CN108877773B - Voice recognition method and electronic equipment - Google Patents
Voice recognition method and electronic equipment Download PDFInfo
- Publication number
- CN108877773B CN108877773B CN201810602734.5A CN201810602734A CN108877773B CN 108877773 B CN108877773 B CN 108877773B CN 201810602734 A CN201810602734 A CN 201810602734A CN 108877773 B CN108877773 B CN 108877773B
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- sound
- electronic equipment
- target
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
- G10L15/065—Adaptation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The invention relates to the technical field of electronic equipment, and discloses a voice recognition method and electronic equipment, wherein the voice recognition method comprises the following steps: the electronic equipment extracts a sound factor from voice input by a user in advance, and generates a sound change curve of the user based on the sound factor according to a preset voice development rule model; the electronic device can recognize the current voice of the user according to the sound change curve. By implementing the embodiment of the invention, the voice change curve of the user can be generated by combining the voice development rule model according to the voice factor in the voice and the voice of the user of the electronic equipment, so that the electronic equipment can accurately recognize the current voice of the user according to the voice change curve of the user, and the accuracy of the voice recognition of the electronic equipment is improved.
Description
Technical Field
The invention relates to the technical field of electronic equipment, in particular to a voice recognition method and electronic equipment.
Background
At present, more and more electronic equipment is equipped with speech recognition function on the market, and along with artificial intelligence's development, many electronic equipment all possess the acoustic control and awaken up the function, thereby the user can input the preset sound information of electronic equipment and awaken up electronic equipment, but electronic equipment is usually towards the adult when setting up the sound model storehouse, the sound of adult is more stable, and the degree of discernment is than higher, can accomplish fast and match the sound of the sound information of adult and sound model storehouse. For students in the development period, the sound changes in the development period, so that it is relatively difficult and inefficient to identify the sound of the students in the development period by using the sound model library facing adults.
Disclosure of Invention
The embodiment of the invention discloses a voice recognition method and electronic equipment, which can improve the accuracy of voice recognition according to a sound change curve generated based on a voice development rule model.
The first aspect of the embodiments of the present invention discloses a speech recognition method, which includes:
extracting a target sound factor from target voice input by a user in advance;
determining a voice change curve of the user based on a preset voice development rule model and the target voice factor;
and identifying the current voice of the user according to the voice change curve.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the recognizing the current voice of the user according to the sound variation curve includes:
detecting a current voice input by the user;
according to the sound change curve, acquiring a sound change stage of the sound of the user at the current date and a current sound factor of the sound of the user in the sound change stage;
and identifying the current voice by taking the current sound factor as a basis.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, before the determining the voice change curve of the user based on the preset speech development law model by using the target voice factor as a basis, the method further includes:
collecting voice information of massive users, wherein the voice information at least comprises sound factors corresponding to all age groups of each user;
calculating all the voice information with the same gender according to a big data calculation method to generate the voice development rule model corresponding to the gender;
the determining the voice change curve of the user based on the preset voice development rule model by taking the target voice factor as a basis comprises the following steps:
and determining the voice change curve of the user based on a preset voice development rule model corresponding to the gender of the user and the target voice factor.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the extracting a target sound factor from a target voice input by a user in advance includes:
recognizing a voiceprint of a target voice input by a user in advance;
extracting a plurality of voiceprint nodes in the voiceprint;
and calculating and generating a sound factor contained in the target voice based on the plurality of voiceprint nodes.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the recognizing the current voice of the user according to the sound variation curve, the method further includes:
identifying a target instruction contained in the current voice through semantic analysis, and detecting whether the electronic equipment is in a black screen state;
if the electronic equipment is in a black screen state, controlling the electronic equipment to execute awakening operation and execute operation corresponding to the target instruction;
and if the electronic equipment is not in the black screen state, controlling the electronic equipment to execute the operation corresponding to the target instruction.
A second aspect of an embodiment of the present invention discloses an electronic device, including:
an extracting unit for extracting a target sound factor from a target voice input by a user in advance;
the determining unit is used for determining a voice change curve of the user based on a preset voice development rule model and the target voice factor;
and the recognition unit is used for recognizing the current voice of the user according to the voice change curve.
As an optional implementation manner, in a second aspect of the embodiment of the present invention, the identification unit includes:
the detection subunit is used for detecting the current voice input by the user;
the obtaining subunit is configured to obtain, according to the sound change curve, a sound change stage of the sound of the user at the current date and a current sound factor of the sound of the user in the sound change stage;
and the first identification subunit is used for identifying the current voice according to the current sound factor.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the electronic device further includes:
the collecting unit is used for collecting voice information of massive users before the determining unit determines the voice change curve of the users based on the preset voice development rule model and the target voice factors, and the voice information at least comprises the voice factors corresponding to all ages of the users;
the generating unit is used for calculating all the voice information with the same gender according to a big data calculating method so as to generate the voice development rule model corresponding to the gender;
the determining unit is specifically configured to determine the voice change curve with the user based on a preset voice development rule model corresponding to the gender of the user and based on the target voice factor.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the extraction unit includes:
the second recognition subunit is used for recognizing the voiceprint of the target voice input by the user in advance;
the extracting subunit is used for extracting a plurality of voiceprint nodes in the voiceprint;
and the calculating subunit is used for calculating and generating the sound factor contained in the target voice based on the plurality of voiceprint nodes.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the electronic device further includes:
the detection unit is used for identifying a target instruction contained in the current voice through semantic analysis after the identification unit identifies the current voice of the user according to the voice change curve, and detecting whether the electronic equipment is in a black screen state;
the first control unit is used for controlling the electronic equipment to execute awakening operation and executing operation corresponding to the target instruction when the detection result of the detection unit is positive;
and the second control unit is used for controlling the electronic equipment to execute the operation corresponding to the target instruction when the detection result of the detection unit is negative.
