CN109859774B - Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium - Google Patents
Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium Download PDFInfo
- Publication number
- CN109859774B CN109859774B CN201910002054.4A CN201910002054A CN109859774B CN 109859774 B CN109859774 B CN 109859774B CN 201910002054 A CN201910002054 A CN 201910002054A CN 109859774 B CN109859774 B CN 109859774B
- Authority
- CN
- China
- Prior art keywords
- voice
- detection sensitivity
- endpoint detection
- user
- time
- 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
Abstract
The invention provides a voice device and an endpoint detection sensitivity adjusting method, a device and a storage medium thereof, wherein the method comprises the following steps: acquiring the awakening time when the user successfully awakens the voice equipment each time; analyzing the use habit of the user on the voice equipment according to the awakening time when the user successfully awakens the voice equipment each time; setting an adjusting strategy of voice endpoint detection sensitivity of the voice equipment according to the use habit of the user to the voice equipment; and adjusting the voice endpoint detection sensitivity of the voice equipment according to the adjusting strategy. The scheme provided by the invention can adaptively adjust the sensitivity of voice endpoint detection according to the use habit of the voice equipment of a user in the state of waiting to be awakened of the voice equipment, thereby avoiding meaningless voice processing.
Description
Technical Field
The present invention relates to the field of control, and in particular, to a voice device, a method and an apparatus for adjusting endpoint detection sensitivity thereof, and a storage medium.
Background
The problem of high noise exists in the remote voice recognition process, and because environmental sound needs to be detected at any time and semantics needs to be recognized, a voice endpoint detection algorithm and a set awakening word are adopted to reduce the misrecognition rate. Voice Activity Detection (VAD), i.e. segmenting the part of valid Voice (i.e. the Voice of a person speaking) from a continuous Voice stream from outside noise or silence, reduces the amount of stored or transmitted data, so as to reduce the computational load of the device and realize fast Voice recognition. The awakening word means that the device needs to be awakened through a preset awakening word before voice control so as to avoid error control, such as 'tianmaoling', 'xiaoauchi classmate', 'grief and the like'. Under the daily use environment, the voice endpoint detection sensitivity in the existing state to be awakened is constant and cannot be adjusted in a self-adaptive manner, which is unreasonable. Since the frequency of use of the device by the user is different at different time periods, i.e. the frequency of wake-up of the device by the user is different at different time periods, if the same endpoint detection sensitivity is set, unnecessary power consumption is wasted.
Disclosure of Invention
The present invention is directed to overcome the drawbacks of the prior art, and provides a voice device, and a method, an apparatus and a storage medium for adjusting endpoint detection sensitivity thereof, so as to solve the problem in the prior art that unnecessary power consumption is wasted when the same endpoint detection sensitivity is set for all time segments during voice endpoint detection in a to-be-woken state.
One aspect of the present invention provides a method for adjusting endpoint detection sensitivity of a voice device, including: acquiring the awakening time when the user successfully awakens the voice equipment each time; analyzing the use habit of the user on the voice equipment according to the awakening time when the user successfully awakens the voice equipment each time; setting an adjusting strategy of voice endpoint detection sensitivity of the voice equipment according to the use habit of the user to the voice equipment; and adjusting the voice endpoint detection sensitivity of the voice equipment according to the adjusting strategy.
Optionally, analyzing the usage habit of the user on the voice device according to the wake-up time of the user when the user successfully wakes up the voice device each time includes: and analyzing the awakening probability of the user to the voice equipment in each time period in a plurality of preset time periods according to the awakening time when the user successfully awakens the voice equipment each time.
Optionally, setting an adjustment policy of voice endpoint detection sensitivity of the voice device according to the usage habit of the user on the voice device includes: and respectively setting voice endpoint detection sensitivities corresponding to a plurality of preset time periods according to the awakening probability of the user to the voice equipment in each of the plurality of preset time periods.
Optionally, adjusting the voice endpoint detection sensitivity of the voice device according to the adjustment policy includes: determining a first time period of the current time in the plurality of preset time periods; acquiring first voice endpoint detection sensitivity corresponding to the first time period according to the adjusting strategy; and setting the first voice endpoint detection sensitivity as the current voice endpoint detection sensitivity of the voice equipment.
