CN110415710B - Parameter adjusting method, device, equipment and medium for vehicle-mounted voice interaction system - Google Patents
Parameter adjusting method, device, equipment and medium for vehicle-mounted voice interaction system Download PDFInfo
- Publication number
- CN110415710B CN110415710B CN201910721204.7A CN201910721204A CN110415710B CN 110415710 B CN110415710 B CN 110415710B CN 201910721204 A CN201910721204 A CN 201910721204A CN 110415710 B CN110415710 B CN 110415710B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- acceleration
- speed
- detection duration
- abnormal state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- 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
- G10L17/22—Interactive procedures; Man-machine interfaces
Abstract
The embodiment of the invention discloses a parameter adjusting method, a parameter adjusting device, a parameter adjusting equipment and a parameter adjusting medium of a vehicle-mounted voice interaction system. The parameter adjusting method of the vehicle-mounted voice interaction system comprises the following steps: acquiring current driving state parameters of a vehicle in real time in the driving process of the vehicle; judging the current running state of the vehicle according to the current running state parameter; if the vehicle is determined to be in a normal driving state, setting the detection duration of VAD service in the vehicle-mounted voice interaction system as the standard detection duration; if it is determined that the vehicle is in the abnormal state processing stage, the detection period of the VAD service is set to be the extended detection period. According to the technical scheme of the embodiment of the invention, whether the vehicle is in an abnormal state processing stage or not is determined by analyzing the vehicle running state parameters, so that the detection duration of VAD service is adjusted under an emergency condition, the condition that recording is interrupted in advance due to the abnormal state processing is avoided, and the success rate of voice recognition is improved.
Description
Technical Field
The embodiment of the invention relates to a voice recognition technology, in particular to a parameter adjusting method, a parameter adjusting device, a parameter adjusting equipment and a parameter adjusting medium of a vehicle-mounted voice interaction system.
Background
With the development of speech recognition technology, speech recognition systems have been applied to various electronic devices and relate to various aspects of daily life, such as smart speakers, smart phones, and speech assistants during driving.
Speech recognition systems generally have the ability to start recording, recognize recorded speech, end speech recording, and provide recognition results. The scheme for ending the voice input is generally two, one is that the user ends manually, and the other is that the system detects that the voice input of the user ends automatically. In the prior art, a technology commonly used for detecting that a user finishes recording after Voice recording is VAD (Voice Activity Detection), which can determine whether the user finishes Voice recording by detecting energy of audio information. The end point detection duration is fixed thereafter, which requires the user to keep the continuity of the recording during the voice input process, however, during the driving process, the user often stops the voice input within a period of time due to a road emergency, which leads to the early termination of the voice input, and may also lead to the reduction of the accuracy of the voice recognition due to the unintended content input by the user in the face of the emergency, which leads to the error of the voice input.
Disclosure of Invention
The embodiment of the invention provides a parameter adjusting method, a parameter adjusting device and a parameter adjusting medium of a vehicle-mounted voice interaction system, which are used for adjusting the detection duration of VAD (voice over VAD) service in real time according to vehicle driving state parameters in the vehicle driving process.
In a first aspect, an embodiment of the present invention provides a method for adjusting parameters of a vehicle-mounted voice interaction system, where the method includes:
acquiring current driving state parameters of a vehicle in real time in the driving process of the vehicle;
judging the current running state of the vehicle according to the current running state parameter;
if the vehicle is determined to be in a normal driving state, setting the detection duration of VAD service in the vehicle-mounted voice interaction system as a standard detection duration;
setting the detection duration of the VAD service to be an extended detection duration if the vehicle is determined to be in an abnormal state processing stage;
wherein the extended detection duration is greater than the standard detection duration.
In a second aspect, an embodiment of the present invention further provides a device for adjusting parameters of a vehicle-mounted voice interaction system, where the device includes:
the state parameter acquisition module is used for acquiring the current driving state parameters of the vehicle in real time in the driving process of the vehicle;
the driving state judging module is used for judging the current driving state of the vehicle according to the current driving state parameter;
the standard detection duration setting module is used for setting the detection duration of VAD service in the vehicle-mounted voice interaction system as the standard detection duration if the vehicle is determined to be in the normal running state;
the extended detection duration setting module is used for setting the detection duration of the VAD service as the extended detection duration if the vehicle is determined to be in the abnormal state processing stage;
wherein the extended detection duration is greater than the standard detection duration.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the parameter adjustment method of the vehicle-mounted voice interaction system provided by any embodiment of the invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the parameter adjustment method of the vehicle-mounted voice interaction system according to any embodiment of the present invention.
According to the technical scheme of the embodiment of the invention, the current running state of the vehicle is judged by acquiring the running state parameters in the running process of the vehicle, if the vehicle is determined to be in the normal running state, the detection time of the VAD service in the vehicle-mounted voice interaction system is set as the standard detection time, and if the vehicle is determined to be in the abnormal state processing stage, the detection time of the VAD service is set as the detection time, so that the detection time of the VAD service is dynamically adjusted according to the running state in the running process of the vehicle, the condition that the voice recognition fails because the recording is finished in advance due to the road emergency is avoided, and the success rate of the voice recognition in the vehicle-mounted voice interaction system is improved.
