CN111161714A - Voice information processing method, electronic equipment and storage medium - Google Patents
Voice information processing method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111161714A CN111161714A CN201911353919.8A CN201911353919A CN111161714A CN 111161714 A CN111161714 A CN 111161714A CN 201911353919 A CN201911353919 A CN 201911353919A CN 111161714 A CN111161714 A CN 111161714A
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- awakening
- target
- matching
- 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.)
- Granted
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 20
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims description 38
- 230000002618 waking effect Effects 0.000 claims description 10
- 101000588924 Anthopleura elegantissima Delta-actitoxin-Ael1a Proteins 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 241001071864 Lethrinus laticaudis Species 0.000 description 4
- 241000746998 Tragus Species 0.000 description 3
- 230000004913 activation Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000011218 segmentation 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
- G10L15/08—Speech classification or search
-
- 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
- G10L15/32—Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephone Function (AREA)
- Circuits Of Receivers In General (AREA)
Abstract
The embodiment of the application discloses a voice information processing method, which comprises the following steps: receiving voice data information; matching processing is carried out on the basis of the voice data information and a first preset model base; the first preset model library comprises at least one piece of matching standard information; if the matching processing is information matching, matching processing is carried out on the basis of the voice data information and a second preset model base, and a voice assistant application program to be awakened is determined; the first preset model library is different from the second preset model library, and the second preset model library comprises at least one matching standard information; and awakening the voice assistant application to be awakened. The embodiment of the application also provides the electronic equipment and the storage medium.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method for processing voice information, an electronic device, and a storage medium.
Background
Along with the rapid development of scientific technology, electronic equipment is more and more widely applied, and has great influence on the work, life, study and entertainment of people. In order to increase the intelligence of the electronic device, a voice assistant is often provided in the electronic device.
However, when a user wakes up one of a plurality of voice assistant applications installed in an electronic device by voice at present, the wake-up rate is low and false wake-up is likely to occur, which results in a low intelligent degree of the electronic device.
Content of application
In order to solve the above technical problem, embodiments of the present application are expected to provide a voice information processing method, an electronic device, and a storage medium, so as to solve the problems that when a voice assistant application installed in the electronic device is woken up at present, a wake-up rate is low and false wake-up is likely to occur, improve the wake-up rate, and reduce the probability of false wake-up, thereby improving the intelligence degree of the electronic device.
The technical scheme of the application is realized as follows:
in a first aspect, a method for processing voice information, the method comprising:
receiving voice data information;
matching processing is carried out on the basis of the voice data information and a first preset model base; the first preset model library comprises at least one piece of matching standard information;
if the matching processing is information matching, matching processing is carried out on the basis of the voice data information and a second preset model base, and a voice assistant application program to be awakened is determined; the first preset model library is different from the second preset model library, and the second preset model library comprises at least one matching standard information;
and awakening the voice assistant application to be awakened.
Optionally, the matching process performed on the basis of the voice data information and the first preset model library includes:
acquiring target awakening information from the voice data information;
matching the target awakening information with first reference awakening information in the first preset model base; the first reference awakening information belongs to at least one matching standard information included in the first preset model base, and the first reference awakening information is at least one piece of information which is possessed by a plurality of awakening information;
and if the target awakening information is matched with the first reference awakening information, determining information matching.
Optionally, if the matching result is information matching, performing matching processing based on the voice data information and a second preset model library to determine a to-be-awakened voice assistant application program, including:
if the matching result is information matching, matching the target awakening information with second reference awakening information in the second preset model base; the second reference awakening information belongs to at least one matching standard information included in the second preset model library;
if the target awakening information is matched with second reference awakening information in the second preset model base, determining a target voice assistant application program corresponding to the target awakening information;
determining the target voice assistant application as the voice assistant application to wake up.
Optionally, the target wake-up information is a first sound model corresponding to a target wake-up word, the first reference wake-up information is a second sound model of the corresponding wake-up word, the second reference wake-up information is a third sound model of the corresponding wake-up word, and if the target wake-up information matches the second reference wake-up information in the second preset model library, the target voice assistant application program corresponding to the target wake-up information is determined, including:
if the first sound model is matched with the second sound model, determining the target awakening word based on the first sound model;
determining the target voice assistant application based on the target wake word.
Optionally, after waking the to-be-woken voice assistant application, the method further includes:
determining a target control instruction based on the voice data information;
sending the target control instruction to a server corresponding to the awakened voice assistant application program to be awakened through the awakened voice assistant application program to be awakened;
receiving feedback information sent by the server, and playing the feedback information; and the feedback information is obtained by the server responding to the target control instruction and executing the operation corresponding to the target control instruction.
Optionally, the determining a target control instruction based on the voice data information includes:
acquiring target voice control information from the voice data information;
and converting the target voice control information between voice signals and characters to obtain the target control instruction.
Optionally, before performing matching processing on the voice data information and a first preset model library, the method further includes:
determining a first number of voice assistant applications installed in the electronic device;
obtaining a wake-up word for each of the first number of voice assistant applications;
determining a first sound model corresponding to the awakening word of each voice assistant application program to obtain a first preset model library;
determining a second sound model corresponding to the awakening word of each voice assistant application program to obtain a second preset model library; wherein the quality requirement of the first acoustic model is lower than the quality requirement of the second acoustic model.
Optionally, after determining the second sound model corresponding to the wake-up word of each voice assistant application program and obtaining the second preset model library, the method further includes:
if it is detected that the updated second number of voice assistant applications have been installed by the electronic device, determining a changed voice assistant application based on the first number of voice assistant applications and the second number of voice assistant applications;
and updating the first preset model library and the second preset model library based on the awakening words corresponding to the changed voice assistant application program.