Optionally, the plurality of preset time periods include: daily on a weekly basis and/or multiple periods of each day.
Another aspect of the present invention provides an apparatus for adjusting endpoint detection sensitivity of a voice device, including: the acquiring unit is used for acquiring the awakening time when the user successfully awakens the voice equipment each time; the analysis unit is used for analyzing the use habit of the user on the voice equipment according to the awakening time when the user successfully awakens the voice equipment each time; the setting unit is used for setting an adjusting strategy of the voice endpoint detection sensitivity of the voice equipment according to the use habit of the user to the voice equipment; and the adjusting unit is used for adjusting the voice endpoint detection sensitivity of the voice equipment according to the adjusting strategy.
Optionally, the analyzing unit analyzes the usage habit of the user on the voice device according to the wake-up time of the user when the user successfully wakes up the voice device each time, and includes: and analyzing the awakening probability of the user to the voice equipment in each time period in a plurality of preset time periods according to the awakening time when the user successfully awakens the voice equipment each time.
Optionally, the setting unit, configured to set an adjustment policy of voice endpoint detection sensitivity of the voice device according to a usage habit of the user on the voice device, includes: and respectively setting voice endpoint detection sensitivity corresponding to each time period in a plurality of preset time periods according to the awakening probability of the user to the voice equipment in each time period in the plurality of preset time periods.
Optionally, the adjusting unit includes: the determining subunit is used for determining a first time period of the current time in the plurality of preset time periods; the acquisition subunit is configured to acquire, according to the adjustment policy, a first voice endpoint detection sensitivity corresponding to the first time period; and the setting subunit is used for setting the first voice endpoint detection sensitivity as the current voice endpoint detection sensitivity of the voice equipment.
Optionally, the plurality of preset time periods include: daily on a weekly basis and/or multiple periods of each day.
A further aspect of the invention provides a storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the methods described above.
A further aspect of the invention provides a speech device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods described above when executing the program.
The invention further provides a voice device, which comprises the endpoint detection sensitivity adjusting device of any one of the voice devices.
According to the technical scheme of the invention, the voice equipment endpoint detection sensitivity self-adaptive adjustment strategy is set based on the use habit of the user on the voice equipment, so that the voice endpoint detection sensitivity can be self-adaptively adjusted according to the use habit of the user in the state that the voice equipment is to be awakened; and, through the time of statistics user awakening voice device, gather the user and to voice device's awakening frequency at different time quantums to the analysis user is to voice device's use habit, thereby, when using voice device not often, reduces pronunciation endpoint detection sensitivity, when often using this equipment, improves pronunciation endpoint detection sensitivity, avoids meaningless speech processing.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic method diagram of an embodiment of an endpoint detection sensitivity adjustment method for a speech device according to the present invention;
FIG. 2 is a histogram of the number of wake-up probabilities that a user wakes up the preset device every preset period of time every day for seven days per week, according to an embodiment of the present invention;
FIG. 3 is a pie chart of wake-up probabilities for multiple periods of the day according to an embodiment of the invention;
FIG. 4 is a pie chart of the wake-up probability for a user to wake up the voice device each day for seven days per week in accordance with an embodiment of the present invention;
FIG. 5 is a flowchart illustrating an embodiment of the step of adjusting the voice endpoint detection sensitivity of the voice device according to the adjustment policy according to the embodiment of the present invention;
fig. 6 is a schematic structural diagram of an embodiment of an endpoint detection sensitivity adjustment apparatus for a speech device provided in the present invention;
fig. 7 is a schematic structural diagram of an embodiment of an adjusting unit according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the specific embodiments of the present invention and the accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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 should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 is a schematic method diagram of an embodiment of an endpoint detection sensitivity adjustment method for a speech device according to the present invention.
As shown in fig. 1, according to an embodiment of the present invention, the method for adjusting the endpoint detection sensitivity of the voice device at least includes step S110, step S120, step S130 and step S140.
Step S110, obtaining the awakening time when the user awakens the voice equipment each time.
The voice equipment can be equipment already distributed with a network, and the networking state is kept. And when the user successfully awakens the voice equipment each time, acquiring and recording the awakening time when the user successfully awakens the voice equipment. Preferably, the wake-up time of the user at each time of waking up the voice device within a first preset time is obtained, for example, the wake-up time of the user at each time of waking up the voice device within one month or one quarter is obtained.