Drawings
Fig. 1 is a flowchart of a parameter adjustment method of a vehicle-mounted voice interaction system according to a first embodiment of the present invention;
fig. 2 is a flowchart of a parameter adjustment method of a vehicle-mounted voice interaction system according to a second embodiment of the present invention;
fig. 3 is a flowchart of a parameter adjustment method of a vehicle-mounted voice interaction system in a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a parameter adjustment apparatus of a vehicle-mounted voice interaction system according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a parameter adjustment method for a vehicle-mounted voice interaction system in an embodiment of the present invention, where the technical solution of this embodiment is suitable for a situation where parameters of the vehicle-mounted voice interaction system are adjusted according to a driving state of a vehicle, and the method may be executed by a parameter adjustment device of the vehicle-mounted voice interaction system, and the device may be implemented by software and/or hardware, and may be integrated in various general-purpose computer devices, and specifically includes the following steps:
and 110, acquiring the current running state parameters of the vehicle in real time in the running process of the vehicle.
In this embodiment, in order to determine the driving state of the vehicle, if it is detected that the user starts the voice interaction system and starts to input the voice in the driving process of the vehicle, the driving state parameters of the vehicle are acquired in real time through a sensor of the vehicle-mounted voice interaction system. For example, when it is detected that the user starts the voice interaction system and records voice in the vehicle driving state, the speed and the acceleration of the vehicle are acquired at regular time through the acceleration sensor and the GPS sensor of the voice interaction system, and for example, the speed and the acceleration values can be acquired and recorded every 0.5 second.
Optionally, the driving state parameters include: a current speed, and/or a current acceleration of the vehicle.
In this optional embodiment, in order to determine the driving state of the vehicle, a speed and an acceleration value that can most represent the driving state of the vehicle are selected as the driving state parameters that need to be acquired in real time.
And 120, judging the current running state of the vehicle according to the current running state parameters, executing step 130 if the vehicle is determined to be in a normal running state, and executing step 140 if the vehicle is determined to be in an abnormal state processing stage.
In this embodiment, according to the vehicle driving state parameters (mainly speed and acceleration) obtained in the above embodiments, the current driving state of the vehicle is determined by setting rules, where the driving state may include a normal driving state and an abnormal state processing stage.
For example, the vehicle running state can be judged by presetting normal value ranges of speed and acceleration and judging whether the currently acquired vehicle running state parameter is within the value range, at this time, if the current running state parameter is within the preset value range, it is determined that the vehicle is in a normal running state, and if the current running state parameter exceeds the preset value range, it is determined that the vehicle is in an abnormal state processing stage;
or, the acquired vehicle running state parameters can be input into a pre-acquired speed and acceleration prediction model to predict the value range of the speed and the acceleration in the next time period, and finally, the vehicle running state is judged by judging whether the acquired actual speed and/or the acquired acceleration of the vehicle are within the prediction range, at this time, if the current running state parameters are within the prediction range, the vehicle is determined to be in a normal running state, and if the current running state parameters exceed the prediction range, the vehicle is determined to be in an abnormal state processing stage.
In this embodiment, when it is determined that the current driving state of the vehicle is in the normal driving state, which indicates that the user can continuously perform the voice input operation, the detection duration of the VAD service in the vehicle-mounted voice interaction system may be maintained as a default value, where the default value of the detection duration of the VAD service may be set to 1 second, and of course, the default duration may also be set autonomously according to an actual situation.
wherein the extended detection duration is greater than the standard detection duration.
In this embodiment, when it is determined that the vehicle is in the abnormal state processing stage, it indicates that the user may stop voice recording within a period of time due to processing the abnormal state, and if the detection duration of the VAD service still adopts a default value at this time, the recording may be ended early, so that the voice recognition may fail, and therefore, the detection duration of the VAD service needs to be delayed, that is, the detection duration of the VAD service is set to be extended. For example, the extended detection duration may be a preset fixed duration, and the fixed duration is greater than a default detection duration; alternatively, the extension detection period may be a variable period flexibly adjusted according to the degree of urgency of the abnormal state.
According to the technical scheme of the embodiment of the invention, the current running state of the vehicle is judged by acquiring the running state parameters in the running process of the vehicle, if the vehicle is determined to be in the normal running state, the detection time of the VAD service in the vehicle-mounted voice interaction system is set as the standard detection time, and if the vehicle is determined to be in the abnormal state processing stage, the detection time of the VAD service is set as the detection time, so that the detection time of the VAD service is dynamically adjusted according to the running state in the running process of the vehicle, the condition that the voice recognition fails because the recording is finished in advance due to the road emergency is avoided, and the success rate of the voice recognition in the vehicle-mounted voice interaction system is improved.
