is used for identifying the acquired voice signal and acquiring an identification result; the second sending module is used for sending the voice signal to a server when the matching degree of the recognition result and the preset N awakening word models is smaller than a threshold value, so that the server can recognize the voice signal, wherein N is a positive integer larger than or equal to 1; and the awakening module is used for awakening the intelligent equipment when the awakening instruction returned by the server is obtained.
According to the intelligent equipment awakening device provided by the embodiment of the invention, after the acquired voice signal is identified and the identification result is acquired, if the matching degree of the identification result and the preset N awakening word models is smaller than the threshold value, the voice signal is sent to the server so that the server identifies the voice signal, and if the awakening instruction returned by the server is acquired, the intelligent equipment is awakened. Therefore, the intelligent equipment is awakened and controlled in an off-line awakening mode, the voice signals are identified by the server, the intelligent equipment is awakened and controlled, consumption of hardware performance in the awakening process is reduced, the user can awaken the intelligent equipment by utilizing the user-defined awakening words, the awakening words are enriched, awakening flexibility is improved, personalized requirements of the user can be better met, and user experience is improved.
An embodiment of a fifth aspect of the present invention provides a server, including:
a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the smart device wake-up method according to the first aspect when executing the program.
An embodiment of a sixth aspect of the present invention provides an intelligent device, including:
a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the smart device wake-up method according to the second aspect when executing the program.
A seventh embodiment of the present invention proposes a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the smart device wake-up method according to the first aspect.
An eighth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the smart device wake-up method according to the second aspect.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a smart device wake-up method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a smart device wake-up method according to another embodiment of the present invention;
fig. 3 is a signaling interaction diagram of a smart device wake-up method according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a wake-up unit of a smart device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a smart device wake-up apparatus according to another embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The embodiments of the present invention provide a method for waking up an intelligent device, which aims at solving the problems that in the prior art, when the intelligent device is woken up, an offline wake-up mode is usually adopted, and the intelligent device is woken up by using a preset single fixed wake-up word or a plurality of fixed wake-up words, the wake-up mode is single in wake-up word, inflexible in update, and incapable of meeting the personalized requirements of users, and the wake-up process may consume more hardware performance and the user experience is poor.
According to the intelligent device awakening method provided by the embodiment of the invention, the intelligent device can send the acquired voice signal to the server for identification, so that the server can issue the awakening instruction to the intelligent device to awaken the intelligent device when the matching degree of the identification result and any awakening word model corresponding to the intelligent device is determined to be greater than the threshold value. Therefore, the server is used for identifying the voice signals and controlling the intelligent device to wake up, so that the consumption of hardware performance in the wake-up process is reduced, the user can wake up the intelligent device by using the self-defined wake-up words, the wake-up words are enriched, the flexibility of wake-up is improved, the individual requirements of the user can be better met, and the user experience is improved.
The following describes an intelligent device wake-up method, an apparatus, a server, and an intelligent device according to embodiments of the present invention with reference to the accompanying drawings.
First, a server side is taken as an example to describe the method for waking up the intelligent device provided by the embodiment of the present invention in detail.
Fig. 1 is a flowchart of a smart device wake-up method according to an embodiment of the present invention.
As shown in fig. 1, the smart device wake-up method includes:
step 101, acquiring a voice signal sent by the intelligent device.
The method for waking up the intelligent device provided by the embodiment of the invention can be executed by the device for waking up the intelligent device provided by the embodiment of the invention. The intelligent equipment awakening device can be configured in a server for controlling intelligent equipment such as a sound box and the like so as to awaken the intelligent equipment.
Specifically, voice input devices such as a microphone may be preset in the smart device, so that when the user wakes up the smart device through voice, the smart device may obtain a voice signal of the user through the voice input device, and then send the voice signal to the server.
And 102, identifying the voice signal and determining an identification result corresponding to the voice signal.
Specifically, the voice recognition module may be arranged in the server or in an intelligent device wake-up device configured in the server, so that after the server acquires the voice signal sent by the intelligent device, the server may perform voice recognition on the acquired voice signal by using the voice recognition module to acquire a recognition result corresponding to the voice signal.
And 103, issuing a wake-up instruction to the intelligent equipment when the matching degree of the recognition result and any wake-up word model corresponding to the intelligent equipment is determined to be greater than a threshold value.
Wherein the threshold value can be set as required. For example, the threshold may be set to a fixed value in advance, such as 80%, 90%, and so on. Or, the value of the threshold may be determined according to the matching condition between the recognition result and each wakeup word model corresponding to the smart device. For example, when it is determined that the matching degree between the recognition result and each wakeup word model corresponding to the intelligent device is high, the threshold value may be set to a high value; when it is determined that the matching degree between the recognition result and each wakeup word model corresponding to the smart device is low, the threshold value may be set to a low value, and so on.