Step S120, analyzing the use habit of the user to the voice equipment according to the awakening time when the user awakens the voice equipment each time.
Specifically, according to the wake-up time of the user when the user successfully wakes up the voice device each time, the wake-up probability of the user on the voice device in each of a plurality of preset time periods is analyzed. More specifically, the awakening times of the voice device successfully awakened by the user in each preset time period in the plurality of preset time periods are respectively counted, and the awakening probability of the user on the voice device in each preset time period is determined according to the awakening times of the voice device successfully awakened by the user in each preset time period and the total times of the voice device successfully awakened by the user. The preset time periods may specifically include: daily on a weekly basis and/or multiple periods of each day.
For example, the number of awakening times that the user successfully awakens the voice device in each of a plurality of preset periods of each day in seven days per week is respectively counted, for example, one day is divided into four periods of 8:00-12:00,12:00-18:00, 18:00-23:00 and 23:00-8:00, and the number of awakening times that the user successfully awakens the voice device in each period of each day in seven days per week is respectively counted, so that the awakening probability of each period of each day in seven days per week is calculated according to the total number of awakening times that the user successfully awakens the voice device and the number of awakening times that the user successfully awakens the voice device in each period of each day in seven days per week. For example, fig. 2 is a bar graph of the number of awakenings by the user to awaken the preset device every preset period of time every day in seven days per week according to an embodiment of the invention.
For another example, a day is divided into a plurality of time intervals, such as four time intervals of 8:00-12:00,12:00-18:00, 18:00-23:00, and 23:00-8:00, and the number of times of awakening of the user successfully awakening the voice device in each time interval of the day is respectively counted, so that the awakening probability of each time interval is calculated according to the total number of times of awakening of the user successfully awakening the voice device and the total number of times of awakening of the user successfully awakening the voice device in each time interval. For example, FIG. 3 is a pie chart of wake-up probabilities for multiple periods of the day according to an embodiment of the invention. Fig. 3 may be the statistical number of awakenings by which the user successfully awakens the voice device per period of the day according to fig. 2. As shown in FIG. 3, the user may be in a sleep state in the early morning (23: 00-8:00), the awakening probability is the lowest, and the user may not be awakened as the user is in the working period in the daytime (8:00-12:00,12:00-18: 00). The user may be in a state of going home at night (18:00-23:00) with the highest probability of waking up.
For another example, the number of awakenings that the user successfully awakens the voice device every day in seven days per week is respectively counted, so that the awakening probability of every day in seven days per week is calculated according to the total number of awakenings that the user successfully awakens the voice device and the number of awakenings that the user successfully awakens the voice device every day in seven days per week. For example, FIG. 4 is a pie chart of the wake-up probability of a user waking up the voice device every day seven days a week, according to an embodiment of the invention. Fig. 4 may be a statistical graph of the number of awakenings that the user successfully awakens the voice device each day for seven days per week according to fig. 2. As shown in fig. 4, the user is generally in a vacation state on saturday and sunday, and the probability of waking up is the highest, and the user may be in a most busy state on wednesday, and the probability of waking up is the lowest.
Step S130, setting an adjusting strategy of the voice endpoint detection sensitivity of the voice equipment according to the use habit of the user to the voice equipment.
Specifically, the adjustment policy includes voice endpoint detection sensitivity corresponding to each of the preset time periods. And respectively setting voice endpoint detection sensitivity corresponding to each time period in a plurality of preset time periods according to the awakening probability of the user to the voice equipment in each time period in the plurality of preset time periods. That is, the preset time periods of different wake-up probabilities set different voice endpoint detection sensitivities. The time period with higher awakening probability, namely the time period in which the user frequently uses the voice equipment, is set with higher voice endpoint detection sensitivity, and the time period with lower awakening probability, namely the time period in which the user does not frequently use the voice equipment, is set with lower voice endpoint detection sensitivity.
And step S140, adjusting the voice endpoint detection sensitivity of the voice equipment according to the adjusting strategy.
Fig. 5 is a flowchart illustrating a specific implementation of the step of adjusting the voice endpoint detection sensitivity of the voice device according to the adjustment policy according to an embodiment of the present invention. As shown in fig. 5, step S140 specifically includes step S141, step S142, and step S143.