In a second aspect, an electronic device, the electronic device comprising: microphone, low voltage digital signal processor DSP, application processor AP, wherein:
the microphone is used for collecting voice data information;
the low-voltage DSP is used for matching the voice data information with information in a first preset model base, and when the voice data information is matched with the information in the first preset model base, the AP is awakened to realize one-time awakening and the voice data information is sent to the AP, so that the power consumption of the electronic equipment is reduced;
and the AP is used for matching the voice data information with information in a second preset model base, awakening the voice assistant application program to be awakened corresponding to the voice data information to realize secondary awakening when the voice data information is matched with the information in the second preset model base, and executing relevant steps after awakening the voice assistant application program to be awakened.
In a third aspect, a storage medium has stored thereon a speech information processing program which, when executed by a processor, implements the steps of the speech information processing method according to any one of the preceding claims.
The embodiment of the application provides a voice information processing method, electronic equipment and a storage medium, wherein voice data information is received, matching processing is carried out on the basis of the voice data information and a first preset model base, if the matching processing result is information matching, matching processing is carried out on the basis of the voice data information and a second preset model base, a voice assistant application program to be awakened is determined, and the voice assistant application program to be awakened is awakened. Therefore, when the received voice data information is matched with the information in the first preset model base, the voice data information is matched with the second preset model base again to determine the voice assistant application program to be awakened and awaken, two-stage awakening is achieved, the problems that when one voice assistant application program installed in the electronic equipment is awakened at present, the awakening rate is low and mistaken awakening is easy to occur are solved, the awakening rate is improved, the mistaken awakening probability is reduced, and the intelligent degree of the electronic equipment is improved.
Drawings
Fig. 1 is a schematic flowchart of a voice information processing method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another speech information processing method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of another voice information processing method according to an embodiment of the present application;
fig. 4 is a flowchart illustrating a voice message processing method according to another embodiment of the present application;
fig. 5 is a schematic flowchart of another speech information processing method according to another embodiment of the present application;
fig. 6 is a schematic view of an application scenario of a voice information processing method according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
An embodiment of the present application provides a voice information processing method, which is applied to an electronic device and is shown in fig. 1, and the method includes the following steps:
In the embodiment of the application, the electronic device may adopt a microphone and other voice acquisition devices to acquire voice data information. The voice collecting device such as a microphone can be arranged in the electronic device, or can be in communication link with the electronic device. The corresponding voice data information may be voice information acquired by a voice acquisition device such as a microphone, or may be acquired by the device after digital preprocessing such as preliminary sampling is performed on the voice information acquired by the voice acquisition device such as the microphone.
And 102, matching the voice data information with a first preset model base.
The first preset model library comprises at least one piece of matching standard information.
In this embodiment of the present application, the first preset model library is preset, and includes at least one matching standard information having the same format as the voice data information and used for performing voice data information matching processing. The matching criterion information is a plurality of different speech model information obtained in advance. The voice model information in the first preset model library has less related sound characteristic information, and preliminary matching between the voice data information and the voice model information in the first preset model library is realized.
And 103, if the matching process is information matching, matching the voice data information with a second preset model base, and determining the voice assistant application program to be awakened.
The first preset model library is different from the second preset model library, and the second preset model library comprises at least one piece of matching standard information.
In this embodiment of the present application, if at least one matching criterion information in the first preset model library matches with the voice data information, it is determined that the matching process is an information matching. And when the matching processing is information matching, performing accurate matching processing on the voice data information and at least one piece of matching standard information in a second preset model library so as to determine the voice assistant application program to be awakened, wherein the determined information can be identification information of the voice assistant application program to be awakened.
And 104, waking up the voice assistant application program to be woken up.
In this embodiment of the present application, after determining the voice assistant application to be woken up, a control instruction for controlling the voice assistant application to be woken up to work may be generated to wake up, that is, the voice assistant application to be woken up is started up to work, for example, voice control instruction information sent by a user is received, and a corresponding operation is executed.
The embodiment of the application provides a voice information processing method, wherein voice data information is received, matching processing is carried out on the basis of the voice data information and a first preset model base, if the matching processing result is information matching, matching processing is carried out on the basis of the voice data information and a second preset model base, a voice assistant application program to be awakened is determined, and the voice assistant application program to be awakened is awakened. Therefore, when the received voice data information is matched with the information in the first preset model base, the voice data information is matched with the second preset model base again to determine the voice assistant application program to be awakened and awaken, two-stage awakening is achieved, the problems that when one voice assistant application program installed in the electronic equipment is awakened at present, the awakening rate is low and mistaken awakening is easy to occur are solved, the awakening rate is improved, the mistaken awakening probability is reduced, and the intelligent degree of the electronic equipment is improved.
Based on the foregoing embodiments, an embodiment of the present application provides a method for processing voice information, which is shown in fig. 2 and is applied to an electronic device, and the method includes the following steps:
In the embodiment of the application, the electronic device collects voice information sent by a user through a voice collection module such as a microphone arranged in the electronic device, and performs sampling processing on the collected voice information to obtain corresponding voice digitalized information, namely voice data information.
And step 202, matching the voice data information with a first preset model base.
The first preset model library comprises at least one piece of matching standard information.
In other embodiments of the present application, step 202 may be implemented by steps 202 a-202 c as follows:
In an embodiment of the present application, the target wake-up message may be a voice vocabulary for waking up the voice assistant application, for example, a certain brand of voice assistant application is developed and configured to automatically start the voice assistant application when the voice assistant application receives and recognizes that the user sends a voice "small X". The target wake-up information may be obtained by a function of voice recognition.
The first reference awakening information belongs to at least one piece of matching standard information included in a first preset model base, and the first reference awakening information is at least one piece of information which is possessed by a plurality of awakening information.
In this embodiment of the application, the first reference wake-up message may be at least one characteristic parameter that the plurality of wake-up messages all have, that is, the first reference wake-up message represents one wake-up message set, for example, the first reference wake-up message may be a pronunciation that the plurality of wake-up messages are all two words, a pronunciation of a first word in the pronunciation of the two words is the same, and a tone of a second word is the same. In other application scenarios, the first reference wake-up information may also be a reference model with a relatively high fault tolerance rate corresponding to a wake-up information, but a relatively low matching degree with the target wake-up information, i.e. for example, the matching degree between the characteristic parameter of the target wake-up information and the characteristic parameter of the first reference wake-up information may be lower than 50%.
