CN105976815A - Vehicle voice recognition method and vehicle voice recognition device - Google Patents

Abstract

A vehicle voice recognition method and a vehicle voice recognition device provided by the invention relate to the technical field of voice recognition. Through the method and the device, a vehicle voice recognition system can serve passengers in addition to the driver. The method comprises the following steps: acquiring voice information received by a voice pickup module configured on each seat in a vehicle, wherein the microphone of each voice pickup module receives the voice information input by a passenger on the corresponding seat; reducing the dimension of the voice information; carrying out signal processing on the dimension-reduced voice information according to the parameter information corresponding to each channel of voice information in the voice information to get a voice signal; and finally, carrying out voice recognition based on the voice signal. The vehicle voice recognition method and the vehicle voice recognition device are applicable to vehicle voice recognition.

Description

Vehicle-mounted speech recognition method and device

technical field

The invention relates to the technical field of voice recognition, in particular to a method and device for vehicle-mounted voice recognition.

Background technique

With the development of science and technology, speech recognition technology is becoming more and more mature, especially widely used in vehicle speech recognition systems. For the pickup module microphone in the vehicle speech recognition system, it is usually used to receive the voice information of the driver or passenger, navigate, make and receive calls, control the car or interact with the car Internet car entertainment system, etc.

At present, the pickup module microphone in the existing vehicle-mounted speech recognition system is generally only installed at the dome light or the A-pillar position of the car, and can only serve the driver. This single pickup device and its special placement cannot meet the needs of the future. The Internet vehicle central control and entertainment system prevents the vehicle voice recognition system from serving passengers other than the driver.

Contents of the invention

Embodiments of the present invention provide a vehicle-mounted voice recognition method and device to solve the problem that the current vehicle-mounted voice recognition system cannot serve passengers other than the driver.

Aiming at the problems existing in the prior art, the embodiment of the present invention provides a vehicle-mounted speech recognition method, including:

Obtain the voice information received by the pickup module microphone configured on each seat in the car, wherein each pickup module microphone receives the voice information input by the passenger in the corresponding seat;

performing noise reduction processing on the voice information;

performing signal processing on the noise-reduced voice information to obtain a voice signal according to parameter information corresponding to each channel of voice information in the voice information;

Voice recognition is performed on the voice signal.

An embodiment of the present invention provides a vehicle-mounted speech recognition device, including:

The acquiring unit is used to acquire the voice information received by the pickup module microphone configured on each seat in the vehicle, wherein each pickup module microphone receives the voice information input by the passenger in the corresponding seat;

a processing unit, configured to perform noise reduction processing on the voice information;

The processing unit is further configured to perform signal processing on the noise-reduced voice information to obtain a voice signal according to parameter information corresponding to each channel of voice information in the voice information;

The recognition unit is configured to perform speech recognition on the speech signal.

In the vehicle-mounted voice recognition method and device provided by the embodiments of the present invention, firstly, the voice information received by the pickup module microphone configured on each seat in the vehicle is obtained, wherein each pickup module microphone receives the voice information input by the passenger in the corresponding seat. voice information; then performing noise reduction processing on the voice information; then according to the parameter information corresponding to each voice information in the voice information, signal processing is performed on the voice information after the noise reduction processing to obtain a voice signal; finally, the voice signal is signal for speech recognition. Compared with the current vehicle-mounted voice recognition system that only serves the driver, the present invention can obtain the voice information of passengers in the vehicle except the driver through the microphone of the pickup module arranged on each seat in the vehicle and perform corresponding voice recognition , can realize the car voice recognition system to serve passengers other than the driver, and can meet the future Internet car central control and entertainment system.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

Fig. 1 is a schematic flow chart of a vehicle-mounted speech recognition method provided by an embodiment of the present invention;

FIG. 2 is a schematic flow chart of another vehicle-mounted voice recognition method provided by an embodiment of the present invention;

3 is a schematic structural diagram of a vehicle-mounted speech recognition device provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of the physical structure of a vehicle-mounted speech recognition device provided by an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of another vehicle-mounted speech recognition device provided by an embodiment of the present invention.

detailed description

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

The embodiment of the present invention provides a vehicle-mounted speech recognition method, as shown in Figure 1, the method includes:

101. Obtain the voice information received by the microphone of the pickup module configured on each seat in the car.

Wherein, each pickup module microphone receives voice information input by a corresponding seat passenger, and the voice information received by each pickup module microphone corresponds to one channel of voice information.