It should be noted that the number of the wakeup word models corresponding to the smart device may be one or multiple, and is not limited herein. In addition, each wake word model corresponds to a wake word.
Specifically, the awakening word models corresponding to the awakening words of the intelligent device can be trained in advance, so that the server can identify the voice signal, determine the identification result corresponding to the voice signal, determine the feature vector corresponding to the identification result, input the feature vector into the awakening word models corresponding to the intelligent device, check and score the feature vector, and determine the matching degree between the identification result and the awakening word models of the intelligent device. If the server determines that the matching degree of the recognition result and any awakening word model of the intelligent device is greater than the threshold value, the voice signal acquired by the intelligent device includes the awakening word corresponding to the intelligent device, and an awakening instruction can be issued to the intelligent device to awaken the intelligent device.
For example, assuming that the predetermined threshold is 90%, the smart device corresponds to 3 wake word models, which are respectively the wake word model a corresponding to "jerry", the wake word model B corresponding to "day mons", and the wake word model C corresponding to "small". If the server identifies the acquired voice signal sent by the intelligent device and determines that the identification result is "day monster", the feature vector corresponding to the "day monster" may be determined and input into the wakeup word model A, B, C, respectively, to determine the matching degree between the identification result and each wakeup word model of the intelligent device. Since the matching degree of the "day demon" and the awakening word model B is greater than 90% of the threshold, the server may issue an awakening instruction to the smart device to awaken the smart device.
Further, before the matching degree of the recognition result and any awakening word model corresponding to the intelligent device is determined to be greater than a threshold value, the awakening word model corresponding to the intelligent device can be obtained. That is, before step 103, the method may further include:
and training the obtained awakening words of the intelligent equipment to generate an awakening word model corresponding to the intelligent equipment.
The awakening word can be Chinese, English or other awakening words in any form. The smart device may correspond to one or more wake words, each corresponding to a wake word model.
Specifically, the server may obtain the wake-up word of the smart device in the following various ways.
In a first mode
And analyzing the voice signal sent by the intelligent equipment, and determining the awakening words corresponding to the intelligent equipment.
Specifically, when a user wants to add a wake-up word of the intelligent device, an instruction for adding the wake-up word can be issued to the intelligent device through voice, or when the user uses the intelligent device for the first time, the intelligent device can also actively report a message for setting the wake-up word to the user, so that the user can send voice including the newly added wake-up word to the intelligent device according to the instruction of the intelligent device. After the intelligent device acquires the voice signal of the user, the voice signal can be sent to the server, so that the server can analyze the acquired voice signal and determine the awakening word corresponding to the intelligent device.
It should be noted that, in the embodiment of the present invention, the wakeup words with the same pronunciation may be regarded as the same wakeup word. For example, "SANY", "mountain", "fir" are the same wake up word.
For example, when the current wake-up word of the smart device is "small", and the user wishes to add the wake-up word "day monster", the user can speak "small" to the smart device by voice, i want to add a name ". After the intelligent device acquires the voice signal of the user, the intelligent device can return to the user 'what name you want to add', so that the user can say 'day monster' to the intelligent device according to the instruction of the intelligent device. After the intelligent device acquires the voice signal of the user including the newly added awakening word, the voice signal can be sent to the server, so that the server can analyze the acquired voice signal and determine that the awakening word is a 'day monster' or an awakening word with the same pronunciation as the 'day monster'.
Or, when the user sends an instruction of a new wake-up word to the smart device, the instruction may also include the new wake-up word, for example, "small degree, i needs to add the name" day monster' ", which is not limited herein.
It is understood that since similar situations may exist in the pronunciation of different words, such as "long" and "flashing" or "triple", the server may not be able to resolve the exact wake-up word from the voice signal after acquiring the voice signal sent by the smart device. At this time, the server may send a voice signal to the smart device to confirm to the user whether the parsed wakeup word is accurate.
For example, when the existing wake word of the smart device is "small", and the user wishes to add the wake word "jersey" of the smart device, the user may say "small" to the smart device, i.e. add the name "jersey". After the intelligent device acquires the voice signal of the user, the intelligent device can send the voice signal to the server, and therefore the server can analyze the acquired voice signal. Since "SARE" and "FLASH", "TRI", etc. are similar in their pronunciation, the wake-up words parsed by the server may be "SARE", "FLASH" or "TRI". At this time, the server may transmit a voice signal "do 'your name to be added" to the smart device, and after the smart device broadcasts a voice "do' your name to be added" to the user, if a voice signal returned by the user is acquired, the voice signal returned by the user may be transmitted to the server, so that the server determines whether the wake-up word corresponding to the smart device is "noy" or the same wake-up word as the "noy" reading, based on the voice signal returned by the user.
Mode two
And determining the awakening words corresponding to the intelligent equipment according to the text information input by the user in the awakening word setting page corresponding to the intelligent equipment.