Step S141, determining a first time period of the current time among the plurality of preset time periods.
And step S142, acquiring the detection sensitivity of the first voice endpoint corresponding to the first time period according to the adjusting strategy.
Step S143, setting the first voice endpoint detection sensitivity as the current voice endpoint detection sensitivity of the voice device.
For example, if the time period of the current time in a day is determined in a manner of dividing the day into a plurality of time periods, for example, the current time is 9:00 and is within a time period of 8:00-12:00, the voice endpoint detection sensitivity corresponding to the time period of 8:00-12:00 is obtained and set as the current voice endpoint detection sensitivity. For another example, if the time period of the current time in the seven days per week, that is, the current day, for example, the current wednesday, is determined according to the above-mentioned division manner of seven days per week, the voice endpoint detection sensitivity corresponding to wednesday is acquired and set as the current voice endpoint detection sensitivity. For another example, if the current time is determined to be on the day of the week in the seven days of the week according to the division manner of the preset time period of each day in the seven days of the week, and then the time period of the current time in the day is determined, for example, the current time is on the day of the wednesday of 9:00, the endpoint detection sensitivity corresponding to the time period of 8:00-12:00 of the wednesday in the adjustment policy is obtained and set as the current voice endpoint detection sensitivity.
And after the voice equipment receives the awakening voice, carrying out voice endpoint detection according to the current voice endpoint detection sensitivity. In one embodiment, the voice endpoint detection is performed using a dual threshold endpoint detection technique based on short-time energy and zero-crossing rate.
Optionally, the wake-up time of the user when the user successfully wakes up the voice device each time in the first preset time is obtained again every second preset time, and the usage habit of the user on the voice device is updated according to the wake-up time of the user when the user successfully wakes up the voice device each time in the first preset time obtained again, so as to update the adjustment strategy of the voice endpoint detection sensitivity of the voice device. That is, the adjustment policy of the voice endpoint detection sensitivity of the voice device is updated at intervals.
For example, the wake-up time when the user successfully wakes up the voice device within one month or one quarter is acquired again every month or every quarter, and the usage habit of the user for the voice device is updated according to the acquired wake-up time when the user successfully wakes up the voice device within one month or one quarter, so as to reset the adjustment strategy of the voice endpoint detection sensitivity of the voice device.
Fig. 6 is a schematic structural diagram of an embodiment of an endpoint detection sensitivity adjustment apparatus for a speech device according to the present invention. As shown in fig. 6, the end point detection sensitivity adjustment apparatus 100 of the voice device includes an acquisition unit 110, an analysis unit 120, a setting unit 130, and an adjustment unit 140.
The obtaining unit 110 is configured to obtain a wake-up time when the user successfully wakes up the voice device each time; the analysis unit 120 is configured to analyze a usage habit of the user on the voice device according to a wake-up time when the user successfully wakes up the voice device each time; the setting unit 130 is configured to set an adjustment policy of voice endpoint detection sensitivity of the voice device according to a usage habit of the user on the voice device; the adjusting unit 140 is configured to adjust the voice endpoint detection sensitivity of the voice device according to the adjusting policy.
The obtaining unit 110 obtains the wake-up time of the user each time the user successfully wakes up the voice device. The voice equipment can be equipment already distributed with a network, and the networking state is kept. And when the user successfully awakens the voice equipment each time, acquiring and recording the awakening time when the user successfully awakens the voice equipment. More specifically, the obtaining unit 110 may obtain the wake-up time of the user waking up the voice device each time within a preset time, for example, obtain the wake-up time of the user waking up the voice device each time within a month or a quarter.
The analysis unit 120 analyzes the usage habit of the user on the voice device according to the wake-up time of the user when the user successfully wakes up the voice device each time. Specifically, the analysis unit 120 may analyze the wake-up probability of the user on the voice device in each of a plurality of preset time periods according to the wake-up time of the user when the user successfully wakes up the voice device each time. More specifically, the awakening times of the voice device successfully awakened by the user in each preset time period in the plurality of preset time periods are respectively counted, and the awakening probability of the user on the voice device in each preset time period is determined according to the awakening times of the voice device successfully awakened by the user in each preset time period and the total times of the voice device successfully awakened by the user. The preset time periods may specifically include: daily on a weekly basis and/or multiple periods of each day.
