CN111880988B - Voiceprint wake-up log collection method and device - Google Patents
Voiceprint wake-up log collection method and device Download PDFInfo
- Publication number
- CN111880988B CN111880988B CN202010659084.5A CN202010659084A CN111880988B CN 111880988 B CN111880988 B CN 111880988B CN 202010659084 A CN202010659084 A CN 202010659084A CN 111880988 B CN111880988 B CN 111880988B
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- wake
- log
- awakening
- mark
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/06—Decision making techniques; Pattern matching strategies
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The embodiment of the invention discloses a method and a device for collecting voiceprint wake-up logs, relates to the technical field of log collection, and solves the problem that collected voiceprint wake-up logs are lack of marks in the prior art. The method comprises the following steps: receiving a voiceprint wake-up input; performing voiceprint wake-up verification on the voiceprint wake-up input; under the condition that the voiceprint awakening verification is not passed, acquiring a first receiving result; the first receiving result is that the awakening input is received within a first preset time length or the awakening input is not received within the first preset time length; acquiring a second receiving result under the condition that the voiceprint awakening verification is passed; the second receiving result is that the effective control instruction is received within a second preset time length, or the effective control instruction is not received within the second preset time length; and generating a voiceprint wake-up log, and determining the mark of the voiceprint wake-up log according to the first receiving result or the second receiving result. The embodiment of the invention is used for collecting the voiceprint awakening log.
Description
Technical Field
The embodiment of the invention relates to the technical field of log collection, in particular to a voiceprint wake-up log collection method and device.
Background
Voiceprint features are one of important biological features of human bodies, have strong individual specificity, and are commonly used as a feature of identity authentication in the fields of voiceprint recognition, voiceprint authentication and the like. With the rapid development of voice processing technology, voiceprint wake-up technology has been widely applied to terminal products supporting voice wake-up function. In the research and development process of the voiceprint wake-up device, in order to improve user experience, research and development engineers need a large number of voiceprint wake-up logs to be used for analyzing user mistaken wake-up and normal wake-up data, so as to adjust an algorithm threshold value or determine an optimization direction of an algorithm model according to the mistaken wake-up and normal wake-up data.
At present, although the voiceprint wake-up log can be collected based on the uploaded work log of the voiceprint wake-up device, the collected voiceprint wake-up log lacks a mark and cannot be directly used for optimization of an algorithm model or adjustment of an algorithm threshold, and the collected voiceprint wake-up log needs to be marked first and then can be used for optimization of the algorithm model or adjustment of the algorithm threshold. In the prior art, two ways of marking a voiceprint wake-up log mainly include marking the voiceprint wake-up log manually, and marking the voiceprint wake-up log by a marking algorithm. The voiceprint awakening logs are marked manually, a large amount of manpower is consumed, efficiency is low, and the requirement for collecting a large amount of voiceprint awakening logs cannot be met. Although the efficiency of marking the voiceprint wake-up log can be improved by marking the voiceprint wake-up log through the marking algorithm, the accuracy of marking the voiceprint wake-up log cannot be guaranteed due to lack of user confirmation.
Disclosure of Invention
The embodiment of the invention provides a method and a device for collecting a wake-up log, which are used for solving the problem that the collected voiceprint wake-up log in the prior art is lack of marks and cannot be directly used for optimization of an algorithm model or adjustment of an algorithm threshold.
In order to solve the above technical problem, the embodiment of the present invention is implemented as follows:
in a first aspect, an embodiment of the present invention provides a method for collecting a voiceprint wake-up log, including:
receiving a voiceprint wake-up input;
performing voiceprint wake-up verification on the voiceprint wake-up input;
under the condition that the voiceprint awakening verification is not passed, acquiring a first receiving result; the first receiving result is that the awakening input is received within a first preset time length, or the awakening input is not received within the first preset time length;
acquiring a second receiving result under the condition that the voiceprint awakening verification is passed; the second receiving result is that an effective control instruction is received within a second preset time length, or the effective control instruction is not received within the second preset time length;
and generating a voiceprint wake-up log, and determining the mark of the voiceprint wake-up log according to the first receiving result or the second receiving result.
In a second aspect, an apparatus for collecting a voiceprint wake-up log is provided, which includes:
a receiving unit for receiving a voiceprint wake-up input;
a verification unit for performing voiceprint wake-up verification on the voiceprint wake-up input;
a first obtaining unit, configured to obtain a first receiving result when the voiceprint wakeup verification fails; the first receiving result is that the awakening input is received within a first preset time length, or the awakening input is not received within the first preset time length;
a second obtaining unit, configured to obtain a second receiving result when the voiceprint wakeup verification passes; the second receiving result is that an effective control instruction is received within a second preset time length, or the effective control instruction is not received within the second preset time length;
the generating unit is used for generating a voiceprint awakening log;
and the marking unit is used for determining the mark of the voiceprint wake-up log according to the first receiving result or the second receiving result.
In a third aspect, a terminal device is provided, which includes: a processor, a memory and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, performs the steps of the voiceprint wake log collection method according to the first aspect.
In a fourth aspect, a computer-readable storage medium is provided, comprising: the computer readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the voiceprint wake log collection method according to the first aspect.