Specifically, a wake-up word setting page corresponding to the intelligent device may be preset, and when a user needs to add a wake-up word, a wake-up word text to be added may be input in a specific position of the wake-up word page, so that the server may obtain text information input by the user in the wake-up word page, and determine the wake-up word corresponding to the intelligent device according to the text information.
It should be noted that, the above example of determining the wakeup word corresponding to the intelligent device is only an illustrative example, and is not a limitation to the technical solution of the present invention, and on the basis, a person skilled in the art may arbitrarily set a manner of determining the wakeup word corresponding to the intelligent device according to needs, and the manner is not limited here.
In addition, when the user needs to modify or delete the awakening words corresponding to the intelligent device, the voice can be sent to the intelligent device, or the operation is performed in the awakening word setting page corresponding to the intelligent device, so that the server can determine the awakening words which the user needs to modify or delete through analyzing the voice signals sent by the intelligent device, or according to text information input by the user in the awakening word setting page, so as to update the awakening words corresponding to the intelligent device.
Specifically, after the server acquires the wake-up word corresponding to the intelligent device, the acquired wake-up word of the intelligent device can be trained to generate a wake-up word model corresponding to the intelligent device.
In specific implementation, each time the server acquires a wake-up word of the intelligent device, the server can train a wake-up word model corresponding to the wake-up word based on the wake-up word and the corpus similar to the pronunciation of the wake-up word.
For example, if the wake word of the smart device acquired by the server is "long", the wake word model corresponding to "long" may be trained using the corpora such as "three", "flashing", "sendson", and the like, which are similar to the reading of "long".
It should be noted that, in the embodiment of the present invention, when the server determines that the matching degrees of all the wakeup word models corresponding to the intelligent device in the recognition result are less than the threshold, the server may further analyze the recognition result, determine the pronunciation similarity between the recognition result and the wakeup word corresponding to each wakeup word model, and if the pronunciation similarity between the recognition result and a certain wakeup word is higher, may further train the wakeup word model corresponding to the wakeup word by using the recognition result as a training corpus when the wakeup word model corresponding to the wakeup word is trained, so as to improve the performance of the wakeup word model.
Specifically, according to the method for waking up the intelligent device provided by the embodiment of the present invention, the server is used to recognize the voice signal of the user and wake up the intelligent device, so that the consumption of hardware performance in the wake up process is reduced. And because the server can obtain abundant resources, a good-performance awakening word model can be trained and generated based on the obtained awakening words and abundant linguistic data of the intelligent device, so that a user can awaken the intelligent device through the self-defined awakening words.
The method for waking up the intelligent device, provided by the embodiment of the invention, comprises the steps of firstly obtaining a voice signal sent by the intelligent device, then identifying the voice signal, determining an identification result corresponding to the voice signal, and issuing a wake-up instruction to the intelligent device when the matching degree of the identification result and any wake-up word model corresponding to the intelligent device is greater than a threshold value. Therefore, the server is used for identifying the voice signals and controlling the intelligent device to wake up, so that the consumption of hardware performance in the wake-up process is reduced, the user can wake up the intelligent device by using the self-defined wake-up words, the wake-up words are enriched, the flexibility of wake-up is improved, the individual requirements of the user can be better met, and the user experience is improved.
The following takes the intelligent device side as an example to describe in detail the method for waking up the intelligent device provided by the embodiment of the present invention.
Fig. 2 is a flowchart of a smart device wake-up method according to an embodiment of the present invention.
As shown in fig. 2, the smart device wake-up method includes:
step 201, recognizing the acquired voice signal, and acquiring a recognition result.
The method for waking up the intelligent device provided by the embodiment of the invention can be executed by the device for waking up the intelligent device provided by the embodiment of the invention. The intelligent equipment awakening device can be configured in intelligent equipment such as a sound box, a mobile phone and a computer to awaken the intelligent equipment.
Specifically, voice input devices such as a microphone may be preset in the smart device, so that when the user wakes up the smart device through voice, the smart device may obtain a voice signal of the user through the voice input device.
In addition, a voice recognition module may be disposed in the smart device or a smart device wake-up apparatus configured in the smart device, so that after the smart device acquires the voice signal, the acquired voice signal may be recognized by using the voice recognition module to acquire a recognition result corresponding to the voice signal.
Step 202, when the matching degree of the recognition result and the preset N awakening word models is smaller than the threshold value, sending the voice signal to the server so that the server recognizes the voice signal, wherein N is a positive integer greater than or equal to 1.
The preset N wakeup word models may be pre-configured in the intelligent device when the intelligent device leaves a factory, obtained by respectively training the intelligent device according to the acquired N wakeup words, or obtained by respectively training the intelligent device after the server acquires the N wakeup words of the intelligent device, which is not limited herein.
The threshold value may be set as desired. For example, it may be preset to a fixed value, such as 80%, 90%, etc. Or, the value of the threshold may be determined according to the matching condition between the recognition result and the preset N wakeup word models. For example, when it is determined that the matching degrees of the recognition result and the preset N wakeup word models are all high, the threshold value may be set to a high value; when the matching degree of the recognition result and the preset N awakening word models is determined to be low, the threshold value may be set to be a low value, and the like.