For example, the number of awakening times that the user successfully awakens the voice device in each of a plurality of preset periods of each day in seven days per week is respectively counted, for example, one day is divided into four periods of 8:00-12:00,12:00-18:00, 18:00-23:00 and 23:00-8:00, and the number of awakening times that the user successfully awakens the voice device in each period of each day in seven days per week is respectively counted, so that the awakening probability of each period of each day in seven days per week is calculated according to the total number of awakening times that the user successfully awakens the voice device and the number of awakening times that the user successfully awakens the voice device in each period of each day in seven days per week. For example, fig. 2 is a bar graph of the number of awakenings by the user to awaken the preset device every preset period of time every day in seven days per week according to an embodiment of the invention.
For another example, a day is divided into a plurality of time intervals, such as four time intervals of 8:00-12:00,12:00-18:00, 18:00-23:00, and 23:00-8:00, and the number of times of awakening of the user successfully awakening the voice device in each time interval of the day is respectively counted, so that the awakening probability of each time interval is calculated according to the total number of times of awakening of the user successfully awakening the voice device and the total number of times of awakening of the user successfully awakening the voice device in each time interval. For example, FIG. 3 is a pie chart of wake-up probabilities for multiple periods of the day according to an embodiment of the invention. Fig. 3 may be the statistical number of awakenings by which the user successfully awakens the voice device per period of the day according to fig. 2. As shown in FIG. 3, the user may be in a sleep state in the early morning (23: 00-8:00), the awakening probability is the lowest, and the user may not be awakened as the user is in the working period in the daytime (8:00-12:00,12:00-18: 00). The user may be in a state of going home at night (18:00-23:00) with the highest probability of waking up.
For another example, the number of awakenings that the user successfully awakens the voice device every day in seven days per week is respectively counted, so that the awakening probability of every day in seven days per week is calculated according to the total number of awakenings that the user successfully awakens the voice device and the number of awakenings that the user successfully awakens the voice device every day in seven days per week. For example, FIG. 4 is a pie chart of the wake-up probability of a user waking up the voice device every day seven days a week, according to an embodiment of the invention. Fig. 4 may be a statistical graph of the number of awakenings that the user successfully awakens the voice device each day for seven days per week according to fig. 2. As shown in fig. 4, the user is generally in a vacation state on saturday and sunday, and the probability of waking up is the highest, and the user may be in a most busy state on wednesday, and the probability of waking up is the lowest.
The setting unit 130 sets an adjustment policy of the voice endpoint detection sensitivity of the voice device according to the usage habit of the user on the voice device. Specifically, the adjustment policy includes voice endpoint detection sensitivity corresponding to each of the preset time periods. The setting unit 130 sets the voice endpoint detection sensitivity corresponding to each of the plurality of preset time periods according to the wake-up probability of the user to the voice device in each of the plurality of preset time periods. That is, the preset time periods of different wake-up probabilities set different voice endpoint detection sensitivities. The time period with higher awakening probability, namely the time period in which the user frequently uses the voice equipment, is set with higher voice endpoint detection sensitivity, and the time period with lower awakening probability, namely the time period in which the user does not frequently use the voice equipment, is set with lower voice endpoint detection sensitivity.
The adjusting unit 140 adjusts the voice endpoint detection sensitivity of the voice device according to the adjusting strategy. Fig. 7 is a schematic structural diagram of an embodiment of an adjusting unit according to an embodiment of the present invention. As shown in fig. 7, the adjusting unit 140 includes a determining subunit 141, an acquiring subunit 142, and a setting subunit 143.
The determining subunit 141 is configured to determine a first time period in which the current time is located in the plurality of preset time periods; the obtaining subunit 142 is configured to obtain, according to the adjustment policy, a first voice endpoint detection sensitivity corresponding to the first time period; the setting subunit 143 is configured to set the first voice endpoint detection sensitivity as the current voice endpoint detection sensitivity of the voice device.