The method for collecting the voiceprint wake-up log includes the steps of firstly conducting voiceprint wake-up verification on a voiceprint wake-up input after the voiceprint wake-up input is received, obtaining a first receiving result that the wake-up input is received within a first preset time period or the wake-up input is not received within the first preset time period under the condition that the voiceprint wake-up verification is not passed, obtaining a second receiving result that an effective control instruction is received within a second preset time period or an effective control instruction is not received within the second preset time period under the condition that the voiceprint wake-up verification is passed, finally generating the voiceprint wake-up log, and determining a mark of the voiceprint wake-up log according to the first receiving result or the second receiving result. According to the embodiment of the invention, the first receiving result or the second receiving result can be obtained according to the passing condition of the voiceprint awakening verification, and the mark of the generated voiceprint awakening log is determined according to the first receiving result or the second receiving result, so that the embodiment of the invention can automatically mark the voiceprint awakening log, the collected voiceprint awakening log is provided with the mark, and the collected voiceprint awakening log can be directly used for optimizing an algorithm model or adjusting an algorithm threshold.
Drawings
Fig. 1 is a flowchart illustrating a first step of a method for collecting a voiceprint wake-up log according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a terminal device supporting voiceprint wake-up according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a second step of a method for collecting a voiceprint wake-up log according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating a third step of the method for collecting a voiceprint wake-up log according to the embodiment of the present invention;
fig. 5 is a first schematic structural diagram of a voiceprint wake-up log collecting device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a voiceprint wake-up log collecting device according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a hardware structure of a terminal device according to an 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 some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
The terms "first" and "second," and the like, in the description and in the claims of the present invention are used for distinguishing between different objects and not for describing a particular order of the objects. For example, the first device and the second device, etc. are for distinguishing different devices, and are not for describing a particular order of the devices.
It should be noted that, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "e.g.," an embodiment of the present invention is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
The terminal equipment in the embodiment of the invention can be intelligent peripheral equipment, mobile terminal equipment or non-mobile terminal equipment. The mobile terminal device may be a terminal device, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted terminal device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), etc.; the non-mobile terminal device may be a Personal Computer (PC), a Television (TV), a teller machine, a self-service machine, or the like, and the embodiment of the present invention is not particularly limited.
The method for collecting the voiceprint wake-up log provided by the embodiment of the invention can be realized by taking the voiceprint wake-up log collecting device as an execution main body and also taking the terminal equipment as the execution main body.
It should be noted that, the apparatus for collecting a voiceprint wakeup log in the embodiment of the present invention may be a terminal device, or may be a functional module or a functional entity built in the terminal device.
An embodiment of the present invention provides a method for collecting a voiceprint wake-up log, as shown in fig. 1, the method for collecting a voiceprint wake-up log includes the following steps S101 to S105:
s101, receiving a voiceprint awakening input.
The voiceprint wake-up input in the embodiment of the invention is voice input, and the voice input can be voice input for waking up the terminal equipment by a user to which the terminal equipment belongs, or input mistakenly input voice input by the user to which the terminal equipment belongs, or input mistakenly input voice input by other users or objects.
And S102, performing voiceprint awakening verification on the voiceprint awakening input.
Illustratively, referring to fig. 2, the terminal device may include: a primary authentication module 21, a secondary authentication module 22, and a voiceprint authentication module 23. The primary verification module 21 runs on a low-power Digital Processor (DSP), and the secondary verification module 22 and the voiceprint verification module 23 run on a Central Processing Unit (CPU) of the terminal device. In the standby state, the primary verification module 21 is always in the activated state, monitors and receives the voice message, and determines whether the received message has a voiceprint wakeup input. The secondary verification module 22 and the voiceprint verification module 23 are started and further perform voiceprint wake-up verification on the voiceprint wake-up input only after the primary verification module 21 determines that the voiceprint wake-up input exists, and when the secondary verification module 22 determines that the voiceprint wake-up input contains a wake-up word and the voiceprint verification module 23 determines that a voiceprint of the voiceprint wake-up input is matched with a preset voiceprint, the voiceprint wake-up verification is determined to pass, and then the terminal device is woken up; if the secondary verification module 22 determines that the voiceprint wake-up input does not include the wake-up word, or if the secondary verification module 22 determines that the voiceprint wake-up input includes the wake-up word, but the voiceprint verification module 23 determines that the voiceprint of the voiceprint wake-up input is not matched with the preset voiceprint, it is determined that the voiceprint wake-up verification fails, and the terminal device is not woken up.
In the above step S102, if the voiceprint wakeup verification fails, the following step S103 is executed; if the voiceprint wakeup verification passes, the following step S104 is executed.
S103, acquiring a first receiving result.
The first receiving result is that the awakening input is received within a first preset time length, or the awakening input is not received within the first preset time length.
Specifically, when the voiceprint wakeup verification fails, a timer may be immediately started, and the duration of the timer may be set to be a first preset duration. Before the timer finishes timing, continuously monitoring whether the awakening input is received again; if the wakeup input is received again before the timer finishes timing, determining that the first result is that the wakeup input is received within the first preset time length, and if the wakeup input is not received after the timer finishes timing, determining that the first result is that the wakeup input is not received within the first preset time length.
For example, the first preset time period may be 15 seconds.