It can be understood that, when the preset N wakeup word models are the wakeup word models obtained by the server training, the server may further send the wakeup word models to the intelligent device. That is, before step 202, the method may further include:
and receiving the awakening word model sent by the server.
And step 203, if the wake-up instruction returned by the server is obtained, waking up the intelligent device.
Specifically, after the intelligent device determines the recognition result of the voice signal, the feature vectors corresponding to the recognition result may be determined, and the feature vectors corresponding to the recognition result are respectively input into the preset N awakening word models to perform verification and scoring, so as to determine the matching degree between the recognition result and the N awakening word models. If the intelligent device determines that the matching degrees of the recognition result and the N awakening word models are smaller than the threshold value, it means that the obtained voice signal does not include the awakening word corresponding to the intelligent device according to the N awakening word models preset in the intelligent device. Because the intelligent device obtains less resources, the voice signal can be sent to the server so that the server can identify the voice signal. And matching the recognition result with each awakening word model corresponding to the intelligent equipment at the server, determining that the matching degree of the recognition result and any awakening word model corresponding to the intelligent equipment is greater than a threshold value, and after an awakening instruction is returned to the intelligent equipment, awakening the intelligent equipment by the intelligent equipment according to the acquired awakening instruction.
It can be understood that, after the feature vectors corresponding to the recognition result are respectively input into the preset N wake-up word models by the intelligent device for verification and scoring, and it is determined that the matching degree between the recognition result and one wake-up word model in the N wake-up word models is greater than a threshold value, it indicates that the voice signal acquired by the intelligent device includes the wake-up word corresponding to the intelligent device, so that the intelligent device can be directly woken up.
It should be noted that, after the intelligent device obtains the voice signal, the intelligent device may also send the voice signal to the server, so that the intelligent device and the server may simultaneously identify the voice signal, match the identification result with each wakeup word model corresponding to the intelligent device, and determine whether to wakeup the intelligent device according to the matching result. Or after the intelligent device acquires the voice signal, the voice signal may not be recognized, but the server recognizes the voice signal, and matches the recognition result with each awakening word model corresponding to the intelligent device, so as to determine whether to awaken the intelligent device according to the matching result.
According to the intelligent device awakening method, after the obtained voice signal is recognized and the recognition result is obtained, if the matching degree of the recognition result and the preset N awakening word models is smaller than the threshold value, the voice signal is sent to the server so that the server can recognize the voice signal, and if the awakening instruction returned by the server is obtained, the intelligent device is awakened. Therefore, the intelligent equipment is awakened and controlled in an off-line awakening mode, the voice signals are identified by the server, the intelligent equipment is awakened and controlled, consumption of hardware performance in the awakening process is reduced, the user can awaken the intelligent equipment by utilizing the user-defined awakening words, the awakening words are enriched, awakening flexibility is improved, personalized requirements of the user can be better met, and user experience is improved.
Fig. 3 is a signaling interaction diagram of a smart device wake-up method according to an embodiment of the present invention.
As shown in fig. 3, the smart device wake-up method is executed by a smart device a and a server B, and the interaction process is as follows:
step 301, a identifies the acquired voice signal to acquire an identification result.
Step 302, when the matching degree of the recognition result and the preset N awakening word models is smaller than the threshold value, the A sends the voice signal to the B.
Wherein N is a positive integer greater than or equal to 1.
And step 303, B, identifying the voice signal and determining an identification result corresponding to the voice signal.
And step 304, B sends a wake-up instruction to A when the matching degree of the recognition result and any wake-up word model corresponding to A is determined to be larger than a threshold value.
And 305, after the A acquires the awakening instruction returned by the B, awakening the A.
Specifically, after the intelligent device identifies the acquired voice signal, if it is determined that the matching degrees of the identification result and the preset N awakening word models are all smaller than the threshold value, the voice signal can be sent to the server. After the server acquires the voice signal, the voice signal can be identified, an identification result corresponding to the voice signal is determined, and if the matching degree of the identification result and any awakening word model corresponding to the intelligent equipment is larger than a threshold value, an awakening instruction is sent to the intelligent equipment. And after the intelligent equipment obtains the awakening instruction, the intelligent equipment can be awakened.
It can be understood that after the intelligent device recognizes the acquired voice signal, if it is determined that the matching degree of a certain awakening word model in the recognition result and the preset N awakening word models is greater than the threshold value, the intelligent device can be directly awakened.
Through the interaction process, the intelligent device can recognize the acquired voice signal in an off-line mode, and whether the intelligent device is awakened or not is determined according to the matching degree of the recognition result and the preset awakening word model. If the intelligent device cannot be awakened in an off-line mode, the voice signal can be sent to the server, and the server identifies the voice signal and performs awakening control on the intelligent device.
