CN106057198B - A kind of method and apparatus controlling intelligent transportation tool - Google Patents

A kind of method and apparatus controlling intelligent transportation tool Download PDF

Info

Publication number
CN106057198B
CN106057198B CN201610366267.1A CN201610366267A CN106057198B CN 106057198 B CN106057198 B CN 106057198B CN 201610366267 A CN201610366267 A CN 201610366267A CN 106057198 B CN106057198 B CN 106057198B
Authority
CN
China
Prior art keywords
information
current speech
speech feature
control instruction
frequency
Prior art date
Application number
CN201610366267.1A
Other languages
Chinese (zh)
Other versions
CN106057198A (en
Inventor
穆亚敏
Original Assignee
北京云知声信息技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京云知声信息技术有限公司 filed Critical 北京云知声信息技术有限公司
Priority to CN201610366267.1A priority Critical patent/CN106057198B/en
Publication of CN106057198A publication Critical patent/CN106057198A/en
Application granted granted Critical
Publication of CN106057198B publication Critical patent/CN106057198B/en

Links

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223Execution procedure of a spoken command

Abstract

The invention discloses a kind of method and apparatus for controlling intelligent transportation tool, to improve the intelligence of smart machine.This method comprises: obtaining the current speech feature of the acoustic information when the acoustic information for inputting intelligent transportation tool is people's acoustic intelligence;If the current speech feature is matched with setting characteristic condition, control instruction corresponding with the current speech feature is determined;According to the determining control instruction, the intelligent transportation tool is controlled.In this way, specific control instruction can be corresponded to for specific phonetic feature, to can further improve the intelligence and safety of intelligent transportation tool.

Description

A kind of method and apparatus controlling intelligent transportation tool

Technical field

The present invention relates to technical field of intelligent equipment, in particular to a kind of method and apparatus for controlling intelligent transportation tool.

Background technique

With the development of smart machine, some vehicles can also become intelligent transportation tool.Such as: intelligent automobile is put down Weigh vehicle, intelligent bicycle, intelligent wheel chair etc..Generally data communication can be all carried out on these intelligent transportation tools, speech recognition, The functions such as instruction control.

Wherein, voice control can be carried out to intelligent transportation tool, such as: after user says " advance ", intelligent wheel chair can be certainly It sets out before trend, and after user says " stopping ", intelligent wheel chair can be automatically stopped.As it can be seen that by voice control, it can be convenient for user's It uses, improves the utilization rate of intelligent transportation tool, also improve user experience.

Summary of the invention

The present invention provides a kind of method and apparatus for controlling intelligent transportation tool, to improve the intelligence of smart machine.

The present invention provides a kind of method for controlling intelligent transportation tool, this method comprises:

When the acoustic information for inputting intelligent transportation tool is people's acoustic intelligence, the current speech for obtaining the acoustic information is special Sign;

If the current speech feature is matched with setting characteristic condition, control corresponding with the current speech feature is determined System instruction;

According to the determining control instruction, the intelligent transportation tool is controlled.

As it can be seen that characteristic condition matching is carried out for the phonetic feature of acoustic information, in this way, for specific phonetic feature Specific control instruction can be corresponded to, to can further improve the intelligence and safety of intelligent transportation tool.

In one embodiment of the invention, the current speech feature for obtaining the acoustic information includes:

Voice recognition is carried out to the acoustic information;

When the acoustic information identified is people's acoustic intelligence, by the audio-frequency information of the acoustic information, frequency range duration Information, at least one information in frequency range spacing frequency information and pronunciation information, is determined as the current language of the acoustic information Sound feature.

As it can be seen that phonetic feature can be it is diversified, in this way, may be used in different scenes, so that intelligent transportation The control of tool is more flexible, also safer.

In one embodiment of the invention, if the current speech feature is matched with setting characteristic condition, determining and institute Stating the corresponding control instruction of current speech feature includes:

If the first audio value of the current speech feature sound intermediate frequency information is in preset high-frequency range, and the frequency range When duration corresponding with first audio value is greater than preset duration in duration information, determination is corresponding with the current speech feature Control instruction be stop control instruction;Or,

If the first audio value of the current speech feature sound intermediate frequency information is in preset high-frequency range, and the frequency range When spacing frequency value corresponding with first audio value is greater than the set value in spacing frequency information, the determining and current speech The corresponding control instruction of feature is to stop control instruction.