It should be noted that, step 202 may be implemented in a Low-voltage (Low-power) Digital Signal Processor (DSP) provided in the electronic device, that is, the first preset model library is stored in a storage area of the Low-power DSP, at this time, the Low-power DSP operates, and other running programs in the electronic device do not operate, for example, are in a sleep state, so that power consumption of the electronic device may be reduced. And matching the target awakening information with the first preset model base, which can be called a primary awakening processing process.
And 203, if the matching process is information matching, performing matching process with a second preset model library based on the voice data information, and determining the voice assistant application program to be awakened.
The first preset model library is different from the second preset model library, and the second preset model library comprises at least one piece of matching standard information.
In this embodiment, the feature parameter of the at least one matching criterion information set in the second preset model library is more than the feature parameter of the at least one matching criterion information set in the first preset model library, that is, the fault tolerance of the matching criterion information in the second preset model library is low, but the matching degree between the voice data information and the matching criterion information in the second preset model library is required to be higher, that is, when the voice data information matches with the matching criterion information in the second preset model library, the feature parameter corresponding to the voice data information is required to be matched with the feature parameter of the matching criterion information in the second preset model library to be higher, for example, the matching degree is more than 90%.
In other embodiments of the present application, step 203 may be implemented by the following steps 203 a-203 c:
and 203a, if the matching result is information matching, matching the target awakening information with second reference awakening information in a second preset model base.
And the second reference awakening information belongs to at least one piece of matching standard information included in a second preset model library.
In this embodiment of the application, when the Low-power DSP successfully matches the target wake-up information with the first reference wake-up information in the first preset model library, that is, when the matching result is information matching, the Low-power DSP may send a signal to the application processor AP of the electronic device to wake up the application processor AP of the electronic device, and then send the target wake-up information to the application processor AP, so that the target application processor AP performs matching processing on the target wake-up information and the second reference wake-up information in the second preset model library stored in the application processor AP.
And 203b, if the target awakening information is matched with second reference awakening information in a second preset model base, determining a target voice assistant application program corresponding to the target awakening information.
In this embodiment of the application, the application processor AP matches, according to a certain matching rule, for example, a sound characteristic parameter of the obtained target wake-up information with a sound characteristic parameter corresponding to the second reference wake-up information, and when the matching degree exceeds 90%, it is determined that the target wake-up information matches the second reference wake-up information, so that it may be determined that the voice assistant application program corresponding to the second reference wake-up information is the target voice assistant application program. The process of matching the target wake-up information with the second preset model library may be referred to as secondary wake-up processing.
In other embodiments of the present application, the target wake-up message is a first sound model corresponding to the target wake-up word, the first reference wake-up message is a second sound model corresponding to the target wake-up word, and the second reference wake-up message is a third sound model corresponding to the target wake-up word, in this case, step 203b may be implemented by the following steps a 11-a 12:
step a11, if the first sound model is matched with the second sound model, determining the target awakening word based on the first sound model.
In this embodiment of the application, the matching between the first acoustic model and the second acoustic model may be matching between a contour of a spectrogram of the collected first acoustic distribution and a contour of a spectrogram of the second acoustic model, that is, when the contours have a certain similarity, for example, a similarity of 20% or more, it may be determined that the first acoustic model matches the second acoustic model. When the first sound model is matched with the second sound model, the first sound model is subjected to speech recognition, and a target awakening word, such as a text message, is determined.
Step a12, determining the target voice assistant application based on the target wake word.
In the embodiment of the application, the target wake-up word is used for uniquely identifying one voice assistant application program, so that the target voice assistant application program can be determined according to the target wake-up word.
And step 204, waking up the voice assistant application program to be woken up.
In this embodiment of the present application, after determining that the voice assistant application program to be woken up is to be woken up, the application processor AP determines that the user wants the voice assistant application program to be woken up to execute some corresponding voice control instructions, and therefore, sends a start instruction to the voice assistant application program to be woken up, so that the voice assistant application program to be woken up works.
In other embodiments of the present application, referring to fig. 3, after the electronic device performs step 204, it may further select to continue to perform the following steps:
In the embodiment of the application, the voice data information sent by the user comprises a target awakening word and a target control instruction. For example, the voice data information is "small X," please query weather forecast, "so that the electronic device analyzes the voice data information, and can determine that the target wake-up word is" small X, "and the corresponding target control instruction is" query weather forecast.
In other embodiments of the present application, step 205 may be implemented by steps b 11-b 12 as follows:
and b11, acquiring the target voice control information from the voice data information.
In the implementation of the present application, the received voice data information is subjected to voice recognition and segmentation, and the voice data information unrelated to the target wake-up word and the control information is deleted, for example, when the voice data information is "small X," please query the weather forecast of beijing today, "the information of" please, "you," "one" and "is deleted, and the first acoustic model" small X "and the target voice control information corresponding to the target wake-up word are obtained and can be recorded as" query the weather forecast of beijing today "or as" query, "" beijing, "" today "and" weather forecast.
And b12, converting the voice signal and the characters of the target voice control information to obtain a target control instruction.
In the embodiment of the application, the target voice control information is recognized by adopting a character recognition technology, the corresponding voice information is converted into character information, and a corresponding target control instruction, namely a target control instruction of 'inquiring Beijing weather forecast of today' is obtained.
And step 206, sending the target control instruction to a server corresponding to the awakened to-be-awakened voice assistant application program through the awakened to-be-awakened voice assistant application program.
In this embodiment of the application, the server corresponding to the voice assistant application to be wakened up after waking up may be a server to which the voice assistant application to be wakened up after waking up may be connected, that is, the voice assistant application to be wakened up after waking up may obtain the operation content corresponding to the target control instruction information from the server. For example, the electronic device sends a target control command of "inquiring weather forecast of beijing" to the corresponding server through the voice assistant application program to be woken up through the internet.