A third aspect of the embodiments of the present invention discloses another electronic device, including:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to perform part or all of the steps of any one of the methods of the first aspect.
A fourth aspect of the present embodiments discloses a computer-readable storage medium storing a program code, where the program code includes instructions for performing part or all of the steps of any one of the methods of the first aspect.
A fifth aspect of embodiments of the present invention discloses a computer program product, which, when run on a computer, causes the computer to perform some or all of the steps of any one of the methods of the first aspect.
A sixth aspect of the present embodiment discloses an application publishing platform, where the application publishing platform is configured to publish a computer program product, where the computer program product is configured to, when running on a computer, cause the computer to perform part or all of the steps of any one of the methods in the first aspect.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, the electronic equipment extracts the sound factor from the voice input by the user in advance, and generates the sound change curve of the user based on the sound factor according to a preset voice development rule model; the electronic device can recognize the current voice of the user according to the sound change curve. Therefore, by implementing the embodiment of the invention, the voice change curve of the user can be generated by combining the voice development rule model according to the voice factor in the voice and the voice of the user of the electronic equipment, so that the electronic equipment can accurately identify the current voice of the user according to the voice change curve of the user, and the accuracy of the voice identification of the electronic equipment is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a speech recognition method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another speech recognition method disclosed in the embodiments of the present invention;
FIG. 3 is a flow chart of another speech recognition method disclosed in the embodiments of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure;
FIG. 5 is a schematic structural diagram of another electronic device disclosed in the embodiments of the present invention;
FIG. 6 is a schematic structural diagram of another electronic device disclosed in the embodiments of the present invention;
fig. 7 is a schematic structural diagram of another electronic device disclosed in the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses a voice recognition method and electronic equipment, which can improve the accuracy of voice recognition according to a sound change curve generated based on a voice development rule model. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a flow chart illustrating a speech recognition method according to an embodiment of the present invention. As shown in fig. 1, the speech recognition method may include the steps of:
101. the electronic device extracts a target sound factor from a target voice input by a user in advance.
In the embodiment of the present invention, the electronic device may be a family education machine, a learning tablet, or the like, which is not limited in the embodiment of the present invention. The user may be a user of the electronic device at any age and at any age. The target voice may be a voice input by a user of the electronic device when using the electronic device for the first time, and the electronic device has been caused to generate a sound variation curve from the target voice. The voice factor may be a voiceprint node having a unique characteristic in the user's voiceprint, and the number of voice factors matched with the user is not limited.
As an optional implementation manner, before the electronic device performs step 101, the following steps may also be performed:
the method comprises the steps that the electronic equipment detects whether a registered account exists in a current user;
if the user information does not exist, the electronic equipment displays and outputs a user information collection page and outputs a voice collection prompt; and when the electronic equipment detects the target voice input by the user, the electronic equipment associates the target voice with the user information and stores the target voice.
By the implementation of the implementation mode, the target voice of the user can be acquired when the user uses the electronic equipment initially, so that the user can directly use the voice recognition function, and the user experience of the user based on the electronic equipment is improved.
102. The electronic equipment determines a sound change curve of the user based on a preset speech development rule model and the target sound factor.
In the embodiment of the invention, the voice development rule model can simulate the voice development trend of the user according to the voice information analysis of massive users, and the electronic equipment can calculate the voice change curve of the user based on the target voice factor according to the voice development rule model. Since the sound of the user is continuously changed during the development period, but the sound may not be continuously changed after the user development period is over, the sound change curve may be a sound change trend during the development period of the user, or a sound change curve of a lifetime of the user.
As an alternative implementation, after the electronic device performs step 102, the following steps may also be performed:
the electronic equipment acquires the current age of the user at preset time intervals;
the electronic equipment updates the sound change curve of the user according to the current age and deletes information irrelevant to the sound change curve;
and the electronic equipment stores the updated sound change curve of the user.
By implementing the implementation mode, the voice change curve corresponding to the user can be updated at regular time, so that the voice recognition of the user by the electronic equipment is more accurate.
103. The electronic equipment identifies the current voice of the user according to the sound change curve.
In the embodiment of the invention, the electronic equipment identifies the user of the electronic equipment by identifying the voice matched with the sound change curve in the environment where the electronic equipment is located. The sound change curve can be generated by calculating a plurality of sound factors generated by a speech development law model.