For example, if the determining subunit 141 determines the time period of the current time in the day in a manner that the day is divided into a plurality of time periods, for example, the current time is 9:00 and is in a time period of 8:00 to 12:00, the acquiring subunit 142 acquires the voice endpoint detection sensitivity corresponding to the time period of 8:00 to 12:00, and the setting subunit 143 sets the voice endpoint detection sensitivity to the current voice endpoint detection sensitivity. For another example, if the determining subunit 141 determines the time period of the current time in the seven days per week, that is, the current day, for example, the current wednesday, in accordance with the above-described division manner of seven days per week, the acquiring subunit 142 acquires the voice endpoint detection sensitivity corresponding to wednesday, and the setting subunit 143 sets this to the current voice endpoint detection sensitivity. For another example, if the current time is determined to be on the day of the week in the seven days of the week according to the division manner of the preset time period of each day in the seven days of the week, and then the time period of the current time in the day is determined, for example, the current time is on the day of the wednesday of 9:00, the endpoint detection sensitivity corresponding to the time period of 8:00-12:00 of the wednesday in the adjustment policy is obtained and set as the current voice endpoint detection sensitivity.
And after the voice equipment receives the awakening voice, carrying out voice endpoint detection according to the current voice endpoint detection sensitivity. In one embodiment, the voice endpoint detection is performed using a dual threshold endpoint detection technique based on short-time energy and zero-crossing rate. Reference is made to the foregoing description of fig. 6 for a specific embodiment.
Optionally, the obtaining unit 110 obtains the wake-up time of the user successfully waking up the voice device every time in the first preset time every second preset time, and the analyzing unit 120 updates the usage habit of the user on the voice device according to the wake-up time of the user successfully waking up the voice device every time in the first preset time obtained again by the obtaining unit 110, so that the setting unit 130 updates the adjustment policy of the voice endpoint detection sensitivity of the voice device according to the usage habit of the user on the voice device updated by the updating unit 120. That is, the adjustment policy of the voice endpoint detection sensitivity of the voice device is updated at intervals.
For example, the wake-up time when the user successfully wakes up the voice device within one month or one quarter is acquired again every month or every quarter, and the usage habit of the user for the voice device is updated according to the acquired wake-up time when the user successfully wakes up the voice device within one month or one quarter, so as to reset the adjustment strategy of the voice endpoint detection sensitivity of the voice device.
The present invention also provides a storage medium corresponding to the method for adjusting the endpoint detection sensitivity of the voice device, on which a computer program is stored, which when executed by a processor implements the steps of any of the methods described above.
The invention also provides a voice device corresponding to the endpoint detection sensitivity adjusting method of the voice device, which comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the methods when executing the program.
The invention also provides a voice device corresponding to the endpoint detection sensitivity adjusting device of the voice device, which comprises the endpoint detection sensitivity adjusting device of any one of the voice devices.
Therefore, according to the scheme provided by the invention, the using habits of the user are analyzed by counting the time period and the times of awakening the voice equipment by the user. The self-adaptive adjusting strategy for the voice equipment endpoint detection sensitivity is set based on the use habits of the user, and the voice equipment endpoint detection sensitivity can be self-adaptively adjusted according to the use habits of the user in the state that the voice equipment is to be awakened, so that the sensitivity is reduced when the equipment is not frequently used, the sensitivity is improved when the equipment is frequently used, and meaningless voice processing is avoided.
The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the invention and the following claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or a combination of any of these. In addition, each functional unit may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and the parts serving as the control device may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The above description is only an example of the present invention, and is not intended to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (11)
1. An endpoint detection sensitivity adjustment method for a voice device, comprising:
acquiring the awakening time when the user successfully awakens the voice equipment each time;
analyzing the use habit of the user on the voice equipment according to the awakening time when the user successfully awakens the voice equipment each time, wherein the analysis comprises the following steps: analyzing the awakening probability of the user to the voice equipment in each time period in a plurality of preset time periods according to the awakening time when the user successfully awakens the voice equipment each time;
setting an adjusting strategy of voice endpoint detection sensitivity of the voice equipment according to the use habit of the user to the voice equipment; setting higher voice endpoint detection sensitivity in a time period with higher awakening probability, and setting lower voice endpoint detection sensitivity in a time period with lower awakening probability;
and adjusting the voice endpoint detection sensitivity of the voice equipment according to the adjusting strategy.