It should be noted that the wake-up input received within the first preset time period may be a voiceprint wake-up input which is input again, or may be a wake-up input in other manners, for example: a wake-up input by a user through a key on the terminal device, or a wake-up input by a user through a specific motion.
And S104, acquiring a second receiving result.
And the second receiving result is that the effective control instruction is received within a second preset time length, or the effective control instruction is not received within the second preset time length.
Specifically, when the voiceprint wakeup verification passes, a timer can be started immediately, and the duration of the timer is set to be a second preset duration. Before the timer finishes timing, continuously monitoring whether an effective control instruction is received; if the effective control instruction is received before the timer finishes timing, determining that the second result is that the effective control instruction is received within a second preset time length, and if the effective control instruction is not received after the timer finishes timing, determining that the second result is that the effective control instruction is not received within the second preset time length.
For example, the second preset time period may be 5 seconds.
The effective control instruction in the embodiment of the present invention refers to a control instruction that can be understood by the terminal device, and includes a control instruction that can be understood by the terminal device but cannot be executed. For example: the terminal device is an intelligent sound box, the control instruction is 'I want to watch the television', the intelligent sound box can understand the intention of the control instruction and control the television to be turned on, but the television which can be controlled by the intelligent sound box does not exist, and in this case, although the terminal device cannot execute the control instruction, the effectiveness of the control instruction is influenced.
And S105, generating a voiceprint wake-up log, and determining the mark of the voiceprint wake-up log according to the first receiving result or the second receiving result.
It should be noted that, the method for collecting a voiceprint wake-up log according to the embodiment of the present invention may further configure, based on a user requirement, whether the terminal device performs the voiceprint wake-up log collection, if the terminal device is configured to perform the voiceprint wake-up log collection, the method for collecting a voiceprint wake-up log according to the embodiment is executed, and if the terminal device is configured not to perform the voiceprint wake-up log collection, the terminal device responds to a voiceprint wake-up input and executes a control instruction, but does not perform the voiceprint wake-up log collection.
The method for collecting the voiceprint wake-up log includes the steps of performing voiceprint wake-up verification on a voiceprint wake-up input after the voiceprint wake-up input is received, acquiring a first receiving result that the wake-up input is received within a first preset time period or the wake-up input is not received within the first preset time period under the condition that the voiceprint wake-up verification is not passed, acquiring a second receiving result that an effective control instruction is received within a second preset time period or an effective control instruction is not received within the second preset time period under the condition that the voiceprint wake-up verification is passed, generating the voiceprint wake-up log, and determining a mark of the voiceprint wake-up log according to the first receiving result or the second receiving result. According to the embodiment of the invention, the first receiving result or the second receiving result can be obtained according to the passing condition of the voiceprint awakening verification, and the mark of the generated voiceprint awakening log is determined according to the first receiving result or the second receiving result, so that the embodiment of the invention can automatically mark the voiceprint awakening log, the collected voiceprint awakening log is provided with the mark, and the collected voiceprint awakening log can be directly used for optimizing an algorithm model or adjusting an algorithm threshold.
A detailed description is given below of a specific implementation manner and a principle of the step S105 (generating the voiceprint wake-up log and determining the mark of the voiceprint wake-up log according to the first receiving result or the second receiving result). Referring to fig. 3, generating a voiceprint wake-up log and determining a mark of the voiceprint wake-up log according to a first receiving result or a second receiving result includes:
the first method,
In case that the first receiving result is that the wakeup input is received within the first preset time period, the following step S301 is performed.
S301, generating a voiceprint wake-up log, and determining that the mark of the voiceprint wake-up log is a first mark.
Wherein the first mark is used for marking a voiceprint wake-up log which is about to wake up the terminal device but is not successfully woken up the terminal device.
Generally, when a user wants to wake up a terminal device, if a voiceprint wake-up input is input into the terminal device but the terminal device is not successfully woken up, the user may wake up the terminal device again in the same manner or another manner in a short time. In the above embodiment, the terminal device receives a voiceprint wake-up input which does not pass the voiceprint wake-up verification first, and then receives another wake-up input within a first preset time length (a short time), so that the first received voiceprint wake-up input is likely to be the voiceprint wake-up input which the user wants to wake up the terminal device but fails to pass the voiceprint wake-up verification, and thus the mark of the voiceprint wake-up log is determined to be the first mark.
The algorithm model can be optimized or the algorithm threshold can be adjusted based on the voiceprint wake-up log marked as the first mark, so that the voiceprint wake-up input can be verified more easily through voiceprint wake-up.
The second method,
If the first receiving result is that the wake-up input is not received within the first preset time period, the following step S302 is performed.
S302, generating a voiceprint wake-up log, and determining that the mark of the voiceprint wake-up log is a second mark.
And the second mark is used for marking the mistaken awakening voiceprint awakening log which fails in the voiceprint awakening verification.
Similarly, when the user wants to wake up the terminal device, if the voiceprint wake-up input is input to the terminal device but the terminal device is not successfully woken up, the user may wake up the terminal device again in the same manner or another manner within a short time. In the above embodiment, when the terminal device receives a voiceprint wake-up input that fails the voiceprint wake-up verification, the terminal device is successfully woken up, but the user does not continue to wake up the terminal device, so that the received voiceprint wake-up input is likely to be a sound that is made by the user to whom the terminal device belongs and does not include a wake-up word by mistake, or a sound made by another user or an object by mistake is determined as the voiceprint wake-up input, and therefore the mark of the voiceprint wake-up log is determined as the second mark.