Specifically, the input angle corresponding to each sound pickup module microphone can be preset, so that each sound pickup module microphone can only receive the voice information input by the corresponding seat passenger.

102. Perform noise reduction processing on the voice information.

Specifically, according to the frequency parameter corresponding to the voice information, the voice whose frequency value exceeds a preset range can be eliminated, and the preset range can be configured according to the frequency parameter range of the user's normal voice call.

For the embodiment of the present invention, by performing noise reduction processing on the voice information, noises such as the sound of opening and closing doors, wind noise, engine sound, and tire noise can be filtered out, thereby improving the accuracy of voice recognition.

103. Perform signal processing on the noise-reduced voice information to obtain a voice signal according to parameter information corresponding to each channel of voice information in the voice information.

Wherein, the parameter information may include time information, frequency information, energy information and the like corresponding to the voice information.

For the embodiment of the present invention, there may be multiple channels of voice information in the voice information, and each channel of voice information may correspond to a sound source. For example, there are three channels of voice information in the voice information, namely channel a, channel b, and channel c, wherein the source of sound corresponding to channel a is the voice from user a, and the source of sound corresponding to channel b is the voice from user b. The sound source corresponding to channel c is the voice uttered by user c.

For example, there are three channels of voice information in the voice information, namely channel a, channel b, and channel c. According to the parameter information corresponding to each channel of voice information, it can be determined that the voice information of channel a is the control command voice issued by the user, and channel b and channel c The channel is the voice of the user chatting, not the voice of the control command, because only the voice duration, voice frequency and voice decibel in the voice information of channel a, these three parameters are respectively in the corresponding preset range, among which, for these three The preset ranges corresponding to the parameters can be configured according to the voice parameters when the user normally performs voice control. Therefore, the b-channel and c-channel voice information in the voice information is eliminated, and only the a-channel voice information is retained, and the signal processing is performed to obtain a voice signal, thereby ensuring that only the control instruction voice is voice recognized.

104. Perform voice recognition on the voice signal.

For the embodiment of the present invention, after voice recognition is performed on the voice signal after signal processing, related operations corresponding to the voice information can be performed. After voice recognition, provide users with the service of playing songs.

In the vehicle-mounted voice recognition method provided by the embodiment of the present invention, firstly, the voice information received by the microphone of the pickup module configured on each seat in the vehicle is acquired, wherein each microphone of the pickup module receives the voice information input by the passenger in the corresponding seat Carry out noise reduction processing to described speech information again; Then according to the parameter information corresponding to each road speech information in described speech information, carry out signal processing to the speech information after noise reduction processing to obtain speech signal; Finally, carry out to described speech signal Speech Recognition. Compared with the current vehicle-mounted voice recognition system that only serves the driver, the present invention can obtain the voice information of passengers in the vehicle except the driver through the microphone of the pickup module arranged on each seat in the vehicle and perform corresponding voice recognition , can realize the car voice recognition system to serve passengers other than the driver, and can meet the future Internet car central control and entertainment system.

The embodiment of the present invention provides another vehicle-mounted speech recognition method, as shown in Figure 2, the method includes:

201. Obtain the voice information received by the microphone of the pickup module configured on each seat in the car.

Wherein, each pickup module microphone receives voice information input by a corresponding seat passenger, and the voice information received by each pickup module microphone corresponds to one channel of voice information.

For the embodiment of the present invention, when the sound pickup module microphone installed in the car detects that the voice input command input by the user is received, the on-board voice recognition device is triggered to obtain the voice received by the sound pickup module microphone configured on each seat in the car. information. The voice input instruction may include preset keyword information, and the specific content in the preset keyword information may be configured according to actual needs, for example, the preset keyword information may be configured as a keyword of "Hello super car" Information, when the user says the voice information of "Hello Super Car" to the microphone of the pickup module, the microphone of the pickup module detects that the voice input command input by the user is received, and triggers the on-board voice recognition device to obtain the information of each seat in the car. Voice information received by the pickup module microphone configured on the phone for further voice recognition.