And step 207, receiving the feedback information sent by the server, and playing the feedback information.
The feedback information is obtained by the server responding to the target control instruction and executing the operation corresponding to the target control instruction.
In the embodiment of the application, the corresponding server responds to the target control instruction, obtains the weather forecast of beijing today, and feeds the weather forecast as feedback information back to the voice assistant application program to be woken up of the electronic device, and after receiving the feedback information, the voice assistant application program performs voice broadcast, for example, the broadcast is in the form of "beijing today's weather is clear, the temperature is 25 degrees, breeze" and the like.
In other embodiments of the present application, referring to fig. 4, before the electronic device performs step 202, the electronic device may further perform the following steps 208 to 211:
In the embodiment of the present application, the first number is at least one.
Step 209 is obtaining a wakeup word for each of a first number of voice assistant applications.
In the embodiment of the present application, each voice assistant application is associated with a wake word, which can uniquely identify and recognize the voice assistant application.
In this embodiment of the present application, the first acoustic model corresponding to the wake-up word of each voice assistant application program may be obtained from a server provided by a developer, that is, according to the determined first number of wake-up words, the first acoustic model corresponding to the first number of wake-up words is obtained from the server provided by the developer, so as to obtain the first preset model library. It should be noted that, because the speech matching quality requirement of the first preset model library is low, a plurality of wake-up words can share one acoustic model, that is, the accuracy of the acoustic model is relatively low. I.e. the number of first acoustic models in the first library of preset models is smaller than or equal to the first number.
And step 211, determining a second sound model corresponding to the awakening word of each voice assistant application program to obtain a second preset model library.
Wherein the quality requirement of the first acoustic model is lower than the quality requirement of the second acoustic model.
In the embodiment of the present application, the number of the second sound models in the second preset model library is preferably a first number, that is, one wakeup word corresponds to one second sound model.
In other embodiments of the present application, referring to fig. 5, after the electronic device performs step 211, the following steps 212 to 213 may be further performed:
In this embodiment, after the voice assistant applications installed in the electronic device are updated, a second number of updated voice assistant applications is determined, where the second number may be greater than the first number, may also be equal to the first number, and may also be smaller than the first number.
And step 213, updating the first preset model library and the second preset model library based on the awakening words corresponding to the changed voice assistant application program.
It should be noted that steps 212 to 213 may be performed after or before any step after step 211.
An application scenario is provided in an embodiment of the present application, as shown in fig. 6, an electronic device includes a microphone a, a low voltage DSPB, an application processor AP C, and an internet end D, where a dotted line path represents a data information transmission path for waking up an application program to be woken up, and a solid line path represents a transmission path of target voice control information, where the microphone a includes: the device comprises a voice acquisition module, an activation detection module, a forward cache module and a bottom application interface; the low-voltage DSP comprises a first preset model library and a low-voltage DSP driver; the application processor AP C comprises a second preset model library, an audio hardware abstraction layer, a recorder, a first installed voice assistant application program and a second installed voice assistant application program; the internet terminal D includes: a first server and a second server. An activation detection module in the microphone A detects whether a user voice is input in real time; if the activation detection module detects the user voice input, the voice acquisition module is started to acquire the user voice; the voice acquisition module sends the acquired voice data information to the forward cache module for cache storage; the voice data information cached and stored in the forward cache module is firstly sent to a low-voltage DSP B through a bottom application interface, and the low-voltage DSP B carries out matching processing on the received voice data information and matching standard information in a first preset model base; when the voice data information is matched with the reference matching information in the first preset model base, the voice data information is driven by the low-voltage DSP B to be sent to the application processor AP C, and the application processor AP C is activated from a dormant state to a working state; the application processor AP C performs matching processing on the received voice data information and matching standard information in the second preset model library, and determines a specific matching object, that is, determines which voice assistant application program corresponds to the voice data information, for example, when it is determined that the voice assistant application program is the first voice assistant application program, wakes up the first voice assistant application program; after the first voice assistant application program is awakened, voice data information cached in the microphone A forward cache module is sent to an audio hardware abstraction layer of an application processor AP C through a low-voltage DSP driver of a low-voltage DSP B; sending voice data information to a recorder through an audio hardware abstraction layer; sending, by the recorder, the voice data information to a first voice assistant application that is awake; and the first voice assistant application program is in communication link with the corresponding first server, acquires the content corresponding to the voice data information and broadcasts the content.