In this way, can be according between the audio-frequency information and frequency range duration information or audio-frequency information and frequency range of acoustic information It can be determined whether to carry out stopping control every frequency information, thus, in emergency situations, the specific cry that user issues can also stop The only operation of intelligent transportation tool further improves the intelligence and safety of intelligent transportation tool.

In one embodiment of the invention, if the current speech feature is matched with setting characteristic condition, determining and institute Stating the corresponding control instruction of current speech feature includes:

If pronunciation information is matched with preset pronunciation information in the current speech feature, the determining and current speech The corresponding control instruction of feature is to stop control instruction.

As it can be seen that in emergency situations, the specific pronunciation that user issues can also stop the operation of intelligent transportation tool, into one Step improves the intelligence and safety of intelligent transportation tool.

In one embodiment of the invention, the method also includes:

If the current speech feature and setting characteristic condition mismatch, the acoustic information is identified as text letter Breath, and the intelligent transportation tool is controlled according to control instruction corresponding with the text information.

Certainly, normal voice control can be carried out for other acoustic informations, so that the function of intelligent transportation tool is more Add complete, further improves the intelligence of intelligent transportation tool.

The present invention provides a kind of device for controlling intelligent transportation tool, which includes:

Acquiring unit, for obtaining the sound letter when the acoustic information for inputting intelligent transportation tool is people's acoustic intelligence The current speech feature of breath;

Determination unit, if matched for the current speech feature with setting characteristic condition, the determining and current language The corresponding control instruction of sound feature;

Control unit, for controlling the intelligent transportation tool according to the determining control instruction.

As it can be seen that characteristic condition matching is carried out for the phonetic feature of acoustic information, in this way, for specific phonetic feature Specific control instruction can be corresponded to, to can further improve the intelligence and safety of intelligent transportation tool.

In one embodiment of the invention, the acquiring unit is specifically used for carrying out voice recognition to the acoustic information, works as knowledge Not Chu the acoustic information be people's acoustic intelligence when, by the audio-frequency information of the acoustic information, frequency range duration information, frequency range interval At least one information in frequency information and pronunciation information is determined as the current speech feature of the acoustic information.

As it can be seen that phonetic feature can be it is diversified, in this way, may be used in different scenes, so that intelligent transportation The control of tool is more flexible, also safer.

In one embodiment of the invention, the determination unit, if specifically for the current speech feature sound intermediate frequency information First audio value in preset high-frequency range, and it is corresponding with first audio value in the frequency range duration information when grow up When preset duration, determine that control instruction corresponding with the current speech feature is to stop control instruction;Or, if described current First audio value of phonetic feature sound intermediate frequency information in preset high-frequency range, and in the frequency range spacing frequency information with institute When stating the corresponding spacing frequency value of the first audio value and being greater than the set value, control instruction corresponding with the current speech feature is determined To stop control instruction.

In this way, can be according between the audio-frequency information and frequency range duration information or audio-frequency information and frequency range of acoustic information It can be determined whether to carry out stopping control every frequency information, thus, in emergency situations, the cry that user issues can also stop intelligence The operation of the energy vehicles, further improves the intelligence and safety of intelligent transportation tool.

In one embodiment of the invention, the determination unit, if be specifically used for the current speech feature in pronunciation information with When preset pronunciation information matches, determine that control instruction corresponding with the current speech feature is to stop control instruction.

As it can be seen that in emergency situations, the specific pronunciation that user issues can also stop the operation of intelligent transportation tool, into one Step improves the intelligence and safety of intelligent transportation tool.

In one embodiment of the invention, described device further include:

Speech control unit, if mismatched for the current speech feature and setting characteristic condition, by the sound Information is identified as text information, and controls the intelligent transportation tool according to control instruction corresponding with the text information.

Certainly, normal voice control can be carried out for other acoustic informations, so that the function of intelligent transportation tool is more Add complete, further improves the intelligence of intelligent transportation tool.

Some beneficial effects of the embodiment of the present invention may include:

As it can be seen that characteristic condition matching is carried out for the phonetic feature of acoustic information, in this way, for specific phonetic feature Specific control instruction can be corresponded to, such as: in emergency situations, the specific cry or specific pronunciation that user issues are ok Stop the operation of intelligent transportation tool to can further improve the intelligence and safety of intelligent transportation tool.

Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by written explanation Specifically noted structure is achieved and obtained in book, claims and attached drawing.