It should be noted that when the microphone of the pickup module installed in the car detects that the voice input command input by the user is received, the on-board voice recognition device is triggered to obtain the voice received by the microphone of the pickup module installed on each seat in the car. Information, to avoid obtaining some voice information that is not actually required by the user for voice recognition, and avoid performing related voice recognition operations on useless voice information for a long time, thereby saving resources and waste.

202. Perform noise reduction processing on the voice information.

For the embodiment of the present invention, by performing noise reduction processing on the voice information, noises such as the sound of opening and closing doors, wind noise, engine sound, and tire noise can be filtered out, thereby improving the accuracy of voice recognition.

203. Perform signal processing on the noise-reduced voice information to obtain a voice signal according to parameter information corresponding to each channel of voice information in the voice information.

Wherein, the parameter information includes time information, energy information and frequency information. The time information may include the duration of the voice, the energy information may include the decibel value of the voice, and the frequency information may include the frequency value of the voice.

For the embodiment of the present invention, the step 203 may specifically include: according to the time information, energy information, and frequency information corresponding to each channel of voice information in the voice information, extracting from the noise-reduced voice information that meets the preset parameter conditions voice information, and perform signal processing to obtain the voice signal. Wherein, the preset parameter condition is that the voice duration is within a preset time range and/or the voice decibel is within a preset energy range and/or the voice frequency is within a preset frequency range. The preset time range, preset energy range, and preset frequency range may be configured according to voice parameters when the user normally performs voice control. For example, the preset time range corresponding to the voice duration can be configured between 3 seconds and 5 seconds, the preset energy range corresponding to the voice decibel can be configured between 60 decibels and 80 decibels, and the preset frequency corresponding to the voice frequency The range can be configured between 4000 Hz and 5000 Hz.

For example, there are three channels of voice information in the voice information, which are channel a, channel b, and channel c. Among them, the voice duration of channel a is 10 seconds, the voice decibel is 10 decibels, and the voice frequency is 3000 Hz; The voice duration of the information is 1 second, the voice decibel is 120 decibels, and the voice frequency is 6000 Hz; the voice duration of the c-channel voice information is 4 seconds, the voice decibel is 70 decibels, and the voice frequency is 5000 Hz. Among the three voice messages, only c The voice duration, voice decibel, and voice frequency in the voice information of channel c, these three parameters are respectively within the corresponding preset ranges, it can be determined that channel c is the sound produced by the user when the user normally performs voice control, therefore, the voice information in the voice information The voice information of channel a and channel b is eliminated, and only the voice information of channel c is retained, and the corresponding signal processing is performed to obtain the voice signal.

204. Perform voice recognition on the voice signal.

205. Obtain seat identification information corresponding to the voice information meeting the preset parameter condition.

Wherein, the seat identification information may be a seat number or an ID (Identity, identification number) number and the like.

206. Determine authority information corresponding to the seat identification information.

Wherein, the authority information corresponding to each seat identification information can be preconfigured according to actual needs, for example, the authority of the driver is preconfigured higher, and the authority of ordinary passengers is preconfigured lower.

207. According to the permission information, determine whether to perform related operations after the speech recognition.

For example, the voice information that meets the preset parameter conditions is received by the No. 2 sound pick-up module microphone, and the seat identification information corresponding to the No. 2 sound pickup module microphone is obtained, specifically seat No. 2 (ordinary passenger seat), which can be determined with The authority level corresponding to the seat identification information is low, and this authority level can only obtain the service of the entertainment function, but cannot obtain the service of controlling the car. After voice recognition, it is recognized that the relevant operation corresponding to the voice information is to obtain the service of controlling the car. Since the corresponding authority level is low, the relevant operation of obtaining the service of controlling the car cannot be performed.