Example two
Fig. 2 is a flowchart of a parameter adjustment method for a vehicle-mounted voice interaction system according to a second embodiment of the present invention, which is further detailed based on the second embodiment of the present invention, and provides a specific step of determining a current driving state of the vehicle according to the driving state parameter and a specific step before setting the detection duration of the VAD service to be extended. The following describes, with reference to fig. 2, a parameter adjustment method for a vehicle-mounted voice interaction system according to a second embodiment of the present invention, including the following steps:
and step 210, acquiring the current running state parameters of the vehicle in real time in the running process of the vehicle.
Optionally, the driving state parameters include: a current speed, and/or a current acceleration of the vehicle.
And 220, acquiring the range of the predicted speed and/or acceleration of the vehicle in the second set time period according to the speed and/or acceleration of the vehicle in the first set time period.
In this embodiment, a speed and acceleration prediction model may be constructed in advance from a historical speed and acceleration during the vehicle running process, the speed and acceleration of the vehicle collected in a first set time period (for example, 10 seconds) may be input to the speed and acceleration prediction model, respectively, the speed and acceleration of the vehicle collected in a second set time period may be predicted, for example, the speed and acceleration of the vehicle collected in a 28 th 30 th to 28 th 40 th minute period during the vehicle running process may be input to the prediction model, and a value range of the speed and acceleration of the vehicle in a 28 th 41 th to 28 th 45 th minute period may be predicted. The predictive model of the speed and the acceleration may be a curve of the speed and the acceleration obtained by quadratic curve fitting based on the historical data of the speed and the acceleration of the vehicle.
And step 221, detecting whether the actual speed and/or acceleration of the vehicle in the second set time length exceeds the range of the predicted speed and/or acceleration, if so, executing step 240 to step 243, otherwise, executing step 230 to step 231.
And step 230, determining that the vehicle is in a normal running state.
In this embodiment, the detected actual speed and acceleration of the vehicle within the second set time period are compared with the value ranges of the speed and acceleration of the vehicle predicted in step 220, and when the actual speed and the acceleration are within the value ranges of the predicted speed and acceleration, respectively, it is determined that the vehicle is in a normal driving state. Illustratively, the values of the speed and the acceleration of the vehicle predicted in step 220 in the 28 th minute 41-28 th minute 45 second range are [40Km/h, 60Km/h ] respectively]And [ -2m/s2，2m/s2]When the range of the actual vehicle speed from 41 seconds to 28 minutes 45 seconds at 28 minutes [40Km/h, 55Km/h ] is detected]The actual vehicle acceleration range is [ -0.5m/s2，0.3m/s2]It is apparent that the actual values of the vehicle speed and the acceleration are within the predicted ranges, and it is determined that the vehicle is in a normal running state.
And 231, setting the detection duration of the VAD service in the vehicle-mounted voice interaction system as a standard detection duration.
And step 240, determining that the vehicle is in an abnormal state processing stage.
In this embodiment, the detected actual speed and acceleration of the vehicle within the second set time period are compared with the value ranges of the speed and acceleration of the vehicle predicted in step 220, and when the actual speed and/or acceleration exceeds the value ranges of the predicted speed and acceleration, it is determined that the vehicle is in the abnormal state processing stage. Illustratively, the values of the speed and the acceleration of the vehicle predicted in step 220 in the 28 th minute 41-28 th minute 45 second range are [40Km/h, 60Km/h ] respectively]And [ -2m/s2，2m/s2]When a range of actual vehicle speeds from 41 seconds to 45 seconds at 28 th minute to 28 th minute is detected [25Km/h, 55Km/h ]]The actual vehicle acceleration range is [ -0.7m/s2，0.3m/s2]Obviously, if the actual value of the vehicle speed exceeds the prediction range, the vehicle is determined to be in the abnormal state processing stage.
It is worth noting that when the actual speed and the acceleration of the vehicle are detected to be respectively in the value ranges of the predicted speed and the predicted acceleration, the vehicle is determined to be in a normal running state, and once one actual value of the speed or the acceleration exceeds the predicted range, the vehicle is determined to be in an abnormal state processing stage.
And 241, determining the emergency degree of the abnormal state according to the relation between the actual speed and the acceleration in the second set time length and the range of the predicted speed and/or the acceleration.
In this embodiment, in order to perform targeted processing for situations with different urgency levels, quantitative analysis is performed on the abnormal state, specifically, the urgency level of the abnormal state is obtained according to a relationship between an actual speed and an acceleration within a second set time period and a range of a predicted speed and/or an acceleration, where a larger quantified value of the urgency level indicates that the current state is more urgent. Illustratively, a case of 0.5 urgency is more urgent than a case of 0.2 urgency.