The server is used for identifying the voice signals and controlling the intelligent device to wake up, so that the consumption of hardware performance in the wake-up process is reduced, the user can wake up the intelligent device by using the self-defined wake-up word, the wake-up word is enriched, the flexibility of wake-up is improved, the individual requirements of the user can be better met, and the user experience is improved.
Fig. 4 is a schematic structural diagram of a smart device wake-up apparatus according to an embodiment of the present invention.
As shown in fig. 4, the smart device wake-up apparatus includes:
a first obtaining module 41, configured to obtain a voice signal sent by an intelligent device;
the first determining module 42 is configured to identify the voice signal and determine an identification result corresponding to the voice signal;
the first sending module 43 is configured to issue a wake-up instruction to the smart device when it is determined that the matching degree of any wake-up word model corresponding to the smart device in the recognition result is greater than a threshold.
Specifically, the intelligent device wake-up apparatus provided in this embodiment may execute the intelligent device wake-up method shown in fig. 1 in the present invention. The apparatus may be configured in a server that controls a speaker or the like to wake up the smart device.
In one possible implementation form, the apparatus may further include:
and the generation module is used for training the acquired awakening words of the intelligent equipment and generating awakening word models corresponding to the intelligent equipment.
The second determining module is used for analyzing the voice signal sent by the intelligent equipment and determining a wakeup word corresponding to the intelligent equipment;
or, the method and the device are used for determining the awakening words corresponding to the intelligent device according to the text information input by the user in the awakening word setting page corresponding to the intelligent device.
It should be noted that the foregoing explanation on the embodiment of the intelligent device wake-up method shown in fig. 1 is also applicable to the intelligent device wake-up apparatus of this embodiment, and is not repeated herein.
The intelligent equipment awakening device of the embodiment of the invention firstly obtains the voice signal sent by the intelligent equipment, then identifies the voice signal, determines the identification result corresponding to the voice signal, and issues an awakening instruction to the intelligent equipment when the matching degree of the identification result and any awakening word model corresponding to the intelligent equipment is larger than a threshold value. Therefore, the server is used for identifying the voice signals and controlling the intelligent device to wake up, so that the consumption of hardware performance in the wake-up process is reduced, the user can wake up the intelligent device by using the self-defined wake-up words, the wake-up words are enriched, the flexibility of wake-up is improved, the individual requirements of the user can be better met, and the user experience is improved.
Fig. 5 is a schematic structural diagram of a smart device wake-up apparatus according to another embodiment of the present invention.
As shown in fig. 5, the smart device wake-up apparatus includes:
a second obtaining module 51, configured to identify the obtained voice signal, and obtain an identification result;
a second sending module 52, configured to send the speech signal to the server when it is determined that matching degrees between the recognition result and the preset N wakeup word models are all smaller than a threshold, so that the server recognizes the speech signal, where N is a positive integer greater than or equal to 1;
and the waking module 53 is configured to wake up the smart device when the waking instruction returned by the server is obtained.
Specifically, the intelligent device wake-up apparatus provided in this embodiment may execute the intelligent device wake-up method shown in fig. 2 in the present invention. The device can be configured in intelligent equipment such as audio amplifier, cell-phone, computer to awaken intelligent equipment.
It should be noted that the foregoing explanation on the embodiment of the intelligent device wake-up method shown in fig. 2 is also applicable to the intelligent device wake-up apparatus of this embodiment, and is not repeated herein.
According to the intelligent equipment awakening device provided by the embodiment of the invention, after the acquired voice signal is identified and the identification result is acquired, if the matching degree of the identification result and the preset N awakening word models is smaller than the threshold value, the voice signal is sent to the server so that the server identifies the voice signal, and if the awakening instruction returned by the server is acquired, the intelligent equipment is awakened. Therefore, the intelligent equipment is awakened and controlled in an off-line awakening mode, the voice signals are identified by the server, the intelligent equipment is awakened and controlled, consumption of hardware performance in the awakening process is reduced, the user can awaken the intelligent equipment by utilizing the user-defined awakening words, the awakening words are enriched, awakening flexibility is improved, personalized requirements of the user can be better met, and user experience is improved.
The invention also proposes a server comprising:
the device comprises a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor executes the program to realize the intelligent device wake-up method according to the embodiment of the first aspect.
The invention also provides an intelligent device, comprising:
the device comprises a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor executes the program to realize the intelligent device wake-up method according to the embodiment of the second aspect.
The present invention also proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the smart device wake-up method as in the foregoing first aspect embodiment.
The present invention also proposes a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the smart device wake-up method as in the embodiment of the second aspect described above.
The present invention also proposes a computer program product, in which instructions, when executed by a processor, perform the smart device wake-up method as in the foregoing first embodiment.
The present invention also proposes a computer program product, in which instructions, when executed by a processor, perform a smart device wake-up method as in the foregoing second aspect embodiment.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims (14)