The algorithm model can be optimized or the algorithm threshold value can be adjusted based on the voiceprint awakening log marked as the second mark, so that the identification of voiceprint awakening input is stricter, the verification of awakening words and voiceprints is prevented from being frequently started, and the power consumption of the terminal equipment is further saved.
The third method,
In a case where the second reception result is that the valid control instruction is received within the second preset time period, the following step S303 is executed.
S303, generating a voiceprint wake-up log, and determining that the mark of the voiceprint wake-up log is a third mark.
And the third mark is used for marking a voiceprint awakening log of the normal awakening terminal equipment.
Generally, after a user successfully wakes up a terminal device, the user inputs a control instruction to the terminal device, and if the terminal device is successfully woken up but the control instruction input by the user is not received within a period of time, the terminal device is likely to be woken up by mistake. In the above embodiment, the voiceprint wake-up input passes the voiceprint wake-up verification, the terminal device is successfully woken up, and an effective control instruction is received within a second preset time duration, so that the mark of the voiceprint wake-up log is determined as the third mark.
The fourth way,
If the second receiving result is that no valid control instruction is received within the second preset time period, the following step S304 is executed.
S304, generating a voiceprint wake-up log, and determining that the mark of the voiceprint wake-up log is a fourth mark.
And the fourth mark is used for marking the mistaken awakening voiceprint awakening log which passes the voiceprint awakening verification.
Similarly, after the user successfully wakes up the terminal device, the user will input a control command to the terminal device, and if the terminal device is successfully woken up but the control command input by the user is not received within a period of time, the terminal device is likely to be woken up by mistake. In the above embodiment, the voiceprint wake-up input passes the voiceprint wake-up verification, the terminal device is successfully woken up, but no valid control instruction is received within the second preset time duration, so that the mark of the voiceprint wake-up log is determined to be the fourth mark.
The algorithm model can be optimized or the algorithm threshold can be adjusted based on the voiceprint wake-up log marked as the fourth mark, so that voiceprint wake-up verification is stricter, frequent wake-up of the terminal device is avoided, power consumption of the terminal device is saved, and user experience is improved.
As an optional implementation manner of the embodiment of the present invention, on the basis of the above embodiment, the method for collecting a voiceprint wake-up log according to the embodiment of the present invention further includes: uploading the collected voiceprint awakening log. Referring to fig. 4, a flow of a method for uploading a collected voiceprint wake-up log includes:
s401, determining whether the current network state is a preset network state.
Optionally, the preset network state may be at least one of access to WIFI, access to a mobile network, and network signal quality reaching a threshold network signal quality.
In the above step S401, if it is determined that the current network status is the preset network status, the following step S402 is executed, and if it is determined that the current network status is not the preset network status, the following step S403 and the following steps are executed.
S402, uploading all the locally stored voiceprint awakening logs and the marks of the voiceprint awakening logs, and deleting the uploaded voiceprint awakening logs and the marks of the voiceprint awakening logs.
And S403, judging whether the number of the locally stored voiceprint wake-up logs is larger than a preset threshold value.
In the above step S403, if the number of the locally stored voiceprint wake-up logs is greater than the preset threshold, the following step S404 is executed, and if the number of the locally stored voiceprint wake-up logs is less than or equal to the preset threshold, it may be determined that the storage of the voiceprint wake-up logs does not occupy too much storage space, and the voiceprint wake-up logs do not need to be processed.
S404, deleting the voiceprint awakening log with the earliest time stamp in the locally stored voiceprint awakening logs.
When the number of the locally stored voiceprint awakening logs is larger than a preset threshold value, the voiceprint awakening log with the earliest timestamp in the locally stored voiceprint awakening logs is deleted, so that the condition that the storage space is occupied due to the excessive storage of the voiceprint awakening logs can be avoided, and the condition that the collection of the voiceprint awakening logs influences the performance of the terminal equipment is further avoided.
Based on the same inventive concept, as an implementation of the above method, an embodiment of the present invention further provides a voiceprint wake-up log collection device that executes the voiceprint wake-up log collection method provided in the above method embodiment, where this embodiment corresponds to the foregoing method embodiment, and for convenience of reading, details in the foregoing method embodiment are not described again in this embodiment one by one, but it should be clear that the voiceprint wake-up log collection device in this embodiment can correspondingly implement all contents in the foregoing method embodiment.
Fig. 5 is a schematic structural diagram of a voiceprint wake-up log collecting device according to an embodiment of the present invention, and referring to fig. 5, a voiceprint wake-up log collecting device 500 according to an embodiment of the present invention includes:
a receiving unit 51 for receiving a voiceprint wake-up input;
a verification unit 52 that performs voiceprint wake-up verification on the voiceprint wake-up input;
a first obtaining unit 53, configured to obtain a first receiving result when the voiceprint wakeup verification fails; the first receiving result is that the awakening input is received within a first preset time length or the awakening input is not received within the first preset time length;
a second obtaining unit 54, configured to obtain a second receiving result when the voiceprint wake-up verification passes; the second receiving result is that the effective control instruction is received within a second preset time length, or the effective control instruction is not received within the second preset time length;
a generating unit 55, configured to generate a voiceprint wake-up log;
and a marking unit 56, configured to determine a mark of the voiceprint wake-up log according to the first reception result or the second reception result.