Optionally, determining the emergency degree of the abnormal state according to the relationship between the actual speed and the acceleration within the second set time period and the range of the predicted speed and/or acceleration, including:
calculating the offset rate of the speed value according to the deviation value of the actual speed of the vehicle within the second set time length from the range of the predicted speed and the current actual speed;
calculating the offset rate of the acceleration value according to the deviation value of the actual acceleration of the vehicle within the second set time length from the range of the predicted acceleration and the current actual acceleration;
and calculating the emergency degree of the abnormal condition according to the speed value offset rate and the acceleration value offset rate.
In this alternative embodiment, a more specific method for determining the degree of urgency of an abnormal state based on the relationship between the actual speed and acceleration and the range of predicted speed and/or acceleration within the second set time period is provided. Firstly, calculating the offset rate beta of the speed value according to the deviation value of the actual speed of the vehicle from the range of the predicted speed and the current actual speed in a second set time period, wherein the specific calculation formula is as follows:
wherein v (t) represents the maximum or minimum value of the actual speed of the vehicle within a second set period of time;
vhighrepresenting a maximum value in the predicted speed range within a second set period of time;
vlowindicating the minimum value in the predicted speed range within the second set period.
Then, calculating the offset rate alpha of the acceleration value according to the deviation value of the actual acceleration of the vehicle within the second set time length from the range of the predicted acceleration and the current actual acceleration, wherein the specific calculation formula is as follows:
wherein a (t) represents the maximum value or the minimum value of the actual acceleration of the vehicle within a second set time period;
ahighrepresenting the maximum value in the predicted acceleration range within the second set period of time;
alowrepresents the minimum value in the predicted acceleration range within the second set period.
And finally, calculating the emergency degree eta of the abnormal condition according to the speed value deviation rate and the acceleration value deviation rate, wherein the specific calculation formula is as follows:
η＝αβ
wherein, the larger the value of eta is, the more urgent the current abnormal state is.
And 242, calculating the extended detection time according to the emergency degree of the abnormal state.
In this embodiment, the extended detection duration is calculated according to the emergency degree of the abnormal state, so as to flexibly adjust the detection duration of the VAD service according to the emergency degree of the abnormal state, and improve the success rate of voice recognition.
Optionally, calculating the extended detection duration according to the emergency degree of the abnormal state includes:
and calculating the prolonged detection time according to the emergency degree of the abnormal state and the standard detection time.
In this optional embodiment, a specific method for calculating the extended detection duration t' according to the emergency degree of the abnormal state and the standard detection duration is provided, and a calculation formula is as follows:
t'＝Cηt
wherein η represents the urgency of the abnormal condition;
t represents a standard detection time length;
c is an extended detection time period calculation constant, wherein C eta is more than 1.
As can be seen from the above formula, the more urgent the degree of urgency of the abnormal state is, the longer the extended detection period is.
Step 243, setting the detection duration of the VAD service as an extended detection duration.
According to the technical scheme of the embodiment, the driving state of the vehicle is determined by comparing the actual speed and the acceleration with the predicted speed and the acceleration range in the driving process of the vehicle, the emergency degree of the abnormal state is calculated according to the relation between the detected actual speed and the acceleration within the second set time and the predicted speed and/or acceleration range, the detection prolonging time is calculated according to the emergency degree of the abnormal state, the detection prolonging time of VAD service is set as the detection prolonging time, the detection prolonging time of VAD service is flexibly adjusted according to the driving state of the vehicle, the time for processing the abnormal state is reserved for a user, the condition that recording is interrupted in advance due to an emergency condition is avoided, and the success rate of voice recognition is improved.
EXAMPLE III
Fig. 3 is a flowchart of a parameter adjustment method for a vehicle-mounted voice interaction system in a third embodiment of the present invention, which is further detailed based on the above embodiment, and provides a specific step of acquiring a current driving state parameter of the vehicle in real time and a specific step of setting the detection duration of the VAD service to be an extended detection duration. A parameter adjustment method of a vehicle-mounted voice interaction system provided by a third embodiment of the present invention is described below with reference to fig. 3, including the following steps:
wherein the VAD service is configured to detect an end recording time of the voice entry service.
In this embodiment, when it is detected that the user starts the vehicle-mounted voice interaction system and starts to perform voice recording, the current driving state parameter of the vehicle is measured in real time through a sensor provided in the vehicle-mounted voice interaction system, so as to determine the driving state of the vehicle.
And step 330, setting the detection duration of the VAD service in the vehicle-mounted voice interaction system as a standard detection duration.
wherein the extended detection duration is greater than the standard detection duration.
Step 341, acquiring the user input voice acquired by the voice input service in the abnormal state processing stage.
When the user is in an abnormal state during voice input in the vehicle-mounted voice interaction system, the user may unconsciously input some exclamation words or information without practical meaning such as "o …" or "tianya …". In this embodiment, the user input voice acquired by the voice input service at the abnormal state processing stage is acquired, so as to process the information contained therein without actual meaning.
And 342, eliminating non-command information included in the voice input by the user.
In this embodiment, information that is included in the user input speech and that has no practical significance is mainly removed to avoid adverse effect on speech recognition.