Below by drawings and examples, technical scheme of the present invention will be described in further detail.

Detailed description of the invention

Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention It applies example to be used to explain the present invention together, not be construed as limiting the invention.In the accompanying drawings:

Fig. 1 is the flow chart of control intelligent transportation tool shown according to an exemplary embodiment;

Fig. 2 is the flow chart according to the control intelligent transportation tool shown in an exemplary embodiment one;

Fig. 3 is the flow chart according to the control intelligent transportation tool shown in an exemplary embodiment two;

Fig. 4 is the structure chart of the device of control intelligent transportation tool shown according to an exemplary embodiment;

Fig. 5 is the structure drawing of device according to the control intelligent transportation tool shown in an exemplary embodiment three.

Specific embodiment

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.

The technical solution that the embodiment of the present disclosure provides, carries out characteristic condition matching for the phonetic feature of acoustic information, In this way, specific control instruction can be corresponded to for specific phonetic feature, and such as: in emergency situations, user issues specific Cry or specific pronunciation can stop the operation of intelligent transportation tool to can further improve the intelligence of intelligent transportation tool It can property and safety.

Fig. 1 is the flow chart of control intelligent transportation tool shown according to an exemplary embodiment.Control intelligent transportation work The process of tool is as shown in Figure 1, comprising:

Step 101: when the acoustic information for inputting intelligent transportation tool is people's acoustic intelligence, obtaining the current language of acoustic information Sound feature.

During using intelligent transportation tool, it might have in many voice input intelligent transportation tools, such as: people Sound, machine operation sound, animal sounds, noise of surrounding enviroment etc..Here, voice recognition technology can be used, it is first determined defeated Whether the acoustic information for entering intelligent transportation tool is people's acoustic intelligence, if so, the current speech feature of acoustic information can be obtained.

In the embodiment of the present disclosure, the phonetic feature of voice can be diversified, such as: the audio-frequency information of acoustic information, Frequency range duration information, frequency range spacing frequency information and pronunciation information.Here, the phonetic feature of acoustic information includes sound letter Audio-frequency information, the frequency range duration information of breath, at least one information in frequency range spacing frequency information and pronunciation information.Such as: Acoustic information is therefore the audio-frequency information of shriek and frequency range duration information can be determined as sound by the lasting shriek of people The current speech feature of message breath.Alternatively, acoustic information be people interruption and rapid cry therefore can be by the sound of shriek Frequency information and frequency range spacing frequency information are determined as the current speech feature of acoustic information.Alternatively, acoustic information is specific hair Message breath, such as:, etc., in this way, specific pronunciation information to be determined as to the current speech feature of acoustic information.

Therefore, the current speech feature for obtaining acoustic information includes: to carry out voice recognition to acoustic information;When what is identified When acoustic information is people's acoustic intelligence, by the audio-frequency information of acoustic information, frequency range duration information, frequency range spacing frequency information and At least one information in pronunciation information is determined as the current speech feature of acoustic information.

Step 102: if current speech feature is matched with setting characteristic condition, determining control corresponding with current speech feature System instruction.

In the embodiment of the present invention, it can be directed to different scenes, preset characteristic condition.Such as: for some urgent feelings Condition, user may be flurried, may scream, or initiate some rapid crys, and therefore, presetting characteristic condition can wrap It includes: the high-frequency range of audio, the corresponding duration of high frequency, corresponding spacing frequency of high frequency etc..For some emergency cases or Emergency, user may issue the pronunciation of some anxieties, such as:, mother etc..Therefore, characteristic condition is preset Can include:, the pronunciation of mother etc..Therefore, characteristic condition is preset can include: the high-frequency range of audio, high frequency are corresponding Duration, the corresponding spacing frequency of high frequency, one of pronunciation of mother etc., two or more.

In this way, if the first audio value of current speech feature sound intermediate frequency information in preset high-frequency range, and when frequency range When duration corresponding with the first audio value is greater than preset duration in long message, control instruction corresponding with current speech feature is determined To stop control instruction.When i.e. user utters a scream, the audio value of shriek i.e. the first audio value in preset high-frequency range, And the duration that user persistently screams is greater than preset duration, to can determine control instruction to stop control instruction.

Alternatively, if the first audio value of current speech feature sound intermediate frequency information in preset high-frequency range, and between frequency range When spacing frequency value corresponding with the first audio value in frequency information is greater than the set value, determination is corresponding with current speech feature Control instruction is to stop control instruction.I.e. user issues rapid intermittent when screaming, the audio value of shriek i.e. the first audio value In preset high-frequency range, and rapid intermittent spacing frequency value is greater than the set value, to can determine that control instruction is to stop Only control instruction.