In the method described in fig. 1, a voice change curve of a user can be generated according to a voice of a user of an electronic device obtained in advance and by combining a voice development rule model according to a voice factor in the voice, so that the electronic device can accurately recognize the current voice of the user according to the voice change curve of the user, thereby improving the accuracy of voice recognition of the electronic device. The voice development rule can be prestored in a memory of the electronic equipment, so that the condition that the voice recognition cannot be carried out due to the fact that the voice change curve is lost is avoided. In addition, a user-specific sound profile of the electronic device can be generated to make the functionality of the electronic device more user-friendly.
Example two
Referring to fig. 2, fig. 2 is a flow chart illustrating another speech recognition method according to an embodiment of the present invention. As shown in fig. 2, the speech recognition method may include the steps of:
201. the electronic equipment collects voice information of massive users, and the voice information at least comprises sound factors corresponding to all ages of the users.
In the embodiment of the present invention, the voice information of the mass users may be the voice information of the users of all the electronic devices collected by the electronic device, or may be obtained from third-party voice analysis software, which is not limited in the embodiment of the present invention.
In the embodiment of the present invention, each age group of the user may be divided by a preset time interval, or may be divided by the user, where the preset time interval may be one month, one year, two years, five years, and the like, and thus, the embodiment of the present invention is not limited.
As an alternative implementation, the manner of collecting voice information of a large number of users by the electronic device may include the following steps:
the method comprises the steps that the electronic equipment obtains a sound factor corresponding to each age group of a user of each electronic equipment, wherein the age groups of the user are divided according to a preset rule;
the electronic equipment associates and matches all the sound factors with the corresponding users and the age groups of the users, and integrates all the age groups corresponding to each user and all the sound factors corresponding to each age group to generate a voice information packet corresponding to the users;
the electronic device sends the voice information packet to the server.
By implementing the implementation mode, the detailed voice information of all electronic equipment users can be acquired, and the voice information of each user is integrated and stored according to the age group, so that the electronic equipment can call the voice information of massive users at any time, and the accuracy of generating the voice development law model is improved.
202. The electronic equipment calculates all the voice information with the same gender according to a big data calculation method so as to generate a voice development rule model corresponding to the gender.
In the embodiment of the invention, because the difference between the male voice and the female voice in the development period is large, the male voice information and the female voice information need to be calculated separately, so that the accuracy of the generated male voice development rule model and the accuracy of the female voice development rule model are ensured.
As an alternative implementation, after the electronic device performs step 202, the following steps may be further performed:
the electronic equipment analyzes the voice development law model so as to divide the voice development law model into a plurality of sound change stages according to the change of the voice development law model;
the electronic equipment acquires the average age range of the user corresponding to each sound change stage;
and the electronic equipment associates each sound change stage with the average age range of the corresponding user and stores the sound change stage to service equipment which is connected with the electronic equipment in advance.
By implementing the implementation mode, the sound change modes of mass users can be comprehensively analyzed to obtain the sound change stages divided according to the sound change modes, so that the division of the sound change stages is more reasonable.
In the embodiment of the present invention, by implementing the steps 201 to 202, mass voice information can be divided into two groups according to gender, and two voice development rule models corresponding to gender are obtained through big data calculation, so that a more accurate voice development rule model is obtained according to gender.
Optionally, steps 201 to 202 may be performed before step 203, or may be performed after step 203 and before step 204, which is not limited in the embodiment of the present invention.
203. The electronic device extracts a target sound factor from a target voice input by a user in advance.
204. The electronic equipment determines a voice change curve with the user based on a preset voice development rule model corresponding to the gender of the user and based on the target voice factor.
In the embodiment of the invention, the voice change curve of the user can be determined according to the voice development rule model corresponding to the gender of the user, and the voice development rule models of the male and the female are distinguished because the voice change difference of the male and the female is large, so that the determined voice change curve of the user can be more accurate.
205. The electronic device detects a current voice input by a user.
In the embodiment of the invention, the current voice input by the user can be the voice randomly spoken by the user, or the voice with instructions used by the user to trigger the electronic equipment to start and/or the electronic equipment to start the target application program.
206. The electronic equipment acquires the sound change stage of the sound of the user at the current date and the current sound factor of the sound of the user in the sound change stage according to the sound change curve.
207. The electronic equipment identifies the current voice according to the current sound factor.
In the embodiment of the present invention, by implementing the above steps 205 to 207, the current sound factor of the sound variation curve of the user can be obtained, and the user matched with the sound variation curve is identified by comparing the current sound factor with the sound factor of the current voice, so that the accuracy of voice identification is improved.
As an alternative embodiment, the electronic device may recognize the current speech based on the current sound factor, and the method may include the following steps:
the method comprises the steps that the electronic equipment obtains current voice in the environment where the electronic equipment is located;
the electronic equipment identifies a plurality of target sound factors contained in the current voice;
the electronic equipment judges whether any one target sound factor matched with the current sound factor acquired by the electronic equipment in advance exists in the target sound factors;
if the voice exists, the electronic equipment determines that the user corresponding to the current voice is the user pre-stored in the electronic equipment.
When the implementation mode is implemented, the plurality of sound factors can be acquired, and when any one of the plurality of sound factors is matched with the current sound factor of the user of the electronic equipment, the user of the electronic equipment can be identified, so that the error of the user of the electronic equipment for speech recognition is reduced, and the accuracy of the speech recognition of the electronic equipment is ensured.