Optionally, removing the non-command information included in the user-entered speech includes:
according to an unintended language model, recognizing unconscious non-command information of a user in the abnormal state processing stage from the input voice of the user;
removing the unconscious non-command information from the voice input by the user;
the non-intention language model is obtained by training through non-intention linguistic data and is used for judging whether the voice input by the user belongs to unconscious non-command information or not.
In this optional embodiment, a specific manner of removing the non-command information included in the user-entered speech is provided, and first, the user-entered speech obtained in step 341 is input to the unintended language model, the non-command information included in the user-entered speech is identified by the unintended language model, and then, the identified non-command information is removed from the user-entered speech.
According to the technical scheme of the embodiment, when the voice input service in the vehicle-mounted voice interaction system is detected to be started, the current running state parameter of the vehicle is obtained in real time, the running state of the vehicle is determined according to the running state parameter, when the vehicle is detected to be in an abnormal state processing stage, the detection time length of the VAD service in the vehicle-mounted voice interaction system is set to be standard detection time length, if the vehicle is determined to be in the abnormal state processing stage, the detection time length of the VAD service is set to be prolonged, and meanwhile, the non-command information included in the voice input of the user is eliminated, on one hand, the detection time length of the VAD service is dynamically adjusted according to the running state of the vehicle, the early interruption of recording caused by an emergency state is avoided, on the other hand, the non-command information included in the voice input of the user is eliminated, and the adverse effect of the non-command information unconsciously input by the user in the emergency state on voice recognition is avoided, and the completion rate of the voice task is improved.
Example four
Fig. 4 is a schematic structural diagram of a parameter adjustment device of a vehicle-mounted voice interaction system in a fourth embodiment of the present invention, where the parameter adjustment device of the vehicle-mounted voice interaction system includes: a state parameter obtaining module 410, a driving state judging module 420, a standard detection duration setting module 430 and an extended detection duration setting module 440.
A state parameter obtaining module 410, configured to obtain a current driving state parameter of a vehicle in real time during a driving process of the vehicle;
a driving state determining module 420, configured to determine a current driving state of the vehicle according to the current driving state parameter;
a standard detection duration setting module 430, configured to set a detection duration of VAD service in the vehicle-mounted voice interaction system as a standard detection duration if it is determined that the vehicle is in a normal driving state;
an extended detection duration setting module 440 configured to set a detection duration of the VAD service as an extended detection duration if it is determined that the vehicle is in an abnormal state processing stage;
wherein the extended detection duration is greater than the standard detection duration.
According to the technical scheme of the embodiment of the invention, the current running state of the vehicle is judged by acquiring the running state parameters in the running process of the vehicle, if the vehicle is determined to be in the normal running state, the detection time of the VAD service in the vehicle-mounted voice interaction system is set as the standard detection time, and if the vehicle is determined to be in the abnormal state processing stage, the detection time of the VAD service is set as the detection time, so that the detection time of the VAD service is dynamically adjusted according to the running state in the running process of the vehicle, the condition that the voice recognition fails because the recording is finished in advance due to the road emergency is avoided, and the success rate of the voice recognition in the vehicle-mounted voice interaction system is improved.
Optionally, the driving state parameters include: a current speed, and/or a current acceleration of the vehicle;
accordingly, the driving state determining module 420 includes:
the range prediction unit is used for obtaining the range of the predicted speed and/or acceleration of the vehicle in a second set time period according to the speed and/or acceleration of the vehicle in the first set time period;
an abnormal state determination unit, which is used for determining that the vehicle is in an abnormal state processing stage when the fact that the actual speed and/or the acceleration of the vehicle in the second set time length exceeds the range of the predicted speed and/or acceleration is detected;
and the normal state determining unit is used for determining that the vehicle is in a normal running state when the actual speed and the acceleration of the vehicle in the second set time length are detected to be in the range of the predicted speed and/or acceleration.
Optionally, the parameter adjustment of the vehicle-mounted voice interaction system further includes:
an urgency level determination module for determining an urgency level of an abnormal state according to a relationship between an actual speed and acceleration within the second set time period and a range of the predicted speed and/or acceleration before setting the detection time period of the VAD service to be an extended detection time period;
and the detection time length prolonging calculation module is used for calculating the detection time length prolonging according to the emergency degree of the abnormal state.
Optionally, the emergency degree determining module includes:
the speed deviation rate calculation unit is used for calculating the deviation rate of the speed value according to the deviation value of the actual speed of the vehicle within the second set time length from the range of the predicted speed and the current actual speed;
the acceleration deviation rate calculation unit is used for calculating the deviation rate of the acceleration value according to the deviation value of the actual acceleration of the vehicle within the second set time length from the range of the predicted acceleration and the current actual acceleration;
and the emergency degree calculating unit is used for calculating the emergency degree of the abnormal condition according to the speed value offset rate and the acceleration value offset rate.
Optionally, the detection duration extension calculating module includes:
the extended detection duration calculation unit is used for calculating the extended detection duration according to the emergency degree of the abnormal state and the standard detection duration;
wherein the more urgent the degree of urgency of the abnormal state is, the longer the extended detection period is.