As an optional implementation manner of the embodiment of the present invention, the marking unit 56 is specifically configured to determine that the mark of the voiceprint wake-up log is a first mark when the first receiving result is that the wake-up input is received within a first preset time period;
wherein the first mark is used for marking a voiceprint wake-up log which is about to wake up the terminal device but is not successfully woken up the terminal device.
As an optional implementation manner of the embodiment of the present invention, the marking unit 56 is specifically configured to determine that the mark of the voiceprint wake-up log is the second mark when the first receiving result is that the wake-up input is not received within the first preset time period;
and the second mark is used for marking the mistaken awakening voiceprint awakening log which fails in the voiceprint awakening verification.
As an optional implementation manner of the embodiment of the present invention, the marking unit 56 is specifically configured to determine that the mark of the voiceprint wake-up log is a third mark when the second receiving result is that an effective control instruction is received within a second preset time period;
and the third mark is used for marking a voiceprint awakening log of the normal awakening terminal equipment.
As an optional implementation manner of the embodiment of the present invention, the marking unit 56 is specifically configured to determine that the mark of the voiceprint wake-up log is a fourth mark when the second receiving result is that an effective control instruction is not received within a second preset time period;
and the fourth mark is used for marking the mistaken awakening voiceprint awakening log which passes the voiceprint awakening verification.
As an optional implementation manner of the embodiment of the present invention, referring to fig. 6, the apparatus 500 for collecting a voiceprint wake-up log further includes:
the processing unit 57 is configured to determine whether the current network state is the preset network state after generating the voiceprint wake-up log and determining the mark of the voiceprint wake-up log according to the first receiving result or the second receiving result;
a sending unit 58, configured to upload all locally stored voiceprint wake-up logs and marks of the voiceprint wake-up logs when it is determined that the current network state is the preset network state;
and a deleting unit 59 configured to delete the uploaded voiceprint wake log and the mark of the voiceprint wake log.
As an optional implementation manner of the embodiment of the present invention, the processing unit 57 is further configured to, when it is determined that the current network state is not the preset network state, determine whether the number of locally stored voiceprint wake-up logs is greater than a preset threshold;
the deleting unit 59 is further configured to delete the voiceprint wake-up log with the earliest timestamp from the locally stored voiceprint wake-up logs in the case that the number of the locally stored voiceprint wake-up logs is greater than a preset threshold.
The apparatus for collecting a voiceprint wake-up log according to the embodiments of the present invention, after receiving a voiceprint wake-up input through a receiving unit, performs a voiceprint wake-up verification on the voiceprint wake-up input through a verifying unit, and under a condition that the voiceprint wake-up verification fails, obtains a first receiving result indicating that the wake-up input is received within a first preset time period or that the wake-up input is not received within the first preset time period through a first obtaining unit, and under a condition that the voiceprint wake-up verification passes, obtains a second receiving result indicating that an effective control instruction is received within a second preset time period or that an effective control instruction is not received within the second preset time period through a second obtaining unit, and finally generates the voiceprint wake-up log, and a marking unit determines a mark of the voiceprint wake-up log according to the first receiving result or the second receiving result. According to the embodiment of the invention, the first receiving result or the second receiving result can be obtained according to the passing condition of the voiceprint awakening verification, and the mark of the generated voiceprint awakening log is determined according to the first receiving result or the second receiving result, so that the embodiment of the invention can automatically mark the voiceprint awakening log, the collected voiceprint awakening log is provided with the mark, and the collected voiceprint awakening log can be directly used for optimizing an algorithm model or adjusting an algorithm threshold.
Fig. 7 is a schematic diagram of a hardware structure of a terminal device for implementing various embodiments of the present invention, as shown in fig. 7, the terminal device 700 includes, but is not limited to: radio Frequency (RF) circuit 710, memory 720, input unit 730, display unit 740, sensor 750, audio circuit 760, wireless fidelity (WiFi) module 770, processor 780, and power supply 790. Therein, the radio frequency circuit 710 includes a receiver 710 and a transmitter 712. Those skilled in the art will appreciate that the terminal device configuration shown in fig. 7 does not constitute a limitation of the terminal device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The RF circuit 710 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, receives downlink information of a base station and then processes the received downlink information to the processor 780; in addition, data for designing uplink is transmitted to the base station. In general, the RF circuit 710 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, the RF circuitry 710 may also communicate with networks and other devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to global system for mobile communications (GSM), general Packet Radio Service (GPRS), code Division Multiple Access (CDMA), wideband Code Division Multiple Access (WCDMA), long Term Evolution (LTE), email, short Message Service (SMS), etc.