Alternatively, if determining and current speech is special when pronunciation information is matched with preset pronunciation information in current speech feature Corresponding control instruction is levied to stop control instruction.Have the pronunciation information of " " in the acoustic information of user, then can determine with Preset pronunciation information matching, thus, determine that control instruction corresponding with current speech feature is to stop control instruction.Certainly, There is " mother " in the acoustic information of user, when the pronunciation informations such as " help ", can also determine to match with preset pronunciation information, thus, Determine that control instruction corresponding with current speech feature is to stop control instruction.

Certainly, in the embodiment of the present invention, setting characteristic condition is without being limited thereto, other are directed to different application scene, also presets Different characteristic conditions.

Step 103: according to determining control instruction, controlling intelligent transportation tool.

After control instruction has been determined, the control of intelligent transportation tool can be carried out according to control instruction.It is with intelligent wheel chair Example: if control instruction is to stop control instruction, the movement of intelligent wheel chair can be stopped, so that intelligent wheel chair stops.

As it can be seen that characteristic condition matching is carried out for the phonetic feature of acoustic information, in this way, right in the embodiment of the present invention Specific control instruction can be corresponded in specific phonetic feature, such as: in emergency situations, user issue specific cry or Specific pronunciation, can stop intelligent transportation tool operation to can further improve intelligent transportation tool intelligence and Safety.

Certainly, normal voice control can be carried out for other acoustic informations, so that the function of intelligent transportation tool is more Add complete, further improves the intelligence of intelligent transportation tool.Therefore, in another embodiment of the present invention, further includes: if current When phonetic feature and setting characteristic condition mismatch, acoustic information is identified as text information, and according to corresponding with text information Control instruction control intelligent transportation tool.

Below by operating process set into specific embodiment, the method that the embodiment of the present disclosure provides is illustrated.

Embodiment one, in the present embodiment, intelligent transportation tool is automobile, and phonetic feature includes: audio-frequency information, frequency range duration Information and frequency range spacing frequency information.

Fig. 2 is according to the flow chart of the control intelligent transportation tool shown in an exemplary embodiment one, referring to fig. 2, this reality Apply in example control intelligent transportation tool process include:

Step 201: the acoustic information of input automobile is identified, judge whether it is voice information? if so, executing step 202, otherwise, control process terminates.

Voice recognition technology can be used, the acoustic information of input automobile is identified, when the acoustic information of input automobile When for people's acoustic intelligence, step 202 is executed, otherwise, this control process terminates.

Step 202: obtaining the current speech feature of acoustic information.

Here, if acoustic information is sound of screaming, the audio-frequency information and frequency range duration information of sound of screaming, frequency are obtained Section spacing frequency information.

Step 203: judging the first audio value of current speech feature sound intermediate frequency information in preset high-frequency range? If so, step 204 is executed, it is no to then follow the steps 207.

Here, highest audio value in audio-frequency information can be determined as to the first audio value, or will occur frequency in audio-frequency information The highest audio value of rate is determined as the first audio value.First audio value is compared with preset high-frequency range, if the first sound Frequency is worth in preset high-frequency range, executes step 204, otherwise, executes step 207.

Step 204: judging whether duration corresponding with the first audio value is big in the frequency range duration information of current speech feature In preset duration? if so, executing step 206, otherwise, step 205 is executed.

If duration corresponding with the first audio value is greater than preset duration, 206 are thened follow the steps, otherwise, executes step 205

Step 205: judging interval frequency corresponding with the first audio value in the frequency range spacing frequency information of current speech feature Does is rate value greater than the set value? if so, executing step 206, otherwise, step 207 is executed.

The shriek of user may not be it is lasting, therefore, if corresponding with the first audio value in frequency range spacing frequency information Spacing frequency value when being greater than the set value, execute step 206, otherwise, execute step 207.

Step 206: determining that control instruction corresponding with current speech feature is to stop control instruction, and stop according to determining Only control instruction, control automobile are stopped.

Since sound of screaming continues for some time or screams frequency greater than setting setting value, accordingly, it can be determined that control refers to It enables to stop control instruction, thus, control automobile is stopped.