Optionally, the state parameter obtaining module 410 includes:
the state parameter acquisition unit is used for acquiring the current driving state parameter of the vehicle in real time when detecting that the voice input service in the vehicle-mounted voice interaction system is started;
wherein the VAD service is configured to detect an end recording time of the voice entry service.
Optionally, the parameter adjusting apparatus of the vehicle-mounted voice interaction system further includes:
a voice acquisition module, configured to acquire a user input voice acquired through the voice input service at the abnormal state processing stage after setting the detection duration of the VAD service to be an extended detection duration;
and the non-command information removing module is used for removing the non-command information included in the voice input by the user.
Optionally, the non-command information elimination module includes:
a non-command information recognition unit, configured to recognize, from the user-entered speech, unconscious non-command information of the user at the abnormal state processing stage according to an unintended language model;
a non-command information removing unit for removing the unconscious non-command information from the voice input by the user;
the non-intention language model is obtained by training through non-intention linguistic data and is used for judging whether the voice input by the user belongs to unconscious non-command information or not.
The parameter adjusting device of the vehicle-mounted voice interaction system provided by the embodiment of the invention can execute the parameter adjusting method of the vehicle-mounted voice interaction system provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention, and as shown in fig. 5, the electronic device includes a processor 50 and a memory 51; the number of processors 50 in the device may be one or more, and one processor 50 is taken as an example in fig. 5; the processor 50 and the memory 51 in the device may be connected by a bus or other means, as exemplified by the bus connection in fig. 5.
The memory 51 is used as a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to a parameter adjustment method of a reverse voice interactive system in an embodiment of the present invention (for example, a state parameter obtaining module 310, a driving state determining module 320, a standard detection duration setting module 330, and an extended detection duration setting module 340 in a parameter adjustment device of a vehicle-mounted voice interactive system). The processor 50 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 51, that is, the parameter adjustment method of the vehicle-mounted voice interaction system is realized.
The method comprises the following steps:
acquiring current driving state parameters of a vehicle in real time in the driving process of the vehicle;
judging the current running state of the vehicle according to the current running state parameter;
if the vehicle is determined to be in a normal driving state, setting the detection duration of VAD service in the vehicle-mounted voice interaction system as a standard detection duration;
setting the detection duration of the VAD service to be an extended detection duration if the vehicle is determined to be in an abnormal state processing stage;
wherein the extended detection duration is greater than the standard detection duration.
The memory 51 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 51 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 non-volatile solid state storage device. In some examples, the memory 51 may further include memory located remotely from the processor 50, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
EXAMPLE six
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the computer-executable instructions are executed by a computer processor to perform a method for adjusting parameters of a vehicle-mounted voice interaction system, and the method includes:
acquiring current driving state parameters of a vehicle in real time in the driving process of the vehicle;
judging the current running state of the vehicle according to the current running state parameter;
if the vehicle is determined to be in a normal driving state, setting the detection duration of VAD service in the vehicle-mounted voice interaction system as a standard detection duration;
setting the detection duration of the VAD service to be an extended detection duration if the vehicle is determined to be in an abnormal state processing stage;
wherein the extended detection duration is greater than the standard detection duration.
Of course, the storage medium including the computer-executable instructions provided in the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the parameter adjustment method of the vehicle-mounted voice interaction system provided in any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the parameter adjustment apparatus for a vehicle-mounted voice interaction system, each included unit and module are only divided according to functional logic, but are not limited to the above division, as long as corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (13)
1. A parameter adjustment method of a vehicle-mounted voice interaction system is characterized by comprising the following steps:
acquiring running state parameters of a vehicle in real time in the running process of the vehicle; the driving state parameters comprise the speed, and/or acceleration of the vehicle;
obtaining the range of the predicted speed and/or acceleration of the vehicle in a second set time period according to the speed and/or acceleration of the vehicle in the first set time period;
when the fact that the actual speed of the vehicle exceeds the range of the predicted speed and/or the actual acceleration of the vehicle exceeds the range of the predicted acceleration is detected within the second set time length, determining that the vehicle is in an abnormal state processing stage;
when the actual speed and the acceleration of the vehicle in the second set time length are detected to be in the ranges of the predicted speed and the acceleration respectively, determining that the vehicle is in a normal running state;
if the vehicle is determined to be in a normal driving state, setting the detection duration of voice endpoint detection VAD service in the vehicle-mounted voice interaction system as standard detection duration;
setting the detection duration of the VAD service to be an extended detection duration if the vehicle is determined to be in an abnormal state processing stage;
wherein the extended detection duration is greater than the standard detection duration.
2. The method of claim 1, before setting the detection duration of the VAD service to be the extended detection duration, comprising:
determining the emergency degree of the abnormal state according to the relation between the actual speed and the acceleration in the second set time length and the range of the predicted speed and/or acceleration;
and calculating the extended detection time according to the emergency degree of the abnormal state.