Illustratively, when a second voice assistant application program with a target wake-up word of 'piggy' is installed in an electronic device such as a mobile phone, if the voice data information collected by the voice collection module is 'piggy, please inquire the weather of Beijing today', the voice data information is sent to the forward cache module for caching; processing the acquired piglet by asking to inquire the current weather of Beijing in a forward cache module, and acquiring a corresponding target awakening word, wherein the obtained target awakening word is the piglet; sending the target awakening word 'piggy' to a low-voltage DSP B through a bottom application interface of a microphone; the low-voltage DSP B matches the target wake-up word with the acoustic model in the first preset model library to determine the first acoustic model corresponding to the piglet, where it should be noted that, because the fault tolerance rate of the acoustic model in the first preset model library is higher, when the obtained target wake-up word is, for example, "tragus a" or "minity", etc., the first acoustic model corresponding to the piglet "may also be obtained by matching, that is, the first acoustic model may be marked as { tragus, tragus a, minity }, which is the first acoustic model in the first preset model library, and of course, other manners such as a voiceprint manner may also be used for recording; as the target awakening word 'piglet' is successfully matched in the first preset model library, the target awakening word 'piglet' is driven and sent to the AP C through the low-voltage DSP; the AP C performs matching processing on the target awakening word 'piglet' and a sound model in a second preset model library, determines a second voice assistant application program matched with the target awakening word from the second preset model library, and awakens the second voice assistant application program; after waking up the second voice assistant application program, the voice data information ' piggy please inquire the current weather of Beijing ' cached in the forward cache module ' is processed to obtain a target control instruction ' inquire the current weather of Beijing '; sending a target control instruction 'inquiring the current weather of Beijing' to a low-voltage DSP driver of a low-voltage DSP B through a bottom application interface of a microphone A so as to send the target control instruction to an audio hardware abstraction layer in an AP C through the low-voltage DSP driver; and the audio hardware abstraction layer in the AP C sends the received target control instruction 'inquiring the current weather of Beijing' to a second voice assistant application program through a recorder, the second voice assistant application program sends the target control instruction to a corresponding second server, the second server acquires the current weather condition of Beijing and feeds the current weather condition of Beijing back to the second voice assistant application program, and the second voice assistant application program broadcasts the received current weather condition of Beijing through a loudspeaker corresponding to the electronic equipment, so that the function of the voice assistant application program is realized. After the electronic equipment plays the weather condition of the background, if the voice data information of other installed voice assistant application programs is received, the above procedures are repeatedly executed, the corresponding voice assistant application program is awakened, and the control instruction of the corresponding user is realized. In some application scenarios, when the primary wake-up in the low-voltage DSP fails, i.e. the target wake-up word matching fails, or when the secondary wake-up in the AP fails, i.e. the target wake-up word matching fails, the electronic device may generate a corresponding prompt message for prompting the target voice assistant application to determine the failure, where the prompt message may be, for example, "the voice assistant application is not installed," or "please re-input the voice message," or the like. When the server does not return the corresponding feedback information, the corresponding prompt information may also be generated, for example, "corresponding content is not found".
It should be noted that the type of the information fed back to the voice assistant application by the server corresponding to the voice assistant application may be a voice type or a text type, and when the fed back information is a text type, the second voice assistant application may perform text-to-speech conversion on the received information to obtain corresponding voice data, thereby implementing broadcast. In some application scenarios, the voice assistant application may also translate information fed back by the server according to the needs of the user. In some other application scenarios, the process of acquiring the target wake-up word and the process of the target control instruction may be performed in the low-voltage DSP. In some application scenarios, the information fed back by the server may also be displayed and stored on a display area corresponding to the voice assistant application.
It should be noted that, for the descriptions of the same steps and the same contents in this embodiment as those in other embodiments, reference may be made to the descriptions in other embodiments, which are not described herein again.
The embodiment of the application provides a voice information processing method, wherein voice data information is received, matching processing is carried out on the basis of the voice data information and a first preset model base, if the matching processing result is information matching, matching processing is carried out on the basis of the voice data information and a second preset model base, a voice assistant application program to be awakened is determined, and the voice assistant application program to be awakened is awakened. Therefore, when the received voice data information is matched with the information in the first preset model base, the voice data information is matched with the second preset model base again to determine the voice assistant application program to be awakened and awaken, two-stage awakening is achieved, the problems that when one voice assistant application program installed in the electronic equipment is awakened at present, the awakening rate is low and mistaken awakening is easy to occur are solved, the awakening rate is improved, the mistaken awakening probability is reduced, and the intelligent degree of the electronic equipment is improved.
Based on the foregoing embodiments, an embodiment of the present application provides an electronic device, which may be applied to the voice information processing method provided in the embodiments corresponding to fig. 1 to 5, and as shown in fig. 7, the electronic device 3 may include: microphone 31, low voltage digital signal processor DSP 32, application processor AP 33, wherein:
a microphone 31 for collecting voice data information;
the low-voltage DSP 32 is used for matching the voice data information with the information in the first preset model base, awakening the AP to realize one-time awakening when the voice data information is matched with the information in the first preset model base, and sending the voice data information to the AP, so that the power consumption of the electronic equipment is reduced;
and the AP 33 is used for matching the voice data information with the information in the second preset model base, awakening the voice assistant application program to be awakened corresponding to the voice data information to realize secondary awakening when the voice data information is matched with the information in the second preset model base, and executing relevant steps after awakening the voice assistant application program to be awakened.
In other embodiments of the present application, when the low voltage DSP 32 performs the step of matching the voice data information with the first preset model library, the following steps are specifically implemented:
acquiring target awakening information from voice data information;
matching the target awakening information with first reference awakening information in a first preset model base; the first reference awakening information belongs to at least one piece of matching standard information included in a first preset model base, and the first reference awakening information is at least one piece of information which is possessed by a plurality of awakening information;
and if the target awakening information is matched with the first reference awakening information, determining that the information is matched.
In other embodiments of the present application, if the matching result is information matching, the AP 33 performs matching processing based on the voice data information and the second preset model library, and when determining that the voice assistant application is to be woken up, specifically implements the following steps:
if the matching result is information matching, matching the target awakening information with second reference awakening information in a second preset model base;
if the target awakening information is matched with second reference awakening information in a second preset model base, determining a target voice assistant application program corresponding to the target awakening information; the second reference awakening information belongs to at least one matching standard information included in a second preset model library;
the target voice assistant application is determined to be the voice assistant application to wake up.
In other embodiments of the present application, the target wake-up information is a first acoustic model corresponding to the target wake-up word, in the low-voltage DSP 32, the first reference wake-up information is a second acoustic model of the corresponding wake-up word, in the AP 33, the second reference wake-up information is a third acoustic model of the corresponding wake-up word, and correspondingly, if the target wake-up information matches with the second reference wake-up information in the second preset model library, the following steps are specifically implemented when determining the target voice assistant application program corresponding to the target wake-up information:
if the first sound model is matched with the second sound model, determining a target awakening word based on the first sound model;
based on the target wake word, a target voice assistant application is determined.
In other embodiments of the present application, after the AP 33 executes the steps to wake up the to-be-woken voice assistant application, the following steps are also executed:
determining a target control instruction based on the voice data information;
sending a target control instruction to a server corresponding to the awakened voice assistant application program to be awakened through the awakened voice assistant application program to be awakened;
receiving feedback information sent by a server, and playing the feedback information; the feedback information is obtained by the server responding to the target control instruction and executing the operation corresponding to the target control instruction.