2. The method according to claim 1, wherein setting an adjustment policy of voice endpoint detection sensitivity of the voice device according to the usage habit of the user on the voice device comprises:
and respectively setting voice endpoint detection sensitivity corresponding to each time period in a plurality of preset time periods according to the awakening probability of the user to the voice equipment in each time period in the plurality of preset time periods.
3. The method of claim 2, wherein adjusting the voice endpoint detection sensitivity of the voice device according to the adjustment policy comprises:
determining a first time period of the current time in the plurality of preset time periods;
acquiring first voice endpoint detection sensitivity corresponding to the first time period according to the adjusting strategy;
and setting the first voice endpoint detection sensitivity as the current voice endpoint detection sensitivity of the voice equipment.
4. The method according to any one of claims 1-3, wherein the plurality of preset time periods comprise: daily on a weekly basis and/or multiple periods of each day.
5. An end point detection sensitivity adjusting apparatus for a speech device, comprising:
the acquiring unit is used for acquiring the awakening time when the user successfully awakens the voice equipment each time;
an analysis unit, configured to analyze a usage habit of the user on the voice device according to a wake-up time when the user successfully wakes up the voice device each time, including: analyzing the awakening probability of the user to the voice equipment in each time period in a plurality of preset time periods according to the awakening time when the user successfully awakens the voice equipment each time;
the setting unit is used for setting an adjusting strategy of the voice endpoint detection sensitivity of the voice equipment according to the use habit of the user to the voice equipment; setting higher voice endpoint detection sensitivity in a time period with higher awakening probability, and setting lower voice endpoint detection sensitivity in a time period with lower awakening probability;
and the adjusting unit is used for adjusting the voice endpoint detection sensitivity of the voice equipment according to the adjusting strategy.
6. The apparatus according to claim 5, wherein the setting unit sets the adjustment policy of the voice endpoint detection sensitivity of the voice device according to the usage habit of the user on the voice device, and includes:
and respectively setting voice endpoint detection sensitivity corresponding to each time period in a plurality of preset time periods according to the awakening probability of the user to the voice equipment in each time period in the plurality of preset time periods.
7. The apparatus of claim 6, wherein the adjustment unit comprises:
the determining subunit is used for determining a first time period of the current time in the plurality of preset time periods;
the acquisition subunit is configured to acquire, according to the adjustment policy, a first voice endpoint detection sensitivity corresponding to the first time period;
and the setting subunit is used for setting the first voice endpoint detection sensitivity as the current voice endpoint detection sensitivity of the voice equipment.
8. The apparatus according to any one of claims 5-7, wherein the plurality of preset time periods comprise: daily on a weekly basis and/or multiple periods of each day.
9. A storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
10. Speech device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method according to any of claims 1-4 when executing the program.
11. A speech device, characterized by comprising an end-point detection sensitivity adjustment means of a speech device according to any one of claims 5-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910002054.4A CN109859774B (en) | 2019-01-02 | 2019-01-02 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910002054.4A CN109859774B (en) | 2019-01-02 | 2019-01-02 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109859774A CN109859774A (en) | 2019-06-07 |
| CN109859774B true CN109859774B (en) | 2021-04-02 |
Family
ID=66893736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910002054.4A Active CN109859774B (en) | 2019-01-02 | 2019-01-02 | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109859774B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459220A (en) * | 2019-08-26 | 2019-11-15 | 杭州涂鸦信息技术有限公司 | A kind of voice awakening method and system and readable storage medium storing program for executing, computer |
| CN111176743B (en) * | 2019-12-31 | 2023-05-05 | 云知声智能科技股份有限公司 | Awakening performance optimization method and device based on user use habit |
| CN112185392A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing system for power supply intelligent client |
| CN112185393A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing method for power supply intelligent client |