In the method described in fig. 2, a voice change curve of a user can be generated according to a voice of a user of an electronic device obtained in advance and by combining a voice development rule model according to a voice factor in the voice, so that the electronic device can accurately recognize the current voice of the user according to the voice change curve of the user, thereby improving the accuracy of voice recognition of the electronic device. Massive user voice information can be analyzed through a big data technology, a voice development rule model can be rapidly obtained, and the operation efficiency of the electronic equipment is guaranteed. In addition, the electronic device can uniquely identify the user of the electronic device in a noisy environment according to the unique sound variation model of the user, so that the user can successfully use the voice recognition function of the electronic device in various environments.
EXAMPLE III
Referring to fig. 3, fig. 3 is a flow chart illustrating another speech recognition method according to an embodiment of the present invention. As shown in fig. 3, the speech recognition method may include the steps of:
step 301 to step 302 are the same as step 201 to step 202, and the following description is omitted.
303. The electronic device recognizes a voiceprint of a target voice previously input by a user.
In the embodiment of the invention, the Voiceprint (Voiceprint) is a sound wave spectrum carrying language information, and the Voiceprint not only has specificity, but also has the characteristic of relative stability. After adulthood, human voice can remain relatively stable for a long period of time, but during the developmental period, human voice is usually in a state of change.
304. The electronic device extracts a number of voiceprint nodes in the voiceprint.
In the embodiment of the present invention, the voiceprint node may be a node capable of obviously expressing the characteristics of the user voiceprint, and the number of the voiceprint nodes included in the user voiceprint is not limited.
305. And the electronic equipment calculates and generates sound factors contained in the target voice based on the plurality of voiceprint nodes.
In the embodiment of the invention, the electronic equipment can comprehensively analyze the voiceprint nodes, so that the electronic equipment obtains the specific sound factor of the user from the voiceprint nodes through analysis.
In the embodiment of the present invention, by implementing steps 303 to 305, a voiceprint node having a personal characteristic of the user can be obtained from a voiceprint of the user voice to generate a voice factor having the personal characteristic of the user, so that difficulty in voice recognition is reduced.
306. The electronic equipment determines a voice change curve with the user based on a preset voice development rule model corresponding to the gender of the user and based on the target voice factor.
307. The electronic equipment identifies the current voice of the user according to the sound change curve.
308. The electronic equipment identifies a target instruction contained in the current voice through semantic analysis, detects whether the electronic equipment is in a black screen state, and if so, executes step 309; if not, step 310 is performed.
In the embodiment of the present invention, the target instruction may be a voice including a specific word, and different instructions may correspond to different words (for example, a word corresponding to the wake-up instruction may be 'smallpox', a word corresponding to the voice question searching instruction may be 'microstep', a word corresponding to the review instruction may be 'xiaolui', and the like). The blank screen state of the electronic equipment can be that the electronic equipment is currently in a shutdown mode or the electronic equipment is currently in a standby mode, and when the electronic equipment is currently in the shutdown mode, if the electronic equipment needs to perform awakening operation, the electronic equipment needs to be automatically started; when the electronic device is currently in the standby mode, if the electronic device is to perform the wake-up operation, the electronic device needs to change the mode of the electronic device to the working mode, and turn on the display screen of the electronic device.
309. The electronic equipment controls the electronic equipment to execute the awakening operation and execute the operation corresponding to the target instruction.
310. The electronic device controls the electronic device to perform an operation corresponding to the target instruction.
In the embodiment of the present invention, by implementing the steps 308 to 310, the electronic device can be directly started according to the current voice of the user, and the application program that the user wants to start can be started, so that the steps of using the electronic device by the user are simplified, and the efficiency of using the electronic device by the user is also improved.
For example, the electronic device may be a family education machine, and when the family education machine recognizes that the current voice is the voice of the user of the family education machine, the family education machine may recognize the content of the current voice; when the family education machine recognizes that the current voice content is 'step by step', the family education machine can judge a target instruction contained in the content, and the target instruction contained in the 'step by step' can be a voice question searching function for starting the family education machine, so that the family education machine needs to start the voice question searching function; the home teaching machine can judge whether the current state of the home teaching machine is in a black screen state, and if the current state of the home teaching machine is in the black screen state, the home teaching machine needs to light a display screen of the home teaching machine; when the family education machine lights up the display screen, a page or an application program containing the voice question searching function can be directly triggered to be started; if the teaching machine is not in the black screen state, the family teaching machine can immediately trigger the opening of a page or an application program containing the voice question searching function. In addition, the teaching machine can detect instructions with more functions, including but not limited to voice question searching function, test function, audio and/or video learning function, note taking function, photo question searching function, review function, etc. Through the target instruction in the discernment current pronunciation, the function that trigger that can be quick corresponds with the target instruction starts, has improved the efficiency that the user used the family education machine.
In the method described in fig. 3, the voice of the user of the electronic device can be obtained in advance, so that the voice change curve of the user can be generated according to the voice factor in the voice and in combination with the voice development rule model, so that the electronic device can accurately recognize the current voice of the user according to the voice change curve of the user, and the accuracy of the voice recognition of the electronic device is improved. And the sound factor can be calculated and generated by extracting the voiceprint node of the user sound, so that the sound factor calculated by the electronic equipment is more accurate.
Example four
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. As shown in fig. 4, the electronic device may include:
an extracting unit 401, configured to extract a target sound factor from a target voice input by a user in advance.
As an optional implementation, the extraction unit 401 may further be configured to:
detecting whether a current user has a registered account;
if the user information does not exist, displaying and outputting a user information collection page, and outputting a voice collection prompt; and when the target voice input by the user is detected, associating the target voice with the user information and storing the target voice.
By the implementation of the implementation mode, the target voice of the user can be acquired when the user uses the electronic equipment initially, so that the user can directly use the voice recognition function, and the user experience of the user based on the electronic equipment is improved.
The determining unit 402 is configured to determine a voice change curve of the user based on a preset voice development law model and based on the target voice factor extracted by the extracting unit 401.
As an optional implementation, the determining unit 402 may further be configured to:
acquiring the current age of a user at preset time intervals;
updating the sound change curve of the user according to the current age, and deleting information irrelevant to the sound change curve;
and storing the updated sound change curve of the user.
By implementing the implementation mode, the voice change curve corresponding to the user can be updated at regular time, so that the voice recognition of the user by the electronic equipment is more accurate.
A recognition unit 403, configured to recognize the current voice of the user according to the sound variation curve determined by the determination unit 402.
It can be seen that, with the electronic device described in fig. 4, the voice of the user of the electronic device can be obtained in advance, and therefore, the voice change curve of the user can be generated according to the voice factor in the voice and in combination with the voice development rule model, so that the electronic device can accurately recognize the current voice of the user according to the voice change curve of the user, and the accuracy of the voice recognition of the electronic device is improved. The voice development rule can be prestored in a memory of the electronic equipment, so that the condition that the voice recognition cannot be carried out due to the fact that the voice change curve is lost is avoided. In addition, a user-specific sound profile of the electronic device can be generated to make the functionality of the electronic device more user-friendly.
EXAMPLE five
Referring to fig. 5, fig. 5 is a schematic structural diagram of another electronic device according to an embodiment of the disclosure. The electronic device shown in fig. 5 is optimized from the electronic device shown in fig. 4. Compared to the electronic device shown in fig. 4, the identification unit 403 of the electronic device shown in fig. 5 may include:
a detecting subunit 4031, configured to detect a current voice input by the user.
An obtaining subunit 4032, configured to obtain, according to the sound change curve determined by the determining unit 402, a sound change phase in which the sound of the user is located at the current date and a current sound factor of the sound of the user in the sound change phase.
The first identifying subunit 4033 is configured to identify the current speech detected by the detecting subunit 4031, based on the current sound factor acquired by the acquiring subunit 4032.
As an alternative embodiment, the first identifying subunit 4033 uses the current sound factor as a basis, and the manner for identifying the current speech may be:
acquiring current voice in the environment where the electronic equipment is located;
identifying a plurality of target sound factors contained in the current voice;
judging whether any one target sound factor matched with the current sound factor acquired by the electronic equipment in advance exists in the plurality of target sound factors;
and if so, determining that the user corresponding to the current voice is a user pre-stored in the electronic equipment.
When the implementation mode is implemented, the plurality of sound factors can be acquired, and when any one of the plurality of sound factors is matched with the current sound factor of the user of the electronic equipment, the user of the electronic equipment can be identified, so that the error of the user of the electronic equipment for speech recognition is reduced, and the accuracy of the speech recognition of the electronic equipment is ensured.
In the embodiment of the invention, the current sound factor of the sound change curve of the user can be obtained, and the user matched with the sound change curve is identified by comparing the current sound factor with the sound factor of the current voice, so that the accuracy of voice identification is improved.
As an alternative implementation, the electronic device shown in fig. 5 may further include:
a collecting unit 404, configured to collect voice information of a large number of users before the determining unit 402 determines a voice change curve of a user based on a preset voice development law model and a target voice factor, where the voice information at least includes a voice factor corresponding to each age group of each user;
the generating unit 405 is configured to calculate all the voice information with the same gender collected by the collecting unit 404 according to a big data calculation method to generate a voice development law model corresponding to the gender.
By implementing the implementation mode, mass voice information can be divided into two groups by taking gender as a basis, and two voice development rule models corresponding to the gender are obtained through big data calculation, so that a more accurate voice development rule model is obtained according to the gender.
As an alternative implementation, the manner of collecting the voice information of the massive users by the collecting unit 404 may be:
acquiring a sound factor corresponding to each age group of a user of each electronic device, wherein the age groups of the user are divided according to a preset rule;
all the sound factors are associated and matched with the corresponding users and the age groups of the users, and all the age groups corresponding to each user and all the sound factors corresponding to each age group are integrated to generate a voice information packet corresponding to the users;
and sending the voice information packet to a server.
By implementing the implementation mode, the detailed voice information of all electronic equipment users can be acquired, and the voice information of each user is integrated and stored according to the age group, so that the electronic equipment can call the voice information of massive users at any time, and the accuracy of generating the voice development law model is improved.
As an optional implementation, the generating unit 405 may further be configured to:
analyzing the speech development law model to divide the speech development law model into a plurality of sound change stages according to the change of the speech development law model;
acquiring an average age range of the user corresponding to each sound change stage;
and associating each sound change stage with the corresponding average age range of the user, and storing the sound change stages to service equipment which is connected with the electronic equipment in advance.
By implementing the implementation mode, the sound change modes of mass users can be comprehensively analyzed to obtain the sound change stages divided according to the sound change modes, so that the division of the sound change stages is more reasonable.
As an alternative embodiment, the determining unit 402 determines the sound variation curve of the user based on the target sound factor extracted by the extracting unit 401 based on a preset speech development law model, which may specifically be:
and determining a voice change curve with the user based on a preset voice development rule model corresponding to the gender of the user and the target voice factor.
By implementing the implementation mode, the voice change curve of the user can be determined according to the voice development rule model corresponding to the gender of the user, and the voice development rule models of the male and the female are distinguished to enable the determined voice change curve of the user to be more accurate due to the fact that the difference between the voice changes of the male and the female is large.
It can be seen that, with the electronic device described in fig. 5, the voice change curve of the user can be generated according to the voice of the user of the electronic device obtained in advance and by combining the voice development rule model according to the voice factor in the voice, so that the electronic device can accurately recognize the current voice of the user according to the voice change curve of the user, and the accuracy of the voice recognition of the electronic device is improved. Massive user voice information can be analyzed through a big data technology, a voice development rule model can be rapidly obtained, and the operation efficiency of the electronic equipment is guaranteed. In addition, the electronic device can uniquely identify the user of the electronic device in a noisy environment according to the unique sound variation model of the user, so that the user can successfully use the voice recognition function of the electronic device in various environments.
EXAMPLE six
Referring to fig. 6, fig. 6 is a schematic structural diagram of another electronic device according to an embodiment of the disclosure. The electronic device shown in fig. 6 is optimized from the electronic device shown in fig. 5. Compared to the electronic device shown in fig. 5, the extraction unit 401 of the electronic device shown in fig. 6 may include:
and a second recognition subunit 4011 configured to recognize a voiceprint of a target speech input by the user in advance.
An extracting sub-unit 4012, configured to extract a plurality of voiceprint nodes in the voiceprint identified by the second identifying sub-unit 4011.
And the computing subunit 4013 is configured to compute and generate a sound factor included in the target speech based on the plurality of voiceprint nodes extracted by the extracting subunit 4012.
In the embodiment of the invention, the voiceprint node with the personal characteristics of the user can be acquired from the voiceprint of the voice of the user to generate the voice factor with the personal characteristics of the user, so that the difficulty of voice recognition is reduced.
As an alternative implementation, the electronic device shown in fig. 6 may further include:
the detection unit 406 is configured to, after the recognition unit 403 recognizes the current voice of the user according to the sound variation curve, recognize a target instruction included in the current voice through semantic analysis, and detect whether the electronic device is in a black screen state;
a first control unit 407, configured to control the electronic device to perform a wake-up operation and perform an operation corresponding to the target instruction when the result detected by the detection unit 406 is yes;
and a second control unit 408 for controlling the electronic device to execute an operation corresponding to the target instruction when the result detected by the detection unit 406 is no.
By implementing the implementation mode, the electronic equipment can be directly started according to the current voice of the user, and the application program which the user wants to start is started, so that the steps of using the electronic equipment by the user are simplified, and the efficiency of using the electronic equipment by the user is also improved.
It can be seen that, with the electronic device described in fig. 6, the voice change curve of the user can be generated according to the voice of the user of the electronic device obtained in advance and by combining the voice development rule model according to the voice factor in the voice, so that the electronic device can accurately recognize the current voice of the user according to the voice change curve of the user, and the accuracy of the voice recognition of the electronic device is improved. And the sound factor can be calculated and generated by extracting the voiceprint node of the user sound, so that the sound factor calculated by the electronic equipment is more accurate.
EXAMPLE seven
Referring to fig. 7, fig. 7 is a schematic structural diagram of another electronic device according to an embodiment of the disclosure. As shown in fig. 7, the electronic device may include:
a memory 701 in which executable program code is stored;
a processor 702 coupled to the memory 701;
wherein, the processor 702 calls the executable program code stored in the memory 701 to execute part or all of the steps of the method in the above method embodiments.
The embodiment of the invention also discloses a computer readable storage medium, wherein the computer readable storage medium stores program codes, wherein the program codes comprise instructions for executing part or all of the steps of the method in the above method embodiments.
Embodiments of the present invention also disclose a computer program product, wherein, when the computer program product is run on a computer, the computer is caused to execute part or all of the steps of the method as in the above method embodiments.
The embodiment of the present invention also discloses an application publishing platform, wherein the application publishing platform is used for publishing a computer program product, and when the computer program product runs on a computer, the computer is caused to execute part or all of the steps of the method in the above method embodiments.
It should be understood that the embodiments described in this specification are exemplary of alternative embodiments and that the acts and modules illustrated are not required to practice the invention. It should also be understood by those skilled in the art that the sequence numbers of the above-mentioned processes do not imply any necessary sequence of execution, and the execution sequence of each process should be determined by its function and its inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a from which B can be determined. It should also be understood, however, that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.