1. A method for waking up an intelligent device is applied to a server and is characterized by comprising the following steps:
acquiring a voice signal sent by intelligent equipment;
recognizing the voice signal and determining a recognition result corresponding to the voice signal;
and issuing a wake-up instruction to the intelligent equipment when the matching degree of the recognition result and any wake-up word model corresponding to the intelligent equipment is determined to be greater than a threshold value so as to determine that the voice signal acquired by the intelligent equipment comprises the wake-up word corresponding to the intelligent equipment, wherein the intelligent equipment corresponds to a plurality of wake-up word models, and each wake-up word model corresponds to one wake-up word.
2. The method of claim 1, wherein before determining that the matching degree of any wakeup word model corresponding to the smart device in the recognition result is greater than a threshold, the method further comprises:
training the obtained awakening words of the intelligent equipment to generate an awakening word model corresponding to the intelligent equipment.
3. The method of claim 2, wherein prior to training the obtained wake up word for the smart device, further comprising:
analyzing the voice signal sent by the intelligent equipment, and determining a wakeup word corresponding to the intelligent equipment;
or determining the awakening word corresponding to the intelligent device according to text information input by a user in the awakening word setting page corresponding to the intelligent device.
4. A method for waking up an intelligent device is applied to the intelligent device, and is characterized by comprising the following steps:
identifying the acquired voice signal to acquire an identification result;
when the matching degree of the recognition result and preset N awakening word models is smaller than a threshold value so as to determine that the voice signal acquired by the intelligent device does not include the awakening word corresponding to the intelligent device, sending the voice signal to a server so that the server recognizes the voice signal, wherein N is a positive integer greater than or equal to 1;
and if a wake-up instruction returned by the server is acquired, waking up the intelligent device, wherein the wake-up instruction is issued to the intelligent device when the voice signal acquired by the intelligent device includes a wake-up word corresponding to the intelligent device, and each wake-up word model corresponds to a wake-up word.
5. The method of claim 4, wherein before determining that the matching degree of the recognition result and the preset wake word model is smaller than a threshold value, the method further comprises:
and receiving the awakening word model sent by the server.
6. The utility model provides a smart machine awakening device, is applied to the server, its characterized in that includes:
the first acquisition module is used for acquiring a voice signal sent by the intelligent equipment;
the first determining module is used for identifying the voice signal and determining an identification result corresponding to the voice signal;
the first sending module is used for issuing a wake-up instruction to the intelligent equipment when the matching degree of any wake-up word model corresponding to the intelligent equipment in the recognition result is larger than a threshold value and the voice signal acquired by the intelligent equipment is determined to include the wake-up word corresponding to the intelligent equipment, wherein the intelligent equipment corresponds to a plurality of wake-up word models, and each wake-up word model corresponds to one wake-up word.
7. The apparatus of claim 6, further comprising:
and the generation module is used for training the acquired awakening words of the intelligent equipment and generating awakening word models corresponding to the intelligent equipment.
8. The apparatus of claim 7, further comprising:
the second determining module is used for analyzing the voice signal sent by the intelligent equipment and determining a wakeup word corresponding to the intelligent equipment;
or, the method and the device are used for determining the awakening word corresponding to the intelligent device according to the text information input by the user in the awakening word setting page corresponding to the intelligent device.
9. The utility model provides a smart machine awakening device, is applied to smart machine which characterized in that includes:
the second acquisition module is used for identifying the acquired voice signal and acquiring an identification result;
a second sending module, configured to send the voice signal to a server to enable the server to identify the voice signal when it is determined that matching degrees of the identification result and preset N wakeup word models are all smaller than a threshold value to determine that the voice signal acquired by the intelligent device does not include a wakeup word corresponding to the intelligent device, where N is a positive integer greater than or equal to 1;
and the awakening module is used for awakening the intelligent equipment when an awakening instruction returned by the server is acquired, wherein the awakening instruction is issued to the intelligent equipment when the voice signal acquired by the intelligent equipment comprises the awakening words corresponding to the intelligent equipment, and each awakening word model corresponds to one awakening word, and the matching degree of the server determining the recognition result and any awakening word model corresponding to the intelligent terminal is greater than the threshold value.
10. The apparatus of claim 9, further comprising:
and the receiving module is used for receiving the awakening word model sent by the server.
11. A server, comprising:
memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the smart device wake-up method according to any of claims 1-3 when executing the program.
12. A smart device, comprising:
memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the smart device wake-up method according to any of claims 4-5 when executing the program.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a smart device wake-up method according to any one of claims 1-3.
14. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a smart device wake-up method according to any one of claims 4-5.
CN201710786739.3A 2017-09-04 2017-09-04 Intelligent device awakening method and device, server and intelligent device Active CN107704275B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710786739.3A CN107704275B (en) 2017-09-04 2017-09-04 Intelligent device awakening method and device, server and intelligent device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710786739.3A CN107704275B (en) 2017-09-04 2017-09-04 Intelligent device awakening method and device, server and intelligent device