The memory 720 may be used to store software programs and modules, and the processor 780 may execute various functional applications of the terminal device and data processing by operating the software programs and modules stored in the memory 720. The memory 720 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the terminal device, and the like. Further, the memory 720 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The input unit 730 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the terminal device. Specifically, the input unit 730 may include a touch panel 731 and other input devices 732. The touch panel 731, also called a touch screen, can collect touch operations of a user (e.g. operations of the user on or near the touch panel 731 by using any suitable object or accessory such as a finger, a stylus, etc.) thereon or nearby, and drive the corresponding connection device according to a preset program. Alternatively, the touch panel 731 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts it to touch point coordinates, and sends the touch point coordinates to the processor 780, and can receive and execute commands from the processor 780. In addition, the touch panel 731 may be implemented by various resistive, capacitive, infrared, and surface acoustic wave. The input unit 730 may include other input devices 732 in addition to the touch panel 731. In particular, other input devices 732 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.
The display unit 740 may be used to display information input by the user or information provided to the user and various menus of the terminal device. The display unit 740 may include a display panel 741, and optionally, the display panel 741 may be configured in the form of a Liquid Crystal Display (LCD), an organic light-Emitting diode (OLED), or the like. Further, the touch panel 731 can cover the display panel 741, and when the touch panel 731 detects a touch operation on or near the touch panel 731, the touch operation is transmitted to the processor 780 to determine a touch event, and then the processor 780 provides a corresponding visual output on the display panel 741 according to the touch event. Although in fig. 7, the touch panel 731 and the display panel 741 are two independent components to implement the input and output functions of the terminal device, in some embodiments, the touch panel 731 and the display panel 741 may be integrated to implement the input and output functions of the terminal device.
The terminal device may also include at least one sensor 750, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 741 according to the brightness of ambient light, and a proximity sensor that may turn off the display panel 741 and/or a backlight when the terminal device is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), detect the magnitude and direction of gravity when stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer and tapping), and the like, for recognizing the attitude of the terminal device; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured in the terminal device, detailed description is omitted here. In the embodiment of the present invention, the terminal device may include an acceleration sensor, a depth sensor, a distance sensor, or the like.
WiFi belongs to a short-distance wireless transmission technology, and the terminal equipment can help a user to receive and send emails, browse webpages, access streaming media and the like through the WiFi module 770, and provides wireless broadband internet access for the user. Although fig. 7 shows the WiFi module 770, it is understood that it does not belong to the essential constitution of the terminal device, and may be omitted entirely as needed within the scope not changing the essence of the invention.
The processor 780 is a control center of the terminal device, connects various parts of the entire terminal device using various interfaces and lines, and performs various functions of the terminal device and processes data by operating or executing software programs and/or modules stored in the memory 720 and calling data stored in the memory 720, thereby integrally monitoring the terminal device. Optionally, processor 780 may include one or more processing units; preferably, the processor 780 may integrate an application processor, which primarily handles operating system, user interface, application programs, etc. and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 780.
The terminal device also includes a power supply 790 (e.g., a battery) for powering the various components, which may preferably be logically coupled to the processor 780 via a power management system to manage charging, discharging, and power consumption management functions via the power management system. Although not shown, the terminal device may further include a camera, a bluetooth module, and the like, which are not described herein.
In an embodiment of the present invention, the microphone 762 is specifically configured to receive a voiceprint wake-up input; processor 780 is configured to perform a voiceprint wake-up verification on the voiceprint wake-up input; the microphone 762 is further configured to obtain a first reception result if the processor 780 determines that the voiceprint wake-up verification is not passed, and obtain a second reception result if the processor 780 determines that the voiceprint wake-up verification is passed; processor 780 is further configured to generate a voiceprint wake-up log and determine a flag of the voiceprint wake-up log according to the first reception result or the second reception result;
the first receiving result is that the awakening input is received within a first preset time length or the awakening input is not received within the first preset time length; the second receiving result is that the effective control instruction is received within the second preset time length, or the effective control instruction is not received within the second preset time length.
As an optional implementation manner of the embodiment of the present invention, the processor 780 is specifically configured to determine, when the first receiving result is that the wakeup input is received within a first preset time period, that the mark of the voiceprint wakeup log is a first mark;
wherein the first mark is used for marking a voiceprint wake-up log which is about to wake up the terminal device but is not successfully woken up the terminal device.
As an optional implementation manner of the embodiment of the present invention, the processor 780 is specifically configured to determine that the mark of the voiceprint wake-up log is the second mark when the first receiving result is that the wake-up input is not received within the first preset time period;
and the second mark is used for marking the mistaken awakening voiceprint awakening log which fails in the voiceprint awakening verification.
As an optional implementation manner of the embodiment of the present invention, the processor 780 is specifically configured to determine that the mark of the voiceprint wake-up log is a third mark when the second receiving result is that an effective control instruction is received within a second preset time period;
and the third mark is used for marking a voiceprint awakening log of the normal awakening terminal equipment.
As an optional implementation manner of the embodiment of the present invention, the processor 780 is specifically configured to determine that the mark of the voiceprint wake-up log is a fourth mark when the second receiving result is that an effective control instruction is not received within a second preset time period;
and the fourth mark is used for marking the mistaken awakening voiceprint awakening log which passes the voiceprint awakening verification.
As an optional implementation manner of the embodiment of the present invention, the radio frequency circuit 710 is specifically configured to, after generating a voiceprint wake-up log and determining a mark of the voiceprint wake-up log according to the first receiving result or the second receiving result, determine whether a current network state is a preset network state, and upload all locally stored voiceprint wake-up logs and marks of the voiceprint wake-up log under the condition that the current network state is determined to be the preset network state;
the memory 720 is specifically configured to delete the uploaded voiceprint wake logs and the tags of the voiceprint wake logs.
As an optional implementation manner of the embodiment of the present invention, the processor 780 and the radio frequency circuit 77 are further configured to, under the condition that it is determined that the current network state is not the preset network state, determine whether the number of locally stored voiceprint wake-up logs is greater than a preset threshold;
the memory 720 is further configured to delete the voiceprint wake-up log with the earliest timestamp in the locally stored voiceprint wake-up logs under the condition that the number of the locally stored voiceprint wake-up logs is greater than a preset threshold.
An embodiment of the present invention further provides a terminal device, where the terminal device may include: the processor, the memory and the computer program stored in the memory and capable of running on the processor, when being executed by the processor, the computer program can implement the method for collecting the voiceprint wake-up log provided by the above method embodiment, and can achieve the same technical effect, and in order to avoid repetition, the details are not repeated here.
An embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method for collecting a voiceprint wake-up log provided in the foregoing method embodiment is implemented.
The first device, the second device, and the storage medium provided in the embodiment of the present invention may achieve the same technical effects as the method for collecting the voiceprint wake-up log provided in the above embodiment of the method, and for avoiding repetition, the technical effects are not described herein again.
The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one of 8230, and" comprising 8230does not exclude the presence of additional like elements in a process, method, article, or apparatus comprising the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the particular illustrative embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but is intended to cover various modifications, equivalent arrangements, and equivalents thereof, which may be made by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A voiceprint wake-up log collection method, comprising:
receiving a voiceprint wake-up input;
performing voiceprint wake-up verification on the voiceprint wake-up input;
under the condition that the voiceprint awakening verification is not passed, acquiring a first receiving result; the first receiving result is that the awakening input is received within a first preset time length, or the awakening input is not received within the first preset time length;
acquiring a second receiving result under the condition that the voiceprint awakening verification is passed; the second receiving result is that an effective control instruction is received within a second preset time length, or the effective control instruction is not received within the second preset time length;
generating a voiceprint wake-up log, and determining a mark of the voiceprint wake-up log according to the first receiving result or the second receiving result;
the generating a voiceprint wake-up log and determining a mark of the voiceprint wake-up log according to the first receiving result or the second receiving result includes:
and generating a voiceprint awakening log under the condition that the first receiving result is that the awakening input is not received within a first preset time length, and determining that the mark of the voiceprint awakening log is a second mark, wherein the second mark is used for marking the mistakenly awakened voiceprint awakening log which is not passed by the voiceprint awakening verification.
2. The method of claim 1, wherein generating the voiceprint wake-up log and determining the label of the voiceprint wake-up log according to the first reception result or the second reception result comprises:
generating a voiceprint wake-up log under the condition that the first receiving result is that a wake-up input is received within a first preset time length, and determining that the voiceprint wake-up log is marked as a first mark;
wherein the first mark is used for marking a voiceprint wake-up log which is about to wake up the terminal equipment but is not successful in waking up the terminal equipment.
3. The method of claim 1, wherein generating the voiceprint wake-up log and determining the label of the voiceprint wake-up log according to the first reception result or the second reception result comprises:
generating a voiceprint wake-up log under the condition that the second receiving result is that an effective control instruction is received within a second preset time length, and determining that the voiceprint wake-up log is marked as a third mark;
and the third mark is used for marking a voiceprint awakening log of the normal awakening terminal equipment.
4. The method of claim 1, wherein generating the voiceprint wake-up log and determining the label of the voiceprint wake-up log according to the first reception result or the second reception result comprises:
generating a voiceprint wake-up log under the condition that the second receiving result is that no effective control instruction is received within a second preset time, and determining that the mark of the voiceprint wake-up log is a fourth mark;
and the fourth mark is used for marking the mistaken awakening voiceprint awakening log which passes the voiceprint awakening verification.
5. The method according to any of claims 1-4, wherein after generating a voiceprint wake-up log and determining the signature of the voiceprint wake-up log from the first received result or the second received result, the method further comprises:
determining whether the current network state is a preset network state;
if yes, uploading all the marks of the voiceprint awakening logs and the voiceprint awakening logs stored locally, and deleting the marks of the uploaded voiceprint awakening logs and the voiceprint awakening logs.
6. The method of claim 5, further comprising:
if the current network state is determined not to be the preset network state, judging whether the number of the locally stored voiceprint wake-up logs is larger than a preset threshold value or not;
and if the number of the locally stored voiceprint awakening logs is larger than a preset threshold value, deleting the voiceprint awakening log with the earliest timestamp in the locally stored voiceprint awakening logs.