3. The method of claim 2, wherein said determining the urgency of the abnormal condition based on the relationship between the actual speed and acceleration within the second set duration and the range of predicted speeds and/or accelerations comprises:
calculating the offset rate of the speed value according to the deviation value of the actual speed of the vehicle from the range of the predicted speed within the second set time period and the actual speed within the second set time period;
calculating the offset rate of the acceleration value according to the deviation value of the actual acceleration of the vehicle within the second set time length from the range of the predicted acceleration and the actual acceleration within the second set time length;
and calculating the emergency degree of the abnormal state according to the offset rate of the speed value and the offset rate of the acceleration value.
4. The method of claim 2, wherein calculating the extended detection period based on the urgency of the abnormal condition comprises:
calculating the extended detection time according to the emergency degree of the abnormal state and the standard detection time;
wherein the more urgent the degree of urgency of the abnormal state is, the longer the extended detection period is.
5. The method according to any one of claims 1-4, wherein obtaining the driving state parameters of the vehicle in real time comprises:
when detecting that a voice recording service in the vehicle-mounted voice interaction system is started, acquiring current driving state parameters of the vehicle in real time;
wherein the VAD service is configured to detect an end recording time of the voice entry service.
6. The method of claim 5, wherein after setting the detection duration of the VAD service to the extended detection duration, further comprising:
acquiring user input voice acquired by the voice input service at the abnormal state processing stage;
and eliminating non-command information included in the voice input by the user.
7. The method of claim 6, wherein the culling of non-command information included in the user-entered speech comprises:
according to an unintended language model, recognizing unconscious non-command information of a user in the abnormal state processing stage from the input voice of the user;
removing the unconscious non-command information from the voice input by the user;
the non-intention language model is obtained by training through non-intention linguistic data and is used for judging whether the voice input by the user belongs to unconscious non-command information or not.
8. The utility model provides a parameter adjustment device of on-vehicle voice interaction system which characterized in that includes:
the state parameter acquisition module is used for acquiring the driving state parameters of the vehicle in real time in the driving process of the vehicle; the driving state parameters comprise the speed, and/or acceleration of the vehicle;
the range prediction module is used for obtaining the range of the predicted speed and/or acceleration of the vehicle in a second set time period according to the speed and/or acceleration of the vehicle in a first set time period;
the abnormal state determining module is used for determining that the vehicle is in an abnormal state processing stage when the fact that the actual speed and/or the actual acceleration of the vehicle within the second set time length are beyond the range of the predicted speed and/or the predicted acceleration;
the normal state determination module is used for determining that the vehicle is in a normal running state when the fact that the actual speed and the acceleration of the vehicle in the second set time length are within the range of the predicted speed and/or acceleration is detected;
the standard detection duration setting module is used for setting the detection duration of VAD service in the vehicle-mounted voice interaction system as the standard detection duration if the vehicle is determined to be in the normal running state;
the extended detection duration setting module is used for setting the detection duration of the VAD service as the extended detection duration if the vehicle is determined to be in the abnormal state processing stage;
wherein the extended detection duration is greater than the standard detection duration.
9. The apparatus of claim 8, wherein the parameter adjustment of the vehicle-mounted voice interaction system further comprises:
an urgency level determination module for determining an urgency level of an abnormal state according to a relationship between an actual speed and acceleration within the second set time period and a range of the predicted speed and/or acceleration before setting the detection time period of the VAD service to be an extended detection time period;
and the detection time length prolonging calculation module is used for calculating the detection time length prolonging according to the emergency degree of the abnormal state.
10. The apparatus according to any one of claims 8-9, wherein the status parameter obtaining module comprises:
the state parameter acquisition unit is used for acquiring the current driving state parameter of the vehicle in real time when detecting that the voice input service in the vehicle-mounted voice interaction system is started;
wherein the VAD service is configured to detect an end recording time of the voice entry service.
11. The apparatus of claim 10, wherein the parameter adjusting apparatus of the vehicle-mounted voice interactive system further comprises:
a voice acquisition module, configured to acquire a user input voice acquired by the voice input service at the abnormal state processing stage after setting the detection duration of the VAD service to be an extended detection duration;
and the non-command information removing module is used for removing the non-command information included in the voice input by the user.