Step 207: acoustic information being identified as text information, and vapour is controlled according to control instruction corresponding with text information Vehicle.

Certainly, the traveling of voice control automobile can be passed through.

As it can be seen that in this implementation, according to the phonetic feature of some special permissions of acoustic information, intelligent transportation tool can also be carried out Control, in this way, it is some in emergency circumstances, user issue special permission sound.Such as lasting shriek or rapid intermittent Shriek all may make intelligent transportation tool to stop, thus, reduce traffic accident odds, significantly improves intelligence The safety of the energy vehicles.

Embodiment two, in the present embodiment, intelligent transportation tool is intelligent wheel chair, and phonetic feature include: eh, mother oh, rescue The pronunciation informations such as life.

Fig. 3 is the flow chart according to the control intelligent transportation tool shown in an exemplary embodiment two.Referring to Fig. 3, this reality Apply in example control intelligent transportation tool process include:

Step 301: the acoustic information of input intelligent wheel chair is identified, judge whether it is voice information? if so, executing Step 302, otherwise, control process terminates.

Step 302: obtaining the current speech feature of acoustic information.

Here, the current speech feature of acquisition includes: pronunciation information.

Step 303: judging that pronunciation information is matched with preset pronunciation information in current speech feature? if so, executing Step 304, otherwise, step 305 is executed.

Preset pronunciation information include: eh, mother oh, help etc. pronunciation informations.In this way, pronunciation information in current speech feature When having any one preset pronunciation information, step 304 is executed.Such as: pronunciation information includes: in current speech feature, then It can determine that pronunciation information is matched with preset pronunciation information in current speech feature, execute step 304.Alternatively, current speech is special Pronunciation information includes: in sign, and help then can determine that pronunciation information is matched with preset pronunciation information in current speech feature, Execute step 304.Certainly, when pronunciation information is without any one preset pronunciation information in current speech feature, step is executed 305。

Step 304: determining that control instruction corresponding with current speech feature is to stop control instruction, and stop according to determining Only control instruction, control intelligent wheel chair are stopped.

Here, if user issues some specific pronunciations, such as:, help, mother etc. can stop intelligent wheel chair.

Step 305: acoustic information being identified as text information, and intelligence is controlled according to control instruction corresponding with text information It can wheelchair.

Certainly, voice control wheel chair can be passed through.

As it can be seen that the control of intelligent transportation tool is carried out according to the pronunciation of special permission also cocoa, in this way, some in this implementation In emergency circumstances, the special permission pronunciation that user issues, such as:, it all may make intelligent transportation tool to stop, thus, it reduces Traffic accident odds, significantly improves the safety of intelligent transportation tool.

Certainly, different characteristic conditions can be preset.Such as: the pronunciation that includes: of setting characteristic condition and pronunciation are set Timing is long.Different application scenarios, setting characteristic condition can be different, just no longer enumerate.

Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.

According to the process of above-mentioned control intelligent transportation tool, a kind of device for controlling intelligent transportation tool, such as Fig. 4 can be constructed It is shown, the device include: include: acquiring unit 410, determination unit 420 and control unit 430, wherein

Acquiring unit 410, for obtaining acoustic information when the acoustic information for inputting intelligent transportation tool is people's acoustic intelligence Current speech feature.

Determination unit 420, if matched for current speech feature with setting characteristic condition, determining and current speech feature Corresponding control instruction.

Control unit 430, for controlling intelligent transportation tool according to determining control instruction.

As it can be seen that characteristic condition matching is carried out for the phonetic feature of acoustic information, in this way, for specific phonetic feature Specific control instruction can be corresponded to, to can further improve the intelligence and safety of intelligent transportation tool.

In the embodiment of the present invention, acquiring unit 410 is specifically used for carrying out voice recognition to acoustic information, when what is identified When acoustic information is people's acoustic intelligence, by the audio-frequency information of acoustic information, frequency range duration information, frequency range spacing frequency information and At least one information in pronunciation information is determined as the current speech feature of acoustic information.

As it can be seen that phonetic feature can be it is diversified, in this way, may be used in different scenes, so that intelligent transportation The control of tool is more flexible, also safer.

In the embodiment of the present invention, determination unit 420, if specifically for the first audio of current speech feature sound intermediate frequency information Value in preset high-frequency range, and in frequency range duration information duration corresponding with the first audio value be greater than preset duration when, really Fixed control instruction corresponding with current speech feature is to stop control instruction;Or, if the of current speech feature sound intermediate frequency information Spacing frequency value corresponding with the first audio value is big in preset high-frequency range, and in frequency range spacing frequency information for one audio value When setting value, determine that control instruction corresponding with current speech feature is to stop control instruction.

In this way, can be according between the audio-frequency information and frequency range duration information or audio-frequency information and frequency range of acoustic information It can be determined whether to carry out stopping control every frequency information, thus, in emergency situations, the cry that user issues can also stop intelligence The operation of the energy vehicles, further improves the intelligence and safety of intelligent transportation tool.

In the embodiment of the present invention, determination unit 420, if being specifically used for pronunciation information and preset hair in current speech feature When sound information matches, determine that control instruction corresponding with current speech feature is to stop control instruction.

As it can be seen that in emergency situations, the specific pronunciation that user issues can also stop the operation of intelligent transportation tool, into one Step improves the intelligence and safety of intelligent transportation tool.

In the embodiment of the present invention, device further include:

If speech control unit identifies acoustic information mismatch for current speech feature and setting characteristic condition Intelligent transportation tool is controlled at text information, and according to control instruction corresponding with text information.

Certainly, normal voice control can be carried out for other acoustic informations, so that the function of intelligent transportation tool is more Add complete, further improves the intelligence of intelligent transportation tool.

In this way, characteristic condition matching can be carried out for the phonetic feature of acoustic information in the embodiment of the present disclosure, in this way, Specific control instruction can be corresponded to for specific phonetic feature, such as: in emergency situations, user issue specific cry or The specific pronunciation of person, can stop intelligent transportation tool operation to can further improve intelligent transportation tool intelligence with And safety.

The device of embodiment of the present disclosure offer is provided.

Embodiment three, in the present embodiment, intelligent transportation tool is automobile, and phonetic feature includes: audio-frequency information, frequency range duration Information and frequency range spacing frequency information.

Fig. 5 be according to the structure drawing of device of the control intelligent transportation tool shown in an exemplary embodiment three, referring to Fig. 5, In the present embodiment, the device include: include: acquiring unit 410, determination unit 420 and control unit 430, further include voice Control unit 440.

Specifically, the acoustic information of 410 pairs of input automobiles of acquiring unit identifies, when the acoustic information of input automobile is When voice information, the current speech feature of acoustic information is obtained.Wherein, if acoustic information is sound of screaming, sound of screaming is obtained Audio-frequency information and frequency range duration information, frequency range spacing frequency information

Whether determination unit 420 judges the first audio value of current speech feature sound intermediate frequency information in preset high-frequency range It is interior, when the first audio value is in preset high-frequency range, can continue to judge in the frequency range duration information of current speech feature with Whether the corresponding duration of the first audio value is greater than preset duration, if duration corresponding with the first audio value is greater than preset duration, Control instruction corresponding with current speech feature be can determine to stop control instruction.

Or determination unit 420 determines the first audio value of current speech feature sound intermediate frequency information in preset high frequency model When enclosing interior, but duration corresponding with the first audio value is not more than preset duration, it is determined that unit 420 can continue to judge current language Whether spacing frequency value corresponding with the first audio value is greater than the set value in the frequency range spacing frequency information of sound feature, if more than, It can determine control instruction corresponding with current speech feature then to stop control instruction.

To which control unit 430 can control automobile and be stopped according to determining stopping control instruction.

Certainly, however, it is determined that unit 420 determines the first audio value of current speech feature sound intermediate frequency information not in preset height Within the scope of frequency;Or determine current speech feature sound intermediate frequency information the first audio value in preset high-frequency range, but with The corresponding duration of first audio value is not more than preset duration, and spacing frequency value corresponding with the first audio value is also not more than and sets Definite value.At this point, acoustic information can be identified as text information by speech control unit 440, and according to control corresponding with text information System instruction control automobile.

As it can be seen that in this implementation, according to the phonetic feature of some special permissions of acoustic information, intelligent transportation tool can also be carried out Control, in this way, it is some in emergency circumstances, user issue special permission sound.Such as lasting shriek or rapid intermittent Shriek all may make intelligent transportation tool to stop, thus, reduce traffic accident odds, significantly improves intelligence The safety of the energy vehicles.

It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more, The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.) Formula.

The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.

These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.

Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies Within, then the present invention is also intended to include these modifications and variations.