In other embodiments of the present application, when the AP 33 executes the step of determining the target control instruction based on the voice data information, the following steps are specifically implemented:
acquiring target voice control information from the voice data information;
and converting the voice signal and the characters of the target voice control information to obtain a target control instruction.
In other embodiments of the present application, before the low-voltage DSP 32 performs the step of matching the first preset model library based on the voice data information, the AP 33 is further configured to perform the following steps:
determining a first number of voice assistant applications installed in the electronic device;
acquiring a wakeup word of each voice assistant application program in a first number of voice assistant application programs;
determining a first sound model corresponding to the awakening word of each voice assistant application program to obtain a first preset model library;
determining a second sound model corresponding to the awakening word of each voice assistant application program to obtain a second preset model library; wherein the quality requirement of the first acoustic model is lower than the quality requirement of the second acoustic model.
In other embodiments of the present application, after the AP 33 executes the steps to determine the second sound model corresponding to the wakeup word of each voice assistant application and obtains the second preset model library, the steps are further configured to:
if it is detected that the updated second number of voice assistant applications have been installed on the electronic device, determining a changed voice assistant application based on the first number of voice assistant applications and the second number of voice assistant applications;
and updating the first preset model library and the second preset model library based on the awakening words corresponding to the changed voice assistant application program.
It should be noted that, for a specific implementation process of the steps executed by the processor in this embodiment, reference may be made to the implementation process in the voice information processing method provided in the embodiments corresponding to fig. 1 to 5, and details are not described here again.
The embodiment of the application provides electronic equipment, which is characterized in that voice data information is received, matching processing is carried out on the basis of the voice data information and a first preset model base, if the matching processing result is information matching, matching processing is carried out on the basis of the voice data information and a second preset model base, a voice assistant application program to be awakened is determined, and the voice assistant application program to be awakened is awakened. Therefore, when the received voice data information is matched with the information in the first preset model base, the voice data information is matched with the second preset model base again to determine the voice assistant application program to be awakened and awaken, two-stage awakening is achieved, the problems that when one voice assistant application program installed in the electronic equipment is awakened at present, the awakening rate is low and mistaken awakening is easy to occur are solved, the awakening rate is improved, the mistaken awakening probability is reduced, and the intelligent degree of the electronic equipment is improved.
Based on the foregoing embodiments, embodiments of the present application provide a computer-readable storage medium, in which executable instructions are stored, and when executed by a processor, the executable instructions will cause the processor to perform the method provided by the embodiments of the present application, for example, the method provided by the embodiments corresponding to fig. 1 to 5.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application 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, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. 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.
The above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application.
Claims (10)
1. A method of speech information processing, the method comprising:
receiving voice data information;
matching processing is carried out on the basis of the voice data information and a first preset model base; the first preset model library comprises at least one piece of matching standard information;
if the matching processing is information matching, matching processing is carried out on the basis of the voice data information and a second preset model base, and a voice assistant application program to be awakened is determined; the first preset model library is different from the second preset model library, and the second preset model library comprises at least one matching standard information;
and awakening the voice assistant application to be awakened.
2. The method of claim 1, wherein the matching with the first pre-set model library based on the voice data information comprises:
acquiring target awakening information from the voice data information;
matching the target awakening information with first reference awakening information in the first preset model base; the first reference awakening information belongs to at least one matching standard information included in the first preset model base, and the first reference awakening information is at least one piece of information which is possessed by a plurality of awakening information;
and if the target awakening information is matched with the first reference awakening information, determining information matching.
3. The method of claim 2, wherein if the matching result is information matching, performing matching processing based on the voice data information and a second preset model library to determine a voice assistant application to be woken up comprises:
if the matching result is information matching, matching the target awakening information with second reference awakening information in the second preset model base; the second reference awakening information belongs to at least one matching standard information included in the second preset model library;
if the target awakening information is matched with second reference awakening information in the second preset model base, determining a target voice assistant application program corresponding to the target awakening information;
determining the target voice assistant application as the voice assistant application to wake up.
4. The method of claim 3, wherein the target wake-up message is a first acoustic model corresponding to a target wake-up word, the first reference wake-up message is a second acoustic model corresponding to the wake-up word, the second reference wake-up message is a third acoustic model corresponding to the wake-up word, and if the target wake-up message matches the second reference wake-up message in the second predetermined model library, determining a target voice assistant application corresponding to the target wake-up message comprises:
if the first sound model is matched with the second sound model, determining the target awakening word based on the first sound model;
determining the target voice assistant application based on the target wake word.
5. The method of claim 1, after the waking of the voice assistant application to wake, the method further comprising:
determining a target control instruction based on the voice data information;
sending the target control instruction to a server corresponding to the awakened voice assistant application program to be awakened through the awakened voice assistant application program to be awakened;
receiving feedback information sent by the server, and playing the feedback information; and the feedback information is obtained by the server responding to the target control instruction and executing the operation corresponding to the target control instruction.
6. The method of claim 5, the determining a target control directive based on the voice data information, comprising:
acquiring target voice control information from the voice data information;
and converting the target voice control information between voice signals and characters to obtain the target control instruction.
7. The method according to any one of claims 1 to 6, before performing the matching process with the first predetermined model library based on the voice data information, further comprising:
determining a first number of voice assistant applications installed in the electronic device;
obtaining a wake-up word for each of the first number of voice assistant applications;
determining a first sound model corresponding to the awakening word of each voice assistant application program to obtain a first preset model library;
determining a second sound model corresponding to the awakening word of each voice assistant application program to obtain a second preset model library; wherein the quality requirement of the first acoustic model is lower than the quality requirement of the second acoustic model.