It should be noted that by obtaining the seat identification information corresponding to the voice information that meets the preset parameter conditions, determining the authority information corresponding to the seat identification information, and determining whether to perform related operations after voice recognition according to the authority information, it can be realized in While making the vehicle-mounted language recognition system serve passengers other than the driver, the vehicle is safely controlled to ensure the normal running of the vehicle.

Further, the method further includes: when the microphone of the pickup module receives an instruction to stop voice recording input by the user, receiving trigger information sent by the microphone of the pickup module; Voice information received by the microphone of the audio module.

For the embodiment of the present invention, when there is an empty seat in the car, it is not necessary to recognize the voice information received by the sound pickup module microphone on the seat, and by stopping acquiring the voice information received by the sound pickup module microphone configured in the empty seat, Waste of resources can be saved.

Another vehicle-mounted voice recognition method provided by the embodiment of the present invention first obtains the voice information received by the microphone of the pickup module configured on each seat in the car, wherein each microphone of the pickup module receives the voice input by the passenger in the corresponding seat information; then carry out noise reduction processing on the voice information; then according to the parameter information corresponding to each voice information in the voice information, carry out signal processing to the voice information after the noise reduction processing to obtain a voice signal; finally the voice signal for voice recognition. Compared with the current vehicle-mounted voice recognition system that only serves the driver, the present invention can obtain the voice information of passengers in the vehicle except the driver through the microphone of the pickup module arranged on each seat in the vehicle and perform corresponding voice recognition , can realize the car voice recognition system to serve passengers other than the driver, and can meet the future Internet car central control and entertainment system.

Further, as a specific implementation of the method shown in FIG. 1 , an embodiment of the present invention provides a vehicle-mounted voice recognition device. As shown in FIG. 3 , the device includes: an acquisition unit 31 , a processing unit 32 , and a recognition unit 33 .

The acquiring unit 31 can be used to acquire the voice information received by the microphone of the pickup module arranged on each seat in the vehicle, wherein each microphone of the pickup module receives the voice information input by the passenger in the corresponding seat. The acquisition unit 31 is a main functional module for acquiring voice information in the device.

The processing unit 32 may be configured to perform noise reduction processing on the voice information acquired by the acquiring unit 31 .

The processing unit 32 may also be configured to perform signal processing on the noise-reduced voice information to obtain a voice signal according to parameter information corresponding to each channel of voice information in the voice information. Described processing unit 32 is the main function module that carries out denoising processing to speech information in this device, and described processing unit 32 extracts effective speech information in the multi-channel speech information through parameters such as speech energy, speech frequency, speech duration, and carries out Signal processing to obtain speech signals for speech recognition.

The recognition unit 33 may be used to perform speech recognition on the speech signal. The recognition unit 33 is a main functional module for performing speech recognition on the processed speech signal in the device.

It should be noted that, for other corresponding descriptions of the functional units involved in the vehicle-mounted speech recognition device provided by the embodiment of the present invention, reference may be made to the corresponding description in FIG. 1 , which will not be repeated here. In the embodiment of the present invention, a hardware processor (hardware processor) may be used to implement related functional modules.

Exemplarily, as shown in FIG. 4, FIG. 4 shows a schematic diagram of the physical structure of a vehicle-mounted speech recognition device provided by an embodiment of the present invention. The vehicle-mounted speech recognition device may include: a processor (processor) 41, a communication interface ( Communications Interface) 42, a memory (memory) 43 and a bus 44, wherein the processor 41, the communication interface 42, and the memory 43 complete mutual communication through the bus 44. The communication interface 42 can be used for information transmission between the server and the client. The processor 41 can call the logic instructions in the memory 43 to perform the following method: first, obtain the voice information received by the microphone of the pickup module configured on each seat in the car, wherein each microphone of the pickup module receives the voice information received by the passenger in the corresponding seat. input voice information; then performing noise reduction processing on the voice information; then according to the parameter information corresponding to each voice information in the voice information, signal processing is performed on the voice information after the noise reduction processing to obtain a voice signal; finally The above speech signal is used for speech recognition. In addition, the logic instructions in the above-mentioned memory 43 may be implemented in the form of software function units and when sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. .