7. A voiceprint wake-up log collection device, comprising:
a receiving unit for receiving a voiceprint wake-up input;
a verification unit for performing voiceprint wake-up verification on the voiceprint wake-up input;
a first obtaining unit, configured to obtain a first receiving result when the voiceprint wakeup verification fails; the first receiving result is that the awakening input is received within a first preset time length, or the awakening input is not received within the first preset time length;
a second obtaining unit, configured to obtain a second receiving result when the voiceprint wake-up verification passes; the second receiving result is that an effective control instruction is received within a second preset time length, or the effective control instruction is not received within the second preset time length;
the generating unit is used for generating a voiceprint wake-up log;
a marking unit, configured to determine a mark of the voiceprint wake-up log according to the first reception result or the second reception result;
the marking unit is specifically configured to determine that the mark of the voiceprint wake-up log is a second mark when the first receiving result is that no wake-up input is received within a first preset time, where the second mark is used to mark a false wake-up voiceprint wake-up log in which the voiceprint wake-up verification fails.
8. A terminal device, comprising: processor, memory and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the voiceprint wake log collection method according to any one of claims 1 to 6.
9. A computer-readable storage medium, comprising: the computer readable storage medium has stored thereon a computer program which, when executed by a processor, carries out the steps of the voiceprint wake log collection method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010659084.5A CN111880988B (en) | 2020-07-09 | 2020-07-09 | Voiceprint wake-up log collection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010659084.5A CN111880988B (en) | 2020-07-09 | 2020-07-09 | Voiceprint wake-up log collection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111880988A CN111880988A (en) | 2020-11-03 |
| CN111880988B true CN111880988B (en) | 2022-11-04 |
Family
ID=73150980
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010659084.5A Active CN111880988B (en) | 2020-07-09 | 2020-07-09 | Voiceprint wake-up log collection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111880988B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112499016A (en) * | 2020-11-17 | 2021-03-16 | 苏州中科先进技术研究院有限公司 | Garbage recycling method and device of intelligent garbage can and intelligent garbage can |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815507A (en) * | 2015-11-30 | 2017-06-09 | 中兴通讯股份有限公司 | Voice wakes up implementation method, device and terminal |
| CN108335696A (en) * | 2018-02-09 | 2018-07-27 | 百度在线网络技术（北京）有限公司 | Voice awakening method and device |
| CN110570861A (en) * | 2019-09-24 | 2019-12-13 | Oppo广东移动通信有限公司 | method and device for voice wake-up, terminal equipment and readable storage medium |
| CN110634468A (en) * | 2019-09-11 | 2019-12-31 | 中国联合网络通信集团有限公司 | Voice wake-up method, device, equipment and computer readable storage medium |
| CN111210817A (en) * | 2019-12-30 | 2020-05-29 | 深圳市优必选科技股份有限公司 | Data processing method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11074912B2 (en) * | 2018-10-23 | 2021-07-27 | Polycom, Inc. | Identifying a valid wake input |
-
2020
- 2020-07-09 CN CN202010659084.5A patent/CN111880988B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815507A (en) * | 2015-11-30 | 2017-06-09 | 中兴通讯股份有限公司 | Voice wakes up implementation method, device and terminal |
| CN108335696A (en) * | 2018-02-09 | 2018-07-27 | 百度在线网络技术（北京）有限公司 | Voice awakening method and device |
| CN110634468A (en) * | 2019-09-11 | 2019-12-31 | 中国联合网络通信集团有限公司 | Voice wake-up method, device, equipment and computer readable storage medium |
| CN110570861A (en) * | 2019-09-24 | 2019-12-13 | Oppo广东移动通信有限公司 | method and device for voice wake-up, terminal equipment and readable storage medium |
| CN111210817A (en) * | 2019-12-30 | 2020-05-29 | 深圳市优必选科技股份有限公司 | Data processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111880988A (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102354275B1 (en) | Speech recognition method and apparatus, and storage medium | |
| CN108712566B (en) | Voice assistant awakening method and mobile terminal | |
| CN110300970B (en) | Unlocking control method and related product | |
| CN106293308B (en) | Screen unlocking method and device | |
| CN107194224B (en) | Unlocking control method and related product | |
| CN107015703B (en) | Unlocking control method and related product | |
| WO2017008569A1 (en) | Message updating method, apparatus, and terminal | |
| CN107025399B (en) | Unlocking control method and related product | |
| CN108322599B (en) | Network access method and mobile terminal | |
| CN107172267B (en) | Fingerprint identification control method and related product | |
| CN108391008B (en) | Message reminding method and mobile terminal | |
| CN106445596B (en) | Method and device for managing setting items | |
| CN107193473B (en) | Unlocking control method and related product | |
| CN107734170B (en) | Notification message processing method, mobile terminal and wearable device | |
| CN111130989A (en) | Information display and sending method and electronic equipment | |
| CN107291280B (en) | Method and device for adjusting sensitivity of touch screen and terminal equipment | |
| CN107066090B (en) | Method for controlling fingerprint identification module and mobile terminal | |
| CN107194223B (en) | Fingerprint identification area display method and related product | |
| CN109639370B (en) | Near field communication antenna detection method and device, mobile terminal and storage medium | |
| CN111880988B (en) | Voiceprint wake-up log collection method and device | |
| WO2016172878A1 (en) | Terminal control method and apparatus, and terminal device | |
| CN106507357B (en) | Access control method and terminal equipment | |
| CN110277097B (en) | Data processing method and related equipment | |
| CN108170360B (en) | Control method of gesture function and mobile terminal | |
| CN107194226B (en) | Unlocking control method and related product |
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 |