8. The method of claim 7, after determining a second acoustic model corresponding to a wake word for each voice assistant application, and obtaining the second pre-defined library of models, the method further comprising:
if it is detected that the updated second number of voice assistant applications have been installed by the electronic device, determining a changed voice assistant application based on the first number of voice assistant applications and the second number of voice assistant applications;
and updating the first preset model library and the second preset model library based on the awakening words corresponding to the changed voice assistant application program.
9. An electronic device, the electronic device comprising: microphone, low voltage digital signal processor DSP, application processor AP, wherein:
the microphone is used for collecting voice data information;
the low-voltage DSP is used for matching the voice data information with information in a first preset model base, and when the voice data information is matched with the information in the first preset model base, the AP is awakened to realize one-time awakening and the voice data information is sent to the AP, so that the power consumption of the electronic equipment is reduced;
and the AP is used for matching the voice data information with information in a second preset model base, awakening the voice assistant application program to be awakened corresponding to the voice data information to realize secondary awakening when the voice data information is matched with the information in the second preset model base, and executing relevant steps after awakening the voice assistant application program to be awakened.
10. A storage medium having stored thereon a voice information processing program which, when executed by a processor, implements the steps of the voice information processing method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353919.8A CN111161714B (en) | 2019-12-25 | 2019-12-25 | Voice information processing method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911353919.8A CN111161714B (en) | 2019-12-25 | 2019-12-25 | Voice information processing method, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111161714A true CN111161714A (en) | 2020-05-15 |
| CN111161714B CN111161714B (en) | 2023-07-21 |
Family
ID=70557995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911353919.8A Active CN111161714B (en) | 2019-12-25 | 2019-12-25 | Voice information processing method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111161714B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640434A (en) * | 2020-06-05 | 2020-09-08 | 三星电子（中国）研发中心 | Method and apparatus for controlling voice device |
| CN111667827A (en) * | 2020-05-28 | 2020-09-15 | 北京小米松果电子有限公司 | Voice control method and device of application program and storage medium |
| CN111696553A (en) * | 2020-06-05 | 2020-09-22 | 北京搜狗科技发展有限公司 | Voice processing method and device and readable medium |
| CN111694605A (en) * | 2020-05-18 | 2020-09-22 | Oppo广东移动通信有限公司 | Voice information processing method and device, storage medium and electronic equipment |
| CN111755002A (en) * | 2020-06-19 | 2020-10-09 | 北京百度网讯科技有限公司 | Speech recognition device, electronic apparatus, and speech recognition method |
| CN114578949A (en) * | 2022-03-23 | 2022-06-03 | 歌尔股份有限公司 | Awakening method and device of intelligent wearable device and intelligent wearable device |
| WO2022206602A1 (en) * | 2021-03-31 | 2022-10-06 | 华为技术有限公司 | Speech wakeup method and apparatus, and storage medium and system |
| WO2023246894A1 (en) * | 2022-06-25 | 2023-12-28 | 华为技术有限公司 | Voice interaction method and related apparatus |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5850627A (en) * | 1992-11-13 | 1998-12-15 | Dragon Systems, Inc. | Apparatuses and methods for training and operating speech recognition systems |
| CN103956164A (en) * | 2014-05-20 | 2014-07-30 | 苏州思必驰信息科技有限公司 | Voice awakening method and system |
| WO2015074411A1 (en) * | 2013-11-20 | 2015-05-28 | 中兴通讯股份有限公司 | Terminal unlocking method, apparatus and terminal |
| CN106448663A (en) * | 2016-10-17 | 2017-02-22 | 海信集团有限公司 | Voice wakeup method and voice interaction device |
| US20170109011A1 (en) * | 2013-07-02 | 2017-04-20 | Hongming Jiang | Mobile operating system |
| CN107315561A (en) * | 2017-06-30 | 2017-11-03 | 联想(北京)有限公司 | A kind of data processing method and electronic equipment |
| US20170329573A1 (en) * | 2016-05-10 | 2017-11-16 | Google Inc. | Implementations for Voice Assistant on Devices |
| CN107591151A (en) * | 2017-08-22 | 2018-01-16 | 百度在线网络技术（北京）有限公司 | Far field voice awakening method, device and terminal device |
| CN107767863A (en) * | 2016-08-22 | 2018-03-06 | 科大讯飞股份有限公司 | voice awakening method, system and intelligent terminal |
| CN107919123A (en) * | 2017-12-07 | 2018-04-17 | 北京小米移动软件有限公司 | More voice assistant control method, device and computer-readable recording medium |
| CN108877790A (en) * | 2018-05-21 | 2018-11-23 | 江西午诺科技有限公司 | Speaker control method, device, readable storage medium storing program for executing and mobile terminal |
| US20190172457A1 (en) * | 2017-11-30 | 2019-06-06 | Compal Electronics, Inc. | Notebook computer and driving method of voice assistant system |
| WO2019126880A1 (en) * | 2017-12-29 | 2019-07-04 | Fluent.Ai Inc. | A low-power keyword spotting system |
| CN110047485A (en) * | 2019-05-16 | 2019-07-23 | 北京地平线机器人技术研发有限公司 | Identification wakes up method and apparatus, medium and the equipment of word |
| CN110322878A (en) * | 2019-07-01 | 2019-10-11 | 华为技术有限公司 | A kind of sound control method, electronic equipment and system |
| CN110602624A (en) * | 2019-08-30 | 2019-12-20 | Oppo广东移动通信有限公司 | Audio testing method and device, storage medium and electronic equipment |
| CN110600008A (en) * | 2019-09-23 | 2019-12-20 | 苏州思必驰信息科技有限公司 | Voice wake-up optimization method and system |
-
2019