Publications (2)

Publication Number Publication Date
CN107704275A CN107704275A (en) 2018-02-16
CN107704275B true CN107704275B (en) 2021-07-23

Family

ID=61171966

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710786739.3A Active CN107704275B (en) 2017-09-04 2017-09-04 Intelligent device awakening method and device, server and intelligent device

Country Status (1)

Country Link
CN (1) CN107704275B (en)

Families Citing this family (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107564517A (en) 2017-07-05 2018-01-09 百度在线网络技术（北京）有限公司 Voice awakening method, equipment and system, cloud server and computer-readable recording medium
CN108536099A (en) * 2018-02-26 2018-09-14 维沃移动通信有限公司 A kind of information processing method, device and mobile terminal
CN108494956A (en) * 2018-03-13 2018-09-04 广州势必可赢网络科技有限公司 Intelligent wearable device reminding method and intelligent wearable device
CN108597507A (en) 2018-03-14 2018-09-28 百度在线网络技术（北京）有限公司 Far field phonetic function implementation method, equipment, system and storage medium
CN108538298B (en) * 2018-04-04 2021-05-04 科大讯飞股份有限公司 Voice wake-up method and device
CN108665900B (en) * 2018-04-23 2020-03-03 百度在线网络技术（北京）有限公司 Cloud wake-up method and system, terminal and computer readable storage medium
CN108665895B (en) * 2018-05-03 2021-05-25 百度在线网络技术（北京）有限公司 Method, device and system for processing information
CN108735210A (en) * 2018-05-08 2018-11-02 宇龙计算机通信科技(深圳)有限公司 A kind of sound control method and terminal
CN108646902A (en) * 2018-05-15 2018-10-12 广州势必可赢网络科技有限公司 Control method and device for standby enabling signal
CN108737933A (en) * 2018-05-30 2018-11-02 上海与德科技有限公司 A kind of dialogue method, device and electronic equipment based on intelligent sound box
CN109166571B (en) * 2018-08-06 2020-11-24 广东美的厨房电器制造有限公司 Household appliance awakening word training method and device and household appliance
CN108962259B (en) * 2018-07-25 2021-06-15 联想(北京)有限公司 Processing method and first electronic device
CN109005482A (en) * 2018-08-14 2018-12-14 汪俊 A kind of method and device of the speaker of sound control working condition
CN109346070A (en) * 2018-09-17 2019-02-15 佛吉亚好帮手电子科技有限公司 A kind of voice based on vehicle device Android system exempts from awakening method
WO2020061787A1 (en) * 2018-09-26 2020-04-02 深圳市博电电子技术有限公司 Intelligent toilet control method and intelligent toilet
CN111105789A (en) * 2018-10-25 2020-05-05 珠海格力电器股份有限公司 Awakening word obtaining method and device
CN109471664A (en) * 2018-10-30 2019-03-15 南昌努比亚技术有限公司 Intelligent assistant's management method, terminal and computer readable storage medium
CN111261151B (en) * 2018-12-03 2022-12-27 中移（杭州）信息技术有限公司 Voice processing method and device, electronic equipment and storage medium
CN110797015B (en) * 2018-12-17 2020-09-29 北京嘀嘀无限科技发展有限公司 Voice wake-up method and device, electronic equipment and storage medium
CN109686370A (en) * 2018-12-24 2019-04-26 苏州思必驰信息科技有限公司 The method and device of fighting landlord game is carried out based on voice control
CN109871238A (en) * 2019-01-02 2019-06-11 百度在线网络技术（北京）有限公司 Voice interactive method, device and storage medium
CN111475206B (en) * 2019-01-04 2023-04-11 优奈柯恩(北京)科技有限公司 Method and apparatus for waking up wearable device
CN111508472B (en) * 2019-01-11 2023-03-03 华为技术有限公司 Language switching method, device and storage medium
CN109887505A (en) * 2019-03-11 2019-06-14 百度在线网络技术（北京）有限公司 Method and apparatus for wake-up device
CN110119083A (en) * 2019-04-17 2019-08-13 惠州市惠泽电器有限公司 The awakening method of smartwatch
CN110049395B (en) * 2019-04-25 2020-06-05 维沃移动通信有限公司 Earphone control method and earphone device
CN110211580B (en) * 2019-05-15 2021-07-16 海尔优家智能科技（北京）有限公司 Multi-intelligent-device response method, device, system and storage medium
CN110364147B (en) * 2019-08-29 2021-08-20 厦门市思芯微科技有限公司 Awakening training word acquisition system and method
CN111124507A (en) * 2019-11-18 2020-05-08 珠海格力电器股份有限公司 Voice equipment and awakening method, awakening device and storage medium thereof
CN112820283B (en) * 2019-11-18 2024-07-05 浙江未来精灵人工智能科技有限公司 Voice processing method, equipment and system
CN111292726A (en) * 2020-03-10 2020-06-16 科通工业技术(深圳)有限公司 Method and system for changing awakening words offline
CN111009246A (en) * 2020-03-10 2020-04-14 展讯通信（上海）有限公司 Intelligent sound box and awakening method thereof, gateway, server and readable storage medium
CN111724780B (en) 2020-06-12 2023-06-30 北京小米松果电子有限公司 Equipment wake-up method and device, electronic equipment and storage medium
CN112133301A (en) * 2020-08-21 2020-12-25 深圳数联天下智能科技有限公司 Voice recognition method, control device, voice recognition circuit and household equipment
CN112634897B (en) * 2020-12-31 2022-10-28 青岛海尔科技有限公司 Equipment awakening method and device, storage medium and electronic device
CN113012697A (en) * 2021-03-05 2021-06-22 北京嘀嘀无限科技发展有限公司 Information interaction method and device and electronic equipment
CN113223529A (en) * 2021-05-14 2021-08-06 成都启英泰伦科技有限公司 Multi-awakening-word anti-error identification method based on multiple single-awakening-word models
CN116030817B (en) * 2022-07-18 2023-09-19 荣耀终端有限公司 Voice wakeup method, equipment and storage medium