It will be understood by those skilled in the art that all or part of the steps in the methods of the embodiments described above may be implemented by instructions associated with a program, which may be stored in a computer-readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), compact disc-Read-Only Memory (CD-ROM), or other Memory, magnetic disk, magnetic tape, or magnetic tape, Or any other medium which can be used to carry or store data and which can be read by a computer.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the above-described method of each embodiment of the present invention.
The speech recognition method and the electronic device disclosed in the embodiments of the present invention are described in detail above, and the principles and embodiments of the present invention are explained herein by applying specific examples, and the description of the embodiments above is only used to help understanding the method and the core ideas of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method of speech recognition, the method comprising:
extracting a target sound factor from target voice input by a user in advance;
determining a voice change curve of the user based on a preset voice development rule model and the target voice factor;
recognizing the current voice of the user according to the voice change curve;
before the determining the voice change curve of the user based on the preset voice development law model by using the target voice factor as a basis, the method further comprises:
collecting voice information of massive users, wherein the voice information at least comprises sound factors corresponding to all age groups of each user;
calculating all the voice information with the same gender according to a big data calculation method to generate the voice development rule model corresponding to the gender;
the determining the voice change curve of the user based on the preset voice development rule model by taking the target voice factor as a basis comprises the following steps:
and determining the voice change curve of the user based on a preset voice development rule model corresponding to the gender of the user and the target voice factor.
2. The method of claim 1, wherein the identifying the current speech of the user according to the voice profile comprises:
detecting a current voice input by the user;
according to the sound change curve, acquiring a sound change stage of the sound of the user at the current date and a current sound factor of the sound of the user in the sound change stage;
and identifying the current voice by taking the current sound factor as a basis.
3. The method according to claim 1 or 2, wherein the extracting a target sound factor from a target voice input by a user in advance comprises:
recognizing a voiceprint of a target voice input by a user in advance;
extracting a plurality of voiceprint nodes in the voiceprint;
and calculating and generating a sound factor contained in the target voice based on the plurality of voiceprint nodes.
4. The method of claim 1, wherein after identifying the current speech of the user according to the voice profile, the method further comprises:
identifying a target instruction contained in the current voice through semantic analysis, and detecting whether the electronic equipment is in a black screen state;
if the electronic equipment is in a black screen state, controlling the electronic equipment to execute awakening operation and execute operation corresponding to the target instruction;
and if the electronic equipment is not in the black screen state, controlling the electronic equipment to execute the operation corresponding to the target instruction.
5. The method of claim 2, wherein after identifying the current speech of the user according to the voice profile, the method further comprises:
identifying a target instruction contained in the current voice through semantic analysis, and detecting whether the electronic equipment is in a black screen state;
if the electronic equipment is in a black screen state, controlling the electronic equipment to execute awakening operation and execute operation corresponding to the target instruction;
and if the electronic equipment is not in the black screen state, controlling the electronic equipment to execute the operation corresponding to the target instruction.
6. An electronic device, comprising:
an extracting unit for extracting a target sound factor from a target voice input by a user in advance;
the determining unit is used for determining a voice change curve of the user based on a preset voice development rule model and the target voice factor;
the recognition unit is used for recognizing the current voice of the user according to the voice change curve;
the electronic device further includes:
the collecting unit is used for collecting voice information of massive users before the determining unit determines the voice change curve of the users based on the preset voice development rule model and the target voice factors, and the voice information at least comprises the voice factors corresponding to all ages of the users;
the generating unit is used for calculating all the voice information with the same gender according to a big data calculating method so as to generate the voice development rule model corresponding to the gender;
the determining unit is specifically configured to determine a voice change curve of the user based on a preset voice development rule model corresponding to the gender of the user and based on the target voice factor.
7. The electronic device according to claim 6, wherein the identification unit includes:
the detection subunit is used for detecting the current voice input by the user;
the obtaining subunit is configured to obtain, according to the sound change curve, a sound change stage of the sound of the user at the current date and a current sound factor of the sound of the user in the sound change stage;
and the first identification subunit is used for identifying the current voice according to the current sound factor.
8. The electronic device according to claim 6 or 7, wherein the extraction unit includes:
the second recognition subunit is used for recognizing the voiceprint of the target voice input by the user in advance;
the extracting subunit is used for extracting a plurality of voiceprint nodes in the voiceprint;
and the calculating subunit is used for calculating and generating the sound factor contained in the target voice based on the plurality of voiceprint nodes.
9. The electronic device of claim 6, further comprising:
the detection unit is used for identifying a target instruction contained in the current voice through semantic analysis after the identification unit identifies the current voice of the user according to the voice change curve, and detecting whether the electronic equipment is in a black screen state;
the first control unit is used for controlling the electronic equipment to execute awakening operation and executing operation corresponding to the target instruction when the detection result of the detection unit is positive;
and the second control unit is used for controlling the electronic equipment to execute the operation corresponding to the target instruction when the detection result of the detection unit is negative.