- 2019-12-25 CN CN201911353919.8A patent/CN111161714B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5850627A (en) * | 1992-11-13 | 1998-12-15 | Dragon Systems, Inc. | Apparatuses and methods for training and operating speech recognition systems |
| US20170109011A1 (en) * | 2013-07-02 | 2017-04-20 | Hongming Jiang | Mobile operating system |
| WO2015074411A1 (en) * | 2013-11-20 | 2015-05-28 | 中兴通讯股份有限公司 | Terminal unlocking method, apparatus and terminal |
| CN103956164A (en) * | 2014-05-20 | 2014-07-30 | 苏州思必驰信息科技有限公司 | Voice awakening method and system |
| US20170329573A1 (en) * | 2016-05-10 | 2017-11-16 | Google Inc. | Implementations for Voice Assistant on Devices |
| CN107767863A (en) * | 2016-08-22 | 2018-03-06 | 科大讯飞股份有限公司 | voice awakening method, system and intelligent terminal |
| CN106448663A (en) * | 2016-10-17 | 2017-02-22 | 海信集团有限公司 | Voice wakeup method and voice interaction device |
| CN107315561A (en) * | 2017-06-30 | 2017-11-03 | 联想(北京)有限公司 | A kind of data processing method and electronic equipment |
| CN107591151A (en) * | 2017-08-22 | 2018-01-16 | 百度在线网络技术（北京）有限公司 | Far field voice awakening method, device and terminal device |
| US20190172457A1 (en) * | 2017-11-30 | 2019-06-06 | Compal Electronics, Inc. | Notebook computer and driving method of voice assistant system |
| CN107919123A (en) * | 2017-12-07 | 2018-04-17 | 北京小米移动软件有限公司 | More voice assistant control method, device and computer-readable recording medium |
| WO2019126880A1 (en) * | 2017-12-29 | 2019-07-04 | Fluent.Ai Inc. | A low-power keyword spotting system |
| CN108877790A (en) * | 2018-05-21 | 2018-11-23 | 江西午诺科技有限公司 | Speaker control method, device, readable storage medium storing program for executing and mobile terminal |
| CN110047485A (en) * | 2019-05-16 | 2019-07-23 | 北京地平线机器人技术研发有限公司 | Identification wakes up method and apparatus, medium and the equipment of word |
| CN110322878A (en) * | 2019-07-01 | 2019-10-11 | 华为技术有限公司 | A kind of sound control method, electronic equipment and system |
| CN110602624A (en) * | 2019-08-30 | 2019-12-20 | Oppo广东移动通信有限公司 | Audio testing method and device, storage medium and electronic equipment |
| CN110600008A (en) * | 2019-09-23 | 2019-12-20 | 苏州思必驰信息科技有限公司 | Voice wake-up optimization method and system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111694605A (en) * | 2020-05-18 | 2020-09-22 | Oppo广东移动通信有限公司 | Voice information processing method and device, storage medium and electronic equipment |
| CN111667827A (en) * | 2020-05-28 | 2020-09-15 | 北京小米松果电子有限公司 | Voice control method and device of application program and storage medium |
| CN111667827B (en) * | 2020-05-28 | 2023-10-17 | 北京小米松果电子有限公司 | Voice control method and device for application program and storage medium |
| CN111640434A (en) * | 2020-06-05 | 2020-09-08 | 三星电子（中国）研发中心 | Method and apparatus for controlling voice device |
| CN111696553A (en) * | 2020-06-05 | 2020-09-22 | 北京搜狗科技发展有限公司 | Voice processing method and device and readable medium |
| CN111696553B (en) * | 2020-06-05 | 2023-08-22 | 北京搜狗科技发展有限公司 | Voice processing method, device and readable medium |
| CN111755002A (en) * | 2020-06-19 | 2020-10-09 | 北京百度网讯科技有限公司 | Speech recognition device, electronic apparatus, and speech recognition method |
| WO2022206602A1 (en) * | 2021-03-31 | 2022-10-06 | 华为技术有限公司 | Speech wakeup method and apparatus, and storage medium and system |
| CN114578949A (en) * | 2022-03-23 | 2022-06-03 | 歌尔股份有限公司 | Awakening method and device of intelligent wearable device and intelligent wearable device |
| WO2023246894A1 (en) * | 2022-06-25 | 2023-12-28 | 华为技术有限公司 | Voice interaction method and related apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111161714B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111161714B (en) | Voice information processing method, electronic equipment and storage medium | |
| 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 | |
| CN111223497B (en) | Nearby wake-up method and device for terminal, computing equipment and storage medium | |
| CN106782554B (en) | Voice awakening method and device based on artificial intelligence | |
| CN108735209B (en) | Wake-up word binding method, intelligent device and storage medium | |
| CN102999161B (en) | A kind of implementation method of voice wake-up module and application | |
| WO2020228270A1 (en) | Speech processing method and device, computer device and storage medium | |
| CN105009204A (en) | Speech recognition power management | |
| CN110111789B (en) | Voice interaction method and device, computing equipment and computer readable medium | |
| CN110875045A (en) | Voice recognition method, intelligent device and intelligent television | |
| CN111210829A (en) | Speech recognition method, apparatus, system, device and computer readable storage medium | |
| CN112634897B (en) | Equipment awakening method and device, storage medium and electronic device | |
| CN112420044A (en) | Voice recognition method, voice recognition device and electronic equipment | |
| CN110473542B (en) | Awakening method and device for voice instruction execution function and electronic equipment | |
| CN111833870A (en) | Awakening method and device of vehicle-mounted voice system, vehicle and medium | |
| CN113160815B (en) | Intelligent control method, device, equipment and storage medium for voice wakeup | |
| CN112420043A (en) | Intelligent awakening method and device based on voice, electronic equipment and storage medium | |
| CN114391165A (en) | Voice information processing method, device, equipment and storage medium | |
| CN114999496A (en) | Audio transmission method, control equipment and terminal equipment | |
| CN112306560B (en) | Method and apparatus for waking up an electronic device | |
| CN115841814A (en) | Voice interaction method and electronic equipment | |
| CN112885341A (en) | Voice wake-up method and device, electronic equipment and storage medium | |
| CN112309396A (en) | AI virtual robot state dynamic setting system | |
| CN113539257A (en) | Voice awakening method and 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 |