Claims (8)

1. a kind of method for controlling intelligent transportation tool characterized by comprising
When the acoustic information for inputting intelligent transportation tool is people's acoustic intelligence, the current speech feature of the acoustic information is obtained;
If the current speech feature is matched with setting characteristic condition, determine that control corresponding with the current speech feature refers to It enables;
According to the determining control instruction, the intelligent transportation tool is controlled;
Wherein, the current speech feature for obtaining the acoustic information includes: to carry out voice recognition to the acoustic information;When When the acoustic information identified is people's acoustic intelligence, by the audio-frequency information of the acoustic information, frequency range duration information, between frequency range Every at least one information in frequency information and pronunciation information, it is determined as the current speech feature of the acoustic information;
If the current speech feature is matched with setting characteristic condition, control corresponding with the current speech feature is determined If system instruction includes: the first audio value of the current speech feature sound intermediate frequency information in preset high-frequency range, and described When duration corresponding with first audio value is greater than preset duration in frequency range duration information, the determining and current speech feature Corresponding control instruction is to stop control instruction.
2. the method as described in claim 1, which is characterized in that if the current speech feature and setting characteristic condition Timing determines that control instruction corresponding with the current speech feature includes:
If the first audio value of the current speech feature sound intermediate frequency information is in preset high-frequency range, and the frequency range interval When spacing frequency value corresponding with first audio value is greater than the set value in frequency information, the determining and current speech feature Corresponding control instruction is to stop control instruction.
3. the method as described in claim 1, which is characterized in that if the current speech feature and setting characteristic condition Timing determines that control instruction corresponding with the current speech feature includes:
If pronunciation information is matched with preset pronunciation information in the current speech feature, the determining and current speech feature Corresponding control instruction is to stop control instruction.
4. the method as described in claim 1, which is characterized in that the method also includes:
If the current speech feature and setting characteristic condition mismatch, the acoustic information is identified as text information, and The intelligent transportation tool is controlled according to control instruction corresponding with the text information.
5. a kind of device for controlling intelligent transportation tool characterized by comprising
Acquiring unit, for obtaining the acoustic information when the acoustic information for inputting intelligent transportation tool is people's acoustic intelligence Current speech feature;
Determination unit, it is determining special with the current speech if matched for the current speech feature with setting characteristic condition Levy corresponding control instruction;
Control unit, for controlling the intelligent transportation tool according to the determining control instruction;
The acquiring unit is specifically used for carrying out voice recognition to the acoustic information, when the acoustic information identified is When voice information, by the audio-frequency information of the acoustic information, frequency range duration information, frequency range spacing frequency information and pronunciation letter At least one information in breath is determined as the current speech feature of the acoustic information;
The determination unit, if specifically for the current speech feature sound intermediate frequency information the first audio value in preset high frequency In range, and when duration corresponding with first audio value is greater than preset duration in the frequency range duration information, determining and institute The corresponding control instruction of current speech feature is stated to stop control instruction.
6. device as claimed in claim 5, which is characterized in that
The determination unit, if specifically for the current speech feature sound intermediate frequency information the first audio value in preset high frequency In range, and when spacing frequency value corresponding with first audio value is greater than the set value in the frequency range spacing frequency information, Determine that control instruction corresponding with the current speech feature is to stop control instruction.
7. device as claimed in claim 5, which is characterized in that
The determination unit, if matched specifically for pronunciation information in the current speech feature with preset pronunciation information, Determine that control instruction corresponding with the current speech feature is to stop control instruction.
8. device as claimed in claim 5, which is characterized in that described device further include:
Speech control unit, if mismatched for the current speech feature and setting characteristic condition, by the acoustic information It is identified as text information, and the intelligent transportation tool is controlled according to control instruction corresponding with the text information.
CN201610366267.1A 2016-05-27 2016-05-27 A kind of method and apparatus controlling intelligent transportation tool CN106057198B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610366267.1A CN106057198B (en) 2016-05-27 2016-05-27 A kind of method and apparatus controlling intelligent transportation tool

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610366267.1A CN106057198B (en) 2016-05-27 2016-05-27 A kind of method and apparatus controlling intelligent transportation tool

Publications (2)

Publication Number Publication Date
CN106057198A CN106057198A (en) 2016-10-26
CN106057198B true CN106057198B (en) 2019-08-16

Family

ID=57174942

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610366267.1A CN106057198B (en) 2016-05-27 2016-05-27 A kind of method and apparatus controlling intelligent transportation tool

Country Status (1)

Country Link
CN (1) CN106057198B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101840700A (en) * 2010-04-28 2010-09-22 宇龙计算机通信科技(深圳)有限公司 Voice recognition method based on mobile terminal and mobile terminal
CN103259908A (en) * 2012-02-15 2013-08-21 联想(北京)有限公司 Mobile terminal and intelligent control method thereof
CN103287362A (en) * 2013-06-25 2013-09-11 安科智慧城市技术(中国)有限公司 Vehicle-mounted voice control system and method and electric automobile
GB2512313A (en) * 2013-03-26 2014-10-01 Gm Global Tech Operations Inc A system for controlling functions of a vehicle by speech
CN105139858A (en) * 2015-07-27 2015-12-09 联想(北京)有限公司 Information processing method and electronic equipment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101840700A (en) * 2010-04-28 2010-09-22 宇龙计算机通信科技(深圳)有限公司 Voice recognition method based on mobile terminal and mobile terminal
CN103259908A (en) * 2012-02-15 2013-08-21 联想(北京)有限公司 Mobile terminal and intelligent control method thereof
GB2512313A (en) * 2013-03-26 2014-10-01 Gm Global Tech Operations Inc A system for controlling functions of a vehicle by speech
CN103287362A (en) * 2013-06-25 2013-09-11 安科智慧城市技术(中国)有限公司 Vehicle-mounted voice control system and method and electric automobile
CN105139858A (en) * 2015-07-27 2015-12-09 联想(北京)有限公司 Information processing method and electronic equipment

Also Published As

Publication number Publication date
CN106057198A (en) 2016-10-26

Similar Documents

Publication Publication Date Title
US20190355350A1 (en) Modification of electronic system operation based on acoustic ambience classification
KR102137213B1 (en) Apparatus and method for traning model for autonomous driving, autonomous driving apparatus
US9368116B2 (en) Speaker separation in diarization
US10446150B2 (en) In-vehicle voice command recognition method and apparatus, and storage medium
US8417526B2 (en) Speech recognition learning system and method
US8639508B2 (en) User-specific confidence thresholds for speech recognition
TWI576825B (en) A voice recognition system of a robot system ?????????????????????????????? and method thereof
CN104737226B (en) Speech recognition in motor vehicle
US10055190B2 (en) Attribute-based audio channel arbitration
JP4131978B2 (en) Voice recognition device controller
US10282166B2 (en) Enhanced control, customization, and/or security of a sound controlled device such as a voice controlled assistance device
US20140114665A1 (en) Keyword voice activation in vehicles
US7437297B2 (en) Systems and methods for predicting consequences of misinterpretation of user commands in automated systems
US9286030B2 (en) Methods and apparatus for processing multiple audio streams at a vehicle onboard computer system
JP2013546223A (en) Method and system for operating a mobile application in a vehicle
AU2001275616B2 (en) Remote control system for a locomotive using voice commands
US20130253933A1 (en) Voice recognition device and navigation device
CN102999161B (en) A kind of implementation method of voice wake-up module and application
CN104036778A (en) Equipment control method, device and system
US10657945B2 (en) Noise control method and device
CN105895095A (en) Adaptive interactive voice system
US20030158731A1 (en) Word training interface
CA2814300C (en) Post processing of natural language asr
DE102013200378A1 (en) A method and system for using noise related vehicle information to enhance speech recognition
DE102013200380A1 (en) A method and system for using noise related vehicle information to enhance a spoken dialogue

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: No. 101, 1st Floor, 1st Building, Xisanqi Building Materials City, Haidian District, Beijing, 100000

Patentee after: Yunzhisheng Intelligent Technology Co., Ltd.

Address before: 100191, Beijing, Huayuan Road, Haidian District No. 2 peony technology building, block A, 5

Patentee before: BEIJING UNISOUND INFORMATION TECHNOLOGY Co.,Ltd.

CP03 Change of name, title or address
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20200416

Address after: No. 101, 1st Floor, 1st Building, Xisanqi Building Materials City, Haidian District, Beijing, 100000

Co-patentee after: Xiamen yunzhixin Intelligent Technology Co., Ltd

Patentee after: Yunzhisheng Intelligent Technology Co., Ltd.

Address before: No. 101, 1st Floor, 1st Building, Xisanqi Building Materials City, Haidian District, Beijing, 100000

Patentee before: Yunzhisheng Intelligent Technology Co., Ltd.