A vehicle-mounted voice recognition device provided by an embodiment of the present invention first obtains the voice information received by the sound pickup module microphone configured on each seat in the car, wherein each sound pickup module microphone receives the voice information input by the passenger in the corresponding seat Carry out noise reduction processing to described speech information again; Then according to the parameter information corresponding to each road speech information in described speech information, carry out signal processing to the speech information after noise reduction processing to obtain speech signal; Finally, carry out to described speech signal Speech Recognition. Compared with the current vehicle-mounted voice recognition system that only serves the driver, the present invention can obtain the voice information of passengers in the vehicle except the driver through the microphone of the pickup module arranged on each seat in the vehicle and perform corresponding voice recognition , can realize the car voice recognition system to serve passengers other than the driver, and can meet the future Internet car central control and entertainment system.

Further, as a specific implementation of the method shown in FIG. 2 , the embodiment of the present invention provides another vehicle-mounted voice recognition device. As shown in FIG. 5 , the device includes: an acquisition unit 51 , a processing unit 52 , and a recognition unit 53 .

The acquiring unit 51 can be used to acquire the voice information received by the microphone of the pickup module arranged on each seat in the vehicle, wherein each microphone of the pickup module receives the voice information input by the passenger in the corresponding seat. The acquisition unit 51 is a main functional module for acquiring voice information in the device.

The processing unit 52 may be configured to perform noise reduction processing on the voice information acquired by the acquiring unit 51 .

The processing unit 52 may also be configured to perform signal processing on the noise-reduced voice information to obtain a voice signal according to parameter information corresponding to each channel of voice information in the voice information. Described processing unit 52 is the main function module that noise reduction processing is carried out to speech information in this device, and described processing unit 52 extracts effective speech information in the multi-channel speech information through parameters such as speech energy, speech frequency, speech duration, and carries out Signal processing to obtain speech signals for speech recognition.

The recognition unit 53 may be used to perform speech recognition on the speech signal. The recognition unit 53 is a main functional module for performing speech recognition on the processed speech signal in the device.

Optionally, the parameter information includes time information, energy information and frequency information.

The processing unit 52 can be specifically configured to extract voice information that meets preset parameter conditions from the voice information after noise reduction processing according to the time information, energy information, and frequency information corresponding to each channel of voice information in the voice information, And carry out signal processing to obtain the voice signal.

Optionally, the preset parameter condition may be that the voice duration is within a preset time range, and/or the voice decibel is within a preset energy range, and/or the voice frequency is within a preset frequency range.

Further, the device further includes: a determination unit 54 .

The acquiring unit 51 may also be configured to acquire seat identification information corresponding to the voice information meeting the preset parameter conditions.

The determining unit 54 may be configured to determine authority information corresponding to the seat identification information.

The determining unit 54 may also be configured to determine whether to perform related operations after voice recognition according to the authority information.

Further, the device further includes: a receiving unit 55 .

The receiving unit 55 may be configured to receive trigger information sent by the microphone of the voice pickup module when the microphone of the pickup module receives an instruction to stop voice recording input by the user.

The acquiring unit 51 may also be configured to stop acquiring the voice information received by the microphone of the sound pickup module according to the trigger information.

It should be noted that for other corresponding descriptions of the functional units involved in another vehicle-mounted speech recognition device provided by the embodiment of the present invention, reference may be made to the corresponding descriptions in FIG. 2 , which will not be repeated here. In the embodiment of the present invention, relevant functional modules may be realized by a hardware processor.

Another vehicle-mounted voice recognition device provided by an embodiment of the present invention first acquires the voice information received by the microphone of the pickup module configured on each seat in the car, wherein each microphone of the pickup module receives the voice input by the passenger in the corresponding seat information; then carry out noise reduction processing on the voice information; then according to the parameter information corresponding to each voice information in the voice information, carry out signal processing to the voice information after the noise reduction processing to obtain a voice signal; finally the voice signal for voice recognition. Compared with the current vehicle-mounted voice recognition system that only serves the driver, the present invention can obtain the voice information of passengers in the vehicle except the driver through the microphone of the pickup module arranged on each seat in the vehicle and perform corresponding voice recognition , can realize the car voice recognition system to serve passengers other than the driver, and can meet the future Internet car central control and entertainment system.