| CN112185365A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Power supply intelligent client processing method and system |
| CN112634897B (en) * | 2020-12-31 | 2022-10-28 | 青岛海尔科技有限公司 | Equipment awakening method and device, storage medium and electronic device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN105182809A (en) * | 2015-07-22 | 2015-12-23 | 小米科技有限责任公司 | Method for adjusting light transmittance of intelligent curtain, intelligent curtain and device |
| CN105516510A (en) * | 2015-12-31 | 2016-04-20 | 广东小天才科技有限公司 | Mobile terminal awakening method and device |
| CN108010515A (en) * | 2017-11-21 | 2018-05-08 | 清华大学 | A kind of speech terminals detection and awakening method and device |
| CN108847219A (en) * | 2018-05-25 | 2018-11-20 | 四川斐讯全智信息技术有限公司 | A kind of wake-up word presets confidence threshold value adjusting method and system |
| CN108962250A (en) * | 2018-09-26 | 2018-12-07 | 出门问问信息科技有限公司 | Audio recognition method, device and electronic equipment |
| CN108986805A (en) * | 2018-06-29 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Method and apparatus for sending information |
| CN109102806A (en) * | 2018-09-29 | 2018-12-28 | 百度在线网络技术（北京）有限公司 | Method, apparatus, equipment and computer readable storage medium for interactive voice |
-
2019
- 2019-01-02 CN CN201910002054.4A patent/CN109859774B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN105182809A (en) * | 2015-07-22 | 2015-12-23 | 小米科技有限责任公司 | Method for adjusting light transmittance of intelligent curtain, intelligent curtain and device |
| CN105516510A (en) * | 2015-12-31 | 2016-04-20 | 广东小天才科技有限公司 | Mobile terminal awakening method and device |
| CN108010515A (en) * | 2017-11-21 | 2018-05-08 | 清华大学 | A kind of speech terminals detection and awakening method and device |
| CN108847219A (en) * | 2018-05-25 | 2018-11-20 | 四川斐讯全智信息技术有限公司 | A kind of wake-up word presets confidence threshold value adjusting method and system |
| CN108986805A (en) * | 2018-06-29 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Method and apparatus for sending information |
| CN108962250A (en) * | 2018-09-26 | 2018-12-07 | 出门问问信息科技有限公司 | Audio recognition method, device and electronic equipment |
| CN109102806A (en) * | 2018-09-29 | 2018-12-28 | 百度在线网络技术（北京）有限公司 | Method, apparatus, equipment and computer readable storage medium for interactive voice |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109859774A (en) | 2019-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109859774B (en) | Voice equipment and method and device for adjusting endpoint detection sensitivity thereof and storage medium | |
| US10052061B2 (en) | Adjusting alarms based on sleep onset latency | |
| CN108847219B (en) | Awakening word preset confidence threshold adjusting method and system | |
| CN111558120B (en) | Sleep wake-up method, device, computer equipment and computer readable storage medium | |
| CN105282343B (en) | A kind of method and apparatus for intelligent reminding of sleeping | |
| CN110111789B (en) | Voice interaction method and device, computing equipment and computer readable medium | |
| US9753517B2 (en) | User-personalized wake policy based on learned user behavior | |
| CN111128155B (en) | Awakening method, device, equipment and medium for intelligent equipment | |
| CN105594261A (en) | Power saving with adaptive inactivity time out | |
| CN111414070A (en) | Case power consumption management method and system, electronic device and storage medium | |
| CN105611074B (en) | A kind of method and system optimizing the pushed information time according to alarm time | |
| CN108509225B (en) | Information processing method and electronic equipment | |
| CN111949323A (en) | Intelligent device awakening optimization method and device, intelligent device and storage medium | |
| CN111012132A (en) | Sleep state adjusting method and device based on pillow and intelligent pillow | |
| WO2022037555A1 (en) | Physiological data acquisition method and apparatus, and wearable device | |
| CN108678564B (en) | Awakening method and device of intelligent lock | |
| CN104052861B (en) | A kind of terminal and its awakening method | |
| WO2018120859A1 (en) | Wakeup method and wakeup device | |
| CN105662394B (en) | A kind of method and apparatus prompting the user with information | |
| CN111028908A (en) | Sleep state monitoring method, device, equipment and computer readable storage medium | |
| CN111176743A (en) | Wake-up performance optimization method and device based on user use habits | |
| CN109549298A (en) | Bracelet prompting control method, device and bracelet | |
| WO2023035598A1 (en) | Air conditioner control method, control apparatus, air conditioner, and device | |
| CN114187904A (en) | Similarity threshold acquisition method, voice household appliance and computer readable storage medium | |
| KR20220060802A (en) | Apparatus and method for managing circadian rhythm based on feedback function |
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 |