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9202465B2 (en) * 2011-03-25 2015-12-01 General Motors Llc Speech recognition dependent on text message content
WO2014055076A1 (en) * 2012-10-04 2014-04-10 Nuance Communications, Inc. Improved hybrid controller for asr
CN103595869A (en) * 2013-11-15 2014-02-19 华为终端有限公司 Terminal voice control method and device and terminal
CN106233804B (en) * 2014-04-24 2019-07-05 Lg电子株式会社 The method and apparatus of maximum uplink transimission power is determined in a wireless communication system
CN104036170A (en) * 2014-06-11 2014-09-10 叶晨光 Smart glasses and a control method and device of same
CN104282307A (en) * 2014-09-05 2015-01-14 中兴通讯股份有限公司 Method, device and terminal for awakening voice control system
CN105654943A (en) * 2015-10-26 2016-06-08 乐视致新电子科技（天津）有限公司 Voice wakeup method, apparatus and system thereof
CN105632486B (en) * 2015-12-23 2019-12-17 北京奇虎科技有限公司 Voice awakening method and device of intelligent hardware
CN105654949B (en) * 2016-01-07 2019-05-07 北京云知声信息技术有限公司 A kind of voice awakening method and device
CN105702253A (en) * 2016-01-07 2016-06-22 北京云知声信息技术有限公司 Voice awakening method and device
CN106098059B (en) * 2016-06-23 2019-06-18 上海交通大学 Customizable voice awakening method and system
CN106653031A (en) * 2016-10-17 2017-05-10 海信集团有限公司 Voice wake-up method and voice interaction device

Also Published As

Publication number Publication date
CN107704275A (en) 2018-02-16

Similar Documents

Publication Publication Date Title
CN107704275B (en) Intelligent device awakening method and device, server and intelligent device
CN108520743B (en) Voice control method of intelligent device, intelligent device and computer readable medium
CN106782554B (en) Voice awakening method and device based on artificial intelligence
CN111161714B (en) Voice information processing method, electronic equipment and storage medium
CN111261151B (en) Voice processing method and device, electronic equipment and storage medium
CN110111789B (en) Voice interaction method and device, computing equipment and computer readable medium
CN107622770A (en) voice awakening method and device
CN107134279A (en) A kind of voice awakening method, device, terminal and storage medium
CN108469966A (en) Voice broadcast control method and device, intelligent device and medium
CN112735418B (en) Voice interaction processing method, device, terminal and storage medium
CN112634897B (en) Equipment awakening method and device, storage medium and electronic device
CN108055617B (en) Microphone awakening method and device, terminal equipment and storage medium
CN103680497A (en) Voice recognition system and voice recognition method based on video
CN110634468B (en) Voice wake-up method, device, equipment and computer readable storage medium
CN109166571B (en) Household appliance awakening word training method and device and household appliance
CN110866090A (en) Method, apparatus, electronic device and computer storage medium for voice interaction
CN110706707B (en) Method, apparatus, device and computer-readable storage medium for voice interaction
CN113470634A (en) Control method of voice interaction equipment, server and voice interaction equipment
CN110473542B (en) Awakening method and device for voice instruction execution function and electronic equipment
CN111243604B (en) Training method for speaker recognition neural network model supporting multiple awakening words, speaker recognition method and system
CN108665900B (en) Cloud wake-up method and system, terminal and computer readable storage medium
CN108986813A (en) Wake up update method, device and the electronic equipment of word
CN114242065A (en) Voice wake-up method and device and training method and device of voice wake-up module
CN108806678A (en) The voice awakening method and device of equipment
CN112306560B (en) Method and apparatus for waking up an electronic device

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
GR01 Patent grant
GR01 Patent grant