The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative effort.

Through the above description of the implementations, those skilled in the art can clearly understand that each implementation can be implemented by means of software plus a necessary general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims (10)

1. a vehicle-mounted voice recognition methods, it is characterised in that including:

The voice messaging that in acquisition car, on each seat, the pickup module Mike of configuration receives, wherein, each Pickup module Mike receives the voice messaging of corresponding seat occupant input；

Described voice messaging is carried out noise reduction process；

According to the parameter information that each road voice messaging in described voice messaging is corresponding, after noise reduction process Voice messaging carries out signal processing and obtains voice signal；

Described voice signal is carried out speech recognition.

Vehicle-mounted voice recognition methods the most according to claim 1, it is characterised in that described parameter is believed Breath comprises temporal information, energy information and frequency information, described according to each in described voice messaging The parameter information that road voice messaging is corresponding, carries out signal processing to the voice messaging after noise reduction process and obtains language Tone signal includes:

According to temporal information, energy information and frequency that each road voice messaging in described voice messaging is corresponding Rate information, extracts the voice messaging meeting parameter preset condition the voice messaging after noise reduction process, and Carry out signal processing and obtain voice signal.

Vehicle-mounted voice recognition methods the most according to claim 2, it is characterised in that described default ginseng Said conditions is that voice duration is in preset time range, and/or voice decibel is in preset energy scope, And/or in the range of speech frequency is in predeterminated frequency.

Vehicle-mounted voice recognition methods the most according to claim 2, it is characterised in that described to described After voice signal carries out speech recognition, described method also includes:

Obtain the seat identification information corresponding with the described voice messaging meeting parameter preset condition；

Determine the authority information corresponding with described seat identification information；

According to described authority information, it is determined whether perform the associative operation after speech recognition.

Vehicle-mounted voice recognition methods the most according to claim 1, it is characterised in that described method is also Including:

When pickup module Mike receives the stopping voice typing instruction of user's input, receive described pickup The trigger message that module Mike sends；

According to described trigger message, stop obtaining the voice messaging that described pickup module Mike receives.

6. a vehicle-mounted voice identification device, it is characterised in that including:

Acquiring unit, the voice letter that on each seat, the pickup module Mike of configuration receives in obtaining car Breath, wherein, each pickup module Mike receives the voice messaging of corresponding seat occupant input；

Processing unit, for carrying out noise reduction process to described voice messaging；

Described processing unit, is additionally operable to the parameter corresponding according to each road voice messaging in described voice messaging Information, carries out signal processing to the voice messaging after noise reduction process and obtains voice signal；

Recognition unit, for carrying out speech recognition to described voice signal.

Vehicle-mounted voice identification device the most according to claim 6, it is characterised in that described parameter is believed Breath comprises temporal information, energy information and frequency information,

Described processing unit, specifically for according to each road voice messaging in described voice messaging corresponding time Between information, energy information and frequency information, the voice messaging after noise reduction process extracts meet default The voice messaging of Parameter Conditions, and carry out signal processing and obtain voice signal.

Vehicle-mounted voice identification device the most according to claim 7, it is characterised in that described default ginseng Said conditions is that voice duration is in preset time range, and/or voice decibel is in preset energy scope, And/or in the range of speech frequency is in predeterminated frequency.

Vehicle-mounted voice identification device the most according to claim 7, it is characterised in that described device is also Comprise determining that unit；

Described acquiring unit, is additionally operable to obtain corresponding with the described voice messaging meeting parameter preset condition Seat identification information；

Described determine unit, for determining the authority information corresponding with described seat identification information；

Described determine unit, be additionally operable to according to described authority information, it is determined whether after performing speech recognition Associative operation.

Vehicle-mounted voice identification device the most according to claim 6, it is characterised in that described device Also include: receive unit；

Described reception unit, refers to for receiving the stopping voice typing of user's input as pickup module Mike When making, receive the trigger message that described pickup module Mike sends；

Described acquiring unit, is additionally operable to according to described trigger message, stops obtaining described pickup module Mike The voice messaging received.