10. The electronic device of claim 7, further comprising:
the detection unit is used for identifying a target instruction contained in the current voice through semantic analysis after the identification unit identifies the current voice of the user according to the voice change curve, and detecting whether the electronic equipment is in a black screen state;
the first control unit is used for controlling the electronic equipment to execute awakening operation and executing operation corresponding to the target instruction when the detection result of the detection unit is positive;
and the second control unit is used for controlling the electronic equipment to execute the operation corresponding to the target instruction when the detection result of the detection unit is negative.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810602734.5A CN108877773B (en) | 2018-06-12 | 2018-06-12 | Voice recognition method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810602734.5A CN108877773B (en) | 2018-06-12 | 2018-06-12 | Voice recognition method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108877773A CN108877773A (en) | 2018-11-23 |
| CN108877773B true CN108877773B (en) | 2020-07-24 |
Family
ID=64338194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810602734.5A Active CN108877773B (en) | 2018-06-12 | 2018-06-12 | Voice recognition method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108877773B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109545196B (en) * | 2018-12-29 | 2022-11-29 | 深圳市科迈爱康科技有限公司 | Speech recognition method, device and computer readable storage medium |
| CN110336723A (en) * | 2019-07-23 | 2019-10-15 | 珠海格力电器股份有限公司 | Control method and device, the intelligent appliance equipment of intelligent appliance |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103151039A (en) * | 2013-02-07 | 2013-06-12 | 中国科学院自动化研究所 | Speaker age identification method based on SVM (Support Vector Machine) |
| CN103544393A (en) * | 2013-10-23 | 2014-01-29 | 北京师范大学 | Method for tracking development of language abilities of children |
| CN104700843A (en) * | 2015-02-05 | 2015-06-10 | 海信集团有限公司 | Method and device for identifying ages |
| CN105575384A (en) * | 2016-01-13 | 2016-05-11 | 广东小天才科技有限公司 | Method, apparatus and equipment for automatically adjusting play resource according to the level of user |
| CN106200886A (en) * | 2015-04-30 | 2016-12-07 | 包伯瑜 | A kind of intelligent movable toy manipulated alternately based on language and toy using method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9620120B2 (en) * | 2015-05-22 | 2017-04-11 | Kabushiki Kaisha Toshiba | Minutes taking system, minutes taking method, and image forming apparatus |
-
2018
- 2018-06-12 CN CN201810602734.5A patent/CN108877773B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103151039A (en) * | 2013-02-07 | 2013-06-12 | 中国科学院自动化研究所 | Speaker age identification method based on SVM (Support Vector Machine) |
| CN103544393A (en) * | 2013-10-23 | 2014-01-29 | 北京师范大学 | Method for tracking development of language abilities of children |
| CN104700843A (en) * | 2015-02-05 | 2015-06-10 | 海信集团有限公司 | Method and device for identifying ages |
| CN106200886A (en) * | 2015-04-30 | 2016-12-07 | 包伯瑜 | A kind of intelligent movable toy manipulated alternately based on language and toy using method |
| CN105575384A (en) * | 2016-01-13 | 2016-05-11 | 广东小天才科技有限公司 | Method, apparatus and equipment for automatically adjusting play resource according to the level of user |
Non-Patent Citations (1)
| Title |
|---|
| 声纹识别技术及其应用现状;郑方 等;《信息安全研究》;20160131;第2卷(第1期);第44-53页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108877773A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109545184B (en) | Recitation detection method based on voice calibration and electronic equipment | |
| CN108053839B (en) | Language exercise result display method and microphone equipment | |
| CN108766431B (en) | Automatic awakening method based on voice recognition and electronic equipment | |
| CN109086590B (en) | Interface display method of electronic equipment and electronic equipment | |
| EP2887229A2 (en) | Communication support apparatus, communication support method and computer program product | |
| CN109240786B (en) | Theme changing method and electronic equipment | |
| CN108320734A (en) | Audio signal processing method and device, storage medium, electronic equipment | |
| JP6866715B2 (en) | Information processing device, emotion recognition method, and program | |
| CN109086455B (en) | Method for constructing voice recognition library and learning equipment | |
| CN109165336B (en) | Information output control method and family education equipment | |
| CN111081080B (en) | Voice detection method and learning device | |
| CN108877773B (en) | Voice recognition method and electronic equipment | |
| CN111343028A (en) | Distribution network control method and device | |
| US20170076626A1 (en) | System and Method for Dynamic Response to User Interaction | |
| KR20190112962A (en) | Cognitive rehabilitation training system | |
| CN111739534B (en) | Processing method and device for assisting speech recognition, electronic equipment and storage medium | |
| CN111077996A (en) | Information recommendation method based on point reading and learning equipment | |
| JP2006230548A (en) | Physical condition judging device and its program | |
| CN109271480B (en) | Voice question searching method and electronic equipment | |
| CN111161745A (en) | Awakening method, device, equipment and medium for intelligent equipment | |
| CN111754989B (en) | Avoiding method for voice false wake-up and electronic equipment | |
| CN111091821B (en) | Control method based on voice recognition and terminal equipment | |
| CN111077997A (en) | Point reading control method in point reading mode and electronic equipment | |
| US20230117535A1 (en) | Method and system for device feature analysis to improve user experience | |
| CN109165277B (en) | Composition output method and learning equipment |
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 |