12. An electronic device, characterized in that the device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the parameter adjustment method of the in-vehicle voice interaction system of any of claims 1-7.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the parameter adjustment method of the in-vehicle voice interaction system according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910721204.7A CN110415710B (en) | 2019-08-06 | 2019-08-06 | Parameter adjusting method, device, equipment and medium for vehicle-mounted voice interaction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910721204.7A CN110415710B (en) | 2019-08-06 | 2019-08-06 | Parameter adjusting method, device, equipment and medium for vehicle-mounted voice interaction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110415710A CN110415710A (en) | 2019-11-05 |
| CN110415710B true CN110415710B (en) | 2022-05-31 |
Family
ID=68366081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910721204.7A Active CN110415710B (en) | 2019-08-06 | 2019-08-06 | Parameter adjusting method, device, equipment and medium for vehicle-mounted voice interaction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415710B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081243A (en) * | 2019-12-20 | 2020-04-28 | 大众问问(北京)信息科技有限公司 | Feedback mode adjusting method, device and equipment |
| CN111402931B (en) * | 2020-03-05 | 2023-05-26 | 云知声智能科技股份有限公司 | Voice boundary detection method and system assisted by sound image |
| CN112016625A (en) * | 2020-08-30 | 2020-12-01 | 北京嘀嘀无限科技发展有限公司 | Vehicle abnormality detection method, device, electronic device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103403798A (en) * | 2011-04-08 | 2013-11-20 | 三菱电机株式会社 | Voice recognition device and navigation device |
| CN104700830A (en) * | 2013-12-06 | 2015-06-10 | 中国移动通信集团公司 | Voice endpoint detection method and voice endpoint detection device |
| CN107298100A (en) * | 2017-05-16 | 2017-10-27 | 开易（北京）科技有限公司 | A kind of track of vehicle Forecasting Methodology, system based on gauss hybrid models |
| WO2017196422A1 (en) * | 2016-05-12 | 2017-11-16 | Nuance Communications, Inc. | Voice activity detection feature based on modulation-phase differences |
| CN107644638A (en) * | 2017-10-17 | 2018-01-30 | 北京智能管家科技有限公司 | Audio recognition method, device, terminal and computer-readable recording medium |
| CN109767792A (en) * | 2019-03-18 | 2019-05-17 | 百度国际科技（深圳）有限公司 | Sound end detecting method, device, terminal and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109718556B (en) * | 2019-01-30 | 2021-09-28 | 腾讯科技（深圳）有限公司 | Game data processing method and device and server |
-
2019
- 2019-08-06 CN CN201910721204.7A patent/CN110415710B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103403798A (en) * | 2011-04-08 | 2013-11-20 | 三菱电机株式会社 | Voice recognition device and navigation device |
| CN104700830A (en) * | 2013-12-06 | 2015-06-10 | 中国移动通信集团公司 | Voice endpoint detection method and voice endpoint detection device |
| WO2017196422A1 (en) * | 2016-05-12 | 2017-11-16 | Nuance Communications, Inc. | Voice activity detection feature based on modulation-phase differences |
| CN107298100A (en) * | 2017-05-16 | 2017-10-27 | 开易（北京）科技有限公司 | A kind of track of vehicle Forecasting Methodology, system based on gauss hybrid models |
| CN107644638A (en) * | 2017-10-17 | 2018-01-30 | 北京智能管家科技有限公司 | Audio recognition method, device, terminal and computer-readable recording medium |
| CN109767792A (en) * | 2019-03-18 | 2019-05-17 | 百度国际科技（深圳）有限公司 | Sound end detecting method, device, terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110415710A (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110415710B (en) | Parameter adjusting method, device, equipment and medium for vehicle-mounted voice interaction system | |
| CN108122556B (en) | Method and device for reducing false triggering of voice wake-up instruction words of driver | |
| CN103886871B (en) | Detection method of speech endpoint and device thereof | |
| CN109669663B (en) | Method and device for acquiring range amplitude, electronic equipment and storage medium | |
| CN110428810A (en) | A kind of recognition methods, device and electronic equipment that voice wakes up | |
| US9424743B2 (en) | Real-time traffic detection | |
| CN111191671B (en) | Electrical appliance waveform detection method, system, electronic equipment and storage medium | |
| CN113421586B (en) | Dream recognition method and device and electronic equipment | |
| CN109243427A (en) | A kind of car fault diagnosis method and device | |
| CN116386277A (en) | Fatigue driving detection method and device, electronic equipment and medium | |
| CN115394318A (en) | Audio detection method and device | |
| CN111402880A (en) | Data processing method and device and electronic equipment | |
| CN109697981B (en) | Voice interaction method, device, equipment and storage medium | |
| US20200402499A1 (en) | Detecting speech activity in real-time in audio signal | |
| CN111159009B (en) | Pressure testing method and device for log service system | |
| CN109147783B (en) | Voice recognition method, medium and system based on Karaoke system | |
| CN113123955A (en) | Plunger pump abnormality detection method and device, storage medium and electronic device | |
| CN107230384B (en) | Parking guidance system and method based on expected parking duration and weather information | |
| CN113241063B (en) | Algorithm parameter updating method, device, terminal and medium in voice recognition system | |
| CN111028830B (en) | Local hot word bank updating method, device and equipment | |
| CN112612844B (en) | Data processing method, device, equipment and storage medium | |
| CN111464644B (en) | Data transmission method and electronic equipment | |
| CN112699563A (en) | Speed segmentation method and device, electronic equipment and storage medium | |
| CN111220234A (en) | Method, device and system for calculating urea liquid level measurement value | |
| CN110931021A (en) | Audio signal processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |