CN201998942U - Theftproof control device with sound control function for automobile - Google Patents

Theftproof control device with sound control function for automobile Download PDF

Info

Publication number
CN201998942U
CN201998942U CN 201120045800 CN201120045800U CN201998942U CN 201998942 U CN201998942 U CN 201998942U CN 201120045800 CN201120045800 CN 201120045800 CN 201120045800 U CN201120045800 U CN 201120045800U CN 201998942 U CN201998942 U CN 201998942U
Authority
CN
China
Prior art keywords
voice
unit
automobile
sound
dsp
Prior art date
Application number
CN 201120045800
Other languages
Chinese (zh)
Inventor
肇江
邵丽媚
Original Assignee
沈阳君天科技股份有限公司
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 沈阳君天科技股份有限公司 filed Critical 沈阳君天科技股份有限公司
Priority to CN 201120045800 priority Critical patent/CN201998942U/en
Application granted granted Critical
Publication of CN201998942U publication Critical patent/CN201998942U/en

Links

Abstract

The utility model discloses a theftproof control device with a sound control function for an automobile, comprising an automobile starting controller, a remote control unit and a sound acquisition unit. The controller consists of a remote control receiving unit, a sound coding and decoding device, a sound prompt unit, a DSP (digital signal processor) central processor, a storage unit and an ignition loop relay of the automobile. After sound signals acquired by the sound acquisition unit are processed, digital sound signals output by the sound coding and decoding device are transmitted to the DSP central processor, and signals output by the processor control the ignition loop relay of the automobile. The DSP central processor outputs signals, and then prompt sounds are output through the sound prompt unit and a loudspeaker. The remote control receiving unit receives signals of the remote control unit, the signals are processed by the DSP central processor, and the output signals can also control the ignition loop relay of the automobile. Since the ignition system of the automobile is controlled by sounds of the owner of the automobile, the theftproof control device with the sound control function is very convenient to use, and even a theft has the key of the automobile, the automobile can not be driven.

Description

一种具有语音控制功能的汽车防盗控制装置 Having a car alarm voice control means controlling

技术领域 FIELD

[0001] 本设备涉及到汽车防盗、语音识别技术领域,即为一种通过说话人语音识别技术来控制的具有语音控制功能的汽车防盗控制装置。 [0001] The present device relates to a car alarm, a voice identification technology, i.e. a vehicle antitheft control device having a control function to control the speech by speaker speech recognition technology.

背景技术 Background technique

[0002] 汽车防盗系统基本上是现在每辆汽车上所必备的安全设备。 [0002] car alarm system is basically on each car now necessary for security equipment. 现有的防盗系统多数只是进行报警,对盗车人起到警示的作用,但没有从根本上解决车辆被盗窃,而且误报率很高,车辆喇叭声音、放鞭炮及打雷等等都会使其误报警。 Existing anti-theft alarm system but the majority of people play the role of car theft warning, but does not solve the vehicle was stolen from a fundamental, and high false alarm rate, the vehicle horn sounds, fireworks and thunder, and so will make it false alarms. 一些系统可以通过GSM网路以信息或电话的方式将报警信息告知给车主,不过一旦误报率高,会影响车主的正常工作生活,导致当车辆真的被盗了,车主确认为是误报警,不去理会。 Some systems through GSM network to information or call the alarm information to inform the owners, but once the high false alarm rate, will affect the normal working life of the owner, resulting when the vehicle really stolen, the owner confirmed to be false alarms , ignore. 再有一旦车主将钥匙丢失,其他人就可以非常轻易地将车开走。 Once again the owners have lost the key, others can very easily drive away. 这些防盗设备没有从根本上解决汽车被盗窃的问题。 These anti-theft devices do not solve the problem of stolen cars from the fundamental.

实用新型内容 SUMMARY

[0003] 针对上述汽车防盗系统存在的不足,本新型提供一种通过车主的语音控制的具有语音控制功能的汽车防盗控制装置。 [0003] For the above-described disadvantages of car alarm system, the present invention provides a controlled owners car alarm by voice with voice control functions of the control apparatus.

[0004] 为实现本发明的目的,该新型采取如下技术方案: [0004] To achieve the object of the present invention, the novel take the following technical solutions:

[0005] 该汽车防盗控制装置,它主要包括:遥控器、汽车发动控制器及语音采集单元;其汽车发动控制器由遥控接收单元、语音编解码器、语音提示单元、DSP中央处理器、存储单元、汽车点火回路继电器组成并与汽车电源连接;所述语音采集单元将语音信号转化成模拟信号送至语音编解码器输入端,经该解码器输出的数字语音信号传输给DSP中央处理器,经该处理器输出的电流信号送至汽车点火回路继电器输入端,它的常开触点串联到汽车启动电机的回路中,DSP中央处理器输出串口端分别连接存储单元和语音提示单元;所述遥控接收单元接收遥控器的信号,该信号经DSP中央处理器处理输出的信号送至汽车点火回路继电器。 [0005] The vehicle anti-theft control device, which includes: a remote controller, the controller and the car to start voice collecting unit; launch vehicle which is controlled by a remote control receiving unit, a voice codec, a voice prompt unit, the DSP CPU, memory unit, relays and ignition circuit connected to the car power source; said voice collecting unit converts the voice signal into an analog signal to the input of a speech codec, the digital voice signal transmitted through the DSP decoder output to the central processor, a current signal outputted from the processor to the input of the ignition relay circuit, its normally open contact connected in series to the automobile starter motor circuit, the serial output terminal of the DSP central processing unit and the memory are connected to the voice prompts unit; the a remote control signal receiver receives a remote control unit, the signal output from the DSP via the central processor to the ignition circuit relay.

[0006] 所述语音编解码器采立体声音频编解码芯片TLV320AIC23。 The [0006] Mining speech codec stereo audio codec chip TLV320AIC23.

[0007] 所述DSP中央处理器采用芯片TMS320C5509A。 [0007] The central processor DSP chip TMS320C5509A.

[0008] 所述语音采集单元采用拾音器CS-07。 [0008] The microphone uses voice collecting unit CS-07.

[0009] 所述遥控接收单元采用304M接收模块。 [0009] The remote control receiving unit uses reception module 304M.

[0010] 所述语音提示单元采用芯片为ISD4003-04M,该单元输出信号通过扬声器输出语 [0010] The unit uses voice prompts chip ISD4003-04M, the output unit outputs a speech signal through a speaker

首提不。 The first mention.

[0011] 本实用新型与现有技术相比有益效果如下: [0011] The present invention as compared with prior art beneficial effects as follows:

[0012] 该装置的优点在于采用说话人语音识别技术进行车主身份识别。 [0012] The advantage of this arrangement is the use of speaker independent speech recognition technology owner identification. 该技术属于生物认证技术的一种,是一项根据语音波形中反映说话人生理和行为特征的语音参数,自动识别说话人身份的技术。 One such technology is the biometric authentication technology, according to a speech waveform is reflected speaker physiological and behavioral characteristics of the speech parameters, automatic speaker recognition technology identity. 采用高速的DSP数字信号处理器来执行语音识别算法。 The high-speed DSP digital signal processor to perform speech recognition algorithm. 由于汽车的点火系统是通过车主的语音来控制的,使用上特别地方便,只要车主进行正常说话语音就可以,其它都跟正常发动汽车一样,没有附加任何操作。 Since the car's ignition system is controlled by the owner of the voice, especially convenient to use, as long as the owner can carry out normal speaking voice, the other related to the normal start the car, there is no any additional action. 并且即使是盗车人有了车的钥匙,没有车主本人在也无法将车开走。 Even people with car theft and car keys, not the owner, you can not drive away in. 附图说明 BRIEF DESCRIPTION

[0013] 图1为本实用新型结构方框图; A block diagram of [0013] the present invention, the structure of FIG 1;

[0014] 图2为系统主程序工作原理流程图。 [0014] FIG 2 is a main flow chart how the system works.

具体实施方式 Detailed ways

[0015] 下面结合附图对本新型方案进一步详细描述: [0015] DRAWINGS The present novel program further described in detail:

[0016] 如图1所示,为本新型结构方框图。 Shown a block diagram of the new structure of the present [0016] FIG 1. 它主要包括:遥控器、汽车发动控制器及语音采集单元;其汽车发动控制器由遥控接收单元、语音编解码器、语音提示单元、DSP中央处理器、存储单元、汽车点火回路继电器组成并与汽车电源连接;所述语音采集单元将语音信号转化成模拟信号送至语音编解码器输入端,经该解码器输出的数字语音信号传输给DSP 中央处理器,经该处理器输出的电流信号送至汽车点火回路继电器输入端,它的常开触点串联到汽车启动电机的回路中,DSP中央处理器输出串口端分别连接存储单元和语音提示单元;所述遥控接收单元接收遥控器的信号,该信号经DSP中央处理器处理输出的信号送至汽车点火回路继电器。 It includes: a remote controller, the controller and the car to start voice collecting unit; launch vehicle which is controlled by a remote control receiving unit, a voice codec, a voice prompt unit, the DSP CPU, a storage unit, relays and ignition circuit and automotive power; said voice collecting unit converts the voice signal into an analog signal to the input of a speech codec, the digital voice signal transmitted through the DSP decoder output to the central processor, the signal processor output current send automotive ignition relay to the circuit input, its normally open contact connected in series to the automobile starter motor circuit, the serial output terminal of the DSP central processing unit and the memory are connected to the voice prompts unit; the remote control receiving unit receives the remote control signal, the signal output from the DSP via the central processor to the ignition circuit relay.

[0017] 存储单元包括EEPROM存储器和SDRAM存储器,EERPOM存储器采用SPI接口的存储器,用于存储DSP中运行的程序、车主的声音模型及遥控密码等信息,SDRAM存储器采用并行数据及地址总线与DSP接口,DSP读出EEPROM中的程序,转移到SDRAM存储器中执行, 提高程序执行效率。 [0017] The memory cells include EEPROM memory and a SDRAM memory, the memory using the memory EERPOM SPI interface, information for the program stored in the DSP operation, the acoustic model and the owner of the remote password, SDRAM memory address bus and a parallel data interface with the DSP , the DSP reads the program in the EEPROM, SDRAM is transferred to memory for execution, to improve the efficiency of program execution.

[0018] 语音采集单元为拾音器CS-07,它是一种新型拾音器件,具有高灵敏度,低噪音,低失真,体积小,工作电压范围宽等特点,其内置电源反向保护电路,耗电小,传输距离远。 [0018] The voice collecting unit PU CS-07, which is a new pickup element having high sensitivity, low noise, low distortion, small size, wide operating voltage range, etc., which built-in power reversal protection circuit, the power consumption small, transmission distance. 它负责将语音信号转化成模拟信号,以便对语音进行下一步处理。 It is responsible for converting the voice signal into an analog signal for subsequent processing of speech.

[0019] 语音编解码器采用TI公司TLV320AIC23,它是TI公司推出的一款高性能的立体声音频编解码芯片,其模数转换及数模转换部件高度集成在芯片内部,采用了先进的Sigma-delta过采样技术,可以在8K〜96K的频率范围内提供16bit,20bit, 24bit和32bit 的采样,模数转换和数模转换的信噪比分别可以达到90DB和100DB。 [0019] The speech codec the TLV320AIC23 using TI, TI which is introduced a high-performance stereo audio codec chip, the analog to digital conversion and digital to analog conversion element in a highly integrated chip, using advanced Sigma- delta oversampling 16bit may be provided in a frequency range of 8K~96K, 20bit, 24bit, and sampling, analog to digital and digital to analog signal to noise ratio can be achieved, respectively, 32bit 90DB and 100DB. 它可以跟DSP中央处理器的多通道缓冲串口无缝连接,将经过解码后的数字语音信号实时的传输给DSP中央处理器进行处理。 It may be buffered serial multichannel DSP seamless connection with the central processor, through the transmission of real-time digital speech signal decoding processing to the DSP CPU.

[0020] DSP中央处理器为TI公司的TMS320C5509A,它是整个系统的核心部分,具有低功耗、处理速度快等特点,最高主频可以达到300MHZ,它的作用是将输入的语音信号,通过一系列的算法处理,达到识别车主身份的目的。 [0020] DSP central processing unit to the TMS320C5509A TI Company, which is the core of the whole system with low power consumption, processing speed, etc., the highest frequency can reach 300MHZ, it is the role of the voice signal inputted by a series of processing algorithms to achieve the purpose of identifying the identity of the owner. 要达到这个目的,语音处理算法中主要包括: 预处理、特征提取、模型训练、模式匹配以及逻辑决策功能模块。 To achieve this object, the speech processing algorithm mainly includes: preprocessing, feature extraction, model training, pattern matching and decision function block logic.

[0021] (1)预处理:主要包括采样与量化、端点检测、预加重处理、加窗。 [0021] (1) Pretreatment: including sampling and quantization, endpoint detection, pre-emphasis, the windowing.

[0022] (2)特征提取:采用美尔倒谱系数(MFCC)做为说话人个性特征参数,其计算过程是将经过预处理的数字语音信号经过快速傅里叶变换(FFT),再将转换到频域的信号进行频谱取模,再经过三角波滤波器组(Mel滤波器组)进行滤波处理,然后对所有滤波器输出做对数运算,得出的矢量再做离散余弦变换(DCT),最终得到语音信号的特征参数美尔到谱系数(MFCC)。 [0022] (2) Feature extraction: The Mel cepstrum (MFCC) as personality traits speaker parameters pedigree, the calculation process is to go through the pre-digital voice signal through fast Fourier transform (FFT), then signal converted into a frequency domain spectrum modulo, and then through the triangular wave filter bank (Mel filter bank) is filtered, then the filter outputs do all operands derived vectors do discrete cosine transform (DCT) finally obtained characteristic parameters of the speech signal to Mel spectral coefficients (MFCC). [0023] (3)模型训练:对说话人模型的建立和模型参数的训练,即为说话人语音训练过程,预先录入车主的声音样本,经过采样与量化、端点检测、预加重处理、加窗和特征提取后,采用Baum-Welch算法对车主的语音建立隐马尔科夫模型(HMM),也就是车主声音特征样板,并将车主声音特征样板存入EEPROM存储器中。 [0023] (3) model training: training and the establishment of model parameters speaker model, the training process is the speaker's voice, prerecorded sound samples owners, through sampling and quantization, endpoint detection, pre-emphasis, windowing and after feature extraction using Baum-Welch algorithm owners to establish voice hidden Markov model (the HMM), i.e. the owner sound feature template, and stores the audio feature template owner EEPROM memory.

[0024] (4)模式匹配以及逻辑决策:测试音与说话人的距离匹配计算,这个过程的实现即为说话人语音的识别过程,也就是身份辨识的过程。 [0024] (4) pattern matching and logical decision: the test tone and speaker distance matching calculation, realization of this process is the process of identifying human voice to speak, that is, the identity of the process of identification. 首先载入训练的HMM模型,通过对当前说话人语音的录入,进行预处理和特征提取,计算出MFCC参数,并用Viterbi算法计算出MFCC特征与HMM模型的匹配概率,如果二者特征匹配则身份识别通过。 First load HMM model training, by entering the current speaker's voice, preprocessing and feature extraction, calculated MFCC parameters and calculate the probability of a match MFCC feature and HMM model using the Viterbi algorithm, if both feature matching the identity identified by.

[0025] 汽车点火回路继电器,型号为HHC67E-1Z,其位于整个控制电路内部,节点可以通过30A的电流,把它的常开触点串联到汽车启动电机的回路中,它的通断由DSP中央处理器来控制,以达到闭合或切断启动电机回路的目的。 [0025] The ignition circuit relay, model HHC67E-1Z, located inside the entire control circuit 30A through a current node may put its normally open contact connected in series to the automobile starter motor circuit, which is off by the DSP a central processor to control, in order to achieve the purpose of closing or cutting off the motor start circuit.

[0026] 遥控接收单元,配合相应遥控器使用。 [0026] The remote control receiving unit, with the corresponding remote. 遥控接收单元是带有密码保护功能,只有知道密码遥控密码才能在接收到信号后进行相应的动作。 With the remote control receiving unit is password protection, the password only know the password to the remote control operation after receiving the appropriate signal. 其功能主要包括:使用人员注册,只有注册的人员才能通过语音识别系统来发动汽车;当前车辆应用语音识别功能来发动;取消语音识别功能,直接点火。 Its functions include: the use of personnel certification, personnel can only be registered by the launch vehicle speech recognition system; the current vehicle applications such as voice recognition function to launch; cancel the voice recognition function, direct ignition.

[0027] 语音提示单元,采用核心芯片为ISD4003-04M。 [0027] The voice prompt unit, both core chip ISD4003-04M. 单片录放时间4分钟,音质好,采用CMOS技术,内含振荡器、防混淆滤波器、平滑滤波器、音频功率放大器、自动静噪及高密度多电平闪烁存储阵列,录制的声音信息可在断电情况下保存100年,反复录音10万次。 Single recording time of 4 minutes, good sound quality, using CMOS technology, contains an oscillator, anti-aliasing filter, a smoothing filter, audio power amplifier, and an automatic squelch high-density multi-level flash memory array, the sound information can be recorded save 100 years in case of power failure, recording 100,000 times repeatedly. 通过SPI协议与DSP进行通信,DSP的多功能缓冲串口可以方便地与其连接,控制预先存储在该芯片内闪存各个地址声音文件的录放。 Communicating, by the DSP and DSP SPI protocol multifunctional buffered serial port can be easily connected thereto, controlling the flash memory recording each address previously stored sound files in the chip. 该芯片输出的声音信号通过音频功率放大器芯片LM4860经过扬声器输出,其作用在于对当前所要操作步骤进行语音提示,该芯片输出的声音信号通过音频功率放大器芯片LM4860经过扬声器输出,其作用在于对当前所要操作步骤进行语音提示。 A sound signal of the chip output through the speaker output, its role is to the current desired operating step voice prompts through the audio amplifier chip LM4860, the sound signal of the chip output through the speaker output, its role is the audio power amplifier chips LM4860 current desired Procedure for voice prompts. 当进行身份注册时,包括:“请您进行身份注册、请录入语音、请再次录入语音、请等待、身份注册成功”等提示音;当已经注册后,正常使用该语音识别系统时,包括“请录入语音、身份验证失败、请重新录入语音、身份验证成功”等提示音;当使用遥控器时,包括“密码输入错误、功能码输入错误、语音识别系统已取消、语音识别系统已开启、密码修改成功”等提示音。 When the identity of the registrant, including: "Please identity register, please enter a voice, entered voice again, wait, identity registration success" and tone; When you have registered, normal use of the voice recognition system, including " Please enter voice, authentication fails, please re-enter voice authentication success "and tone; when using the remote control, including the" password input error, the function code input errors, the speech recognition system has been canceled, the speech recognition system is turned on, password changed successfully "and beep. 通过这些提示音让车主非常清楚当前系统的工作状态,了解当前需要做什么工作。 These tones let the owner is very clear work status of the current system, what needs to be done to understand the current work.

[0028] 系统装置工作原理及工作过程: [0028] The working principle of the system and working process means:

[0029] 参见附图2,开机时,系统将读取当前状态标志,如果车主首次使用该系统,则有扬声器语音提示,需要先进行身份注册,否则系统将有语音提示直接进入身份验证过程:首先,身份注册需通过遥控器密码系统进入注册模式,注册模式即为对车主语音进行模型训练的过程,其根据系统的提示音重复进行若干次任意短语音的录入,对其进行采样与量化、 端点检测、预加重处理、加窗和特征提取,等待系统为车主建立模型,采用的是Baum-Welch 算法对车主的语音建立隐马尔科夫模型(HMM),建立模型的过程及结束时系统都会做提示, 能够很明确地知道建立模型的进程,当得到系统提示注册结束后,说明模型已建立成功并保存到EEPROM存储器中。 [0029] See Figure 2, when turned on, the system will read the current status flag, if the owner for the first time using the system, the speaker voice prompts, you need to be registered identity, otherwise the system will have voice prompts directly into the authentication process: first, you need to go through the remote identity registration system password registration mode, a registration mode is the voice of the owners of the process model training, which is repeated any number of times in a short speech input according to the tone of the system, which is sampled and quantized, endpoint detection, pre-emphasis, and windowing feature extraction, wait for the system to model the owner, using the Baum-Welch algorithm for establishing hidden Markov model (HMM) speech of the owner, and the process model of the system will end do suggest that it is able to know exactly what the process of building the model, when prompted to get the end of the registration, indicating that the model has been successfully established and saved to the EEPROM memory. 系统下一次重新启动时,就可以正常地使用该语音识别系统了。 When a restart, can normally be used the speech recognition system of the system.

[0030] 点火之前,通过钥匙给系统上电,系统同样要读取状态标志,如果车主已经进行过身份注册,系统将进入身份验证过程,即对车主语音进行识别的过程。 [0030] before the ignition, with the key to the system power-up, the system also have to read the status flag, if the identity of the owner has been registered, the system will enter the authentication process, namely the owners of the speech recognition process. 听到系统装置的语音提示后,就开始进行短语音的录入,该短语音应为车主在注册时所录入的短语音才有效,否则系统将不能正确识别车主身份。 After hearing the voice prompt system device, it began a short speech input, the speech should be short to be effective as a short speech at the registered owners of the entry, otherwise the system will not be able to correctly identify the identity of the owner. 接下来系统对说话人的语音进行识别,同样对该语音进行采样与量化、端点检测、预加重处理、加窗和特征提取这些处理,计算出MFCC参数,并用Viterbi算法计算出MFCC特征与训练时所建立的HMM模型的匹配概率,若匹配成功,则说话人身份被确定为车主,系统会接通汽车点火回路继电器闭合,车主便可以正常地用钥匙发动汽车。 Next, when the system speaker speech recognition, the speech samples with the same quantization, endpoint detection, pre-emphasis, the windowing processing and feature extraction, the calculated MFCC parameters and using the Viterbi algorithm with the training MFCC feature HMM matching probability model established, if the match is successful, the identity of the speaker is determined to be the owner, the system will turn on the car ignition relay circuit is closed, the owner will be able to properly use the key to start the car. 若没有匹配成功,则说话人身份没有被确定,系统将提示再次进行语音录入。 If no match is found, the speaker's identity has not been determined, the system will prompt for voice recording again. 说话人将有3次进行身份验证的机会,如果语音录入次数大于3,系统将不接通点火回路继电器,这时用钥匙也无法发动汽车。 People will have the opportunity to speak three times for authentication, if the voice input is greater than 3 times, the system will not turn on the ignition relay circuit, this time with the key can not start the car.

[0031] 如果车主需要使用遥控器实现相对应功能,则无需在听到录入语音的提示后进行语音录入,等待3次,该3次语音识别过程将不会通过,之后系统将不会再有提示音,此时车主就可以使用遥控器实现相应功能。 [0031] If the owner needs to correspond with the remote control function, there is no need to hear the voice input entered after the voice prompt, wait 3 times, 3 times the process of speech recognition will not pass, then the system will not have tone, then the owner can use the remote control corresponding function. 当车主使用遥控器输入时,DSP中央处理器会通过遥控接收单元接收到加密的编码信息,随即对该信息进行解码,解码后就可以实现该编码所对应的功能。 When the owner inputs using the remote control, the DSP processor will be received by the central unit to the remote receiver the encrypted encoded information, then the information is decoded, decoding the encoded after the corresponding functions may be implemented. 遥控器可以实现的功能主要有以下几项:身份注册,即建立新的说话人语音模型;取消语音识别功能,此时上电不需要通过语音识别,系统直接接通点火回路继电器,车辆可以通过钥匙直接启动;此外还有密码修改功能,可以随时修改遥控密码。 Remote control functions can be achieved mainly the following: Identity Register, namely the establishment of a new speaker voice model; cancel the voice recognition function, this time on the power without going through a voice recognition system is directly connected to the ignition circuit relay, the vehicle can be key direct start; in addition to the password change function, you can modify the remote password at any time.

Claims (6)

1. 一种具有语音控制功能的汽车防盗控制装置,其特征在于:它主要包括:遥控器、汽车发动控制器及语音采集单元;其汽车发动控制器由遥控接收单元、语音编解码器、语音提示单元、DSP中央处理器、存储单元、汽车点火回路继电器组成并与汽车电源连接;所述语音采集单元将语音信号转化成模拟信号送至语音编解码器输入端,经该解码器输出的数字语音信号传输给DSP中央处理器,经该处理器输出的电流信号送至汽车点火回路继电器输入端,它的常开触点串联到汽车启动电机的回路中,DSP中央处理器输出串口端分别连接存储单元和语音提示单元;所述遥控接收单元接收遥控器的信号,该信号经DSP中央处理器处理输出的信号送至汽车点火回路继电器。 CLAIMS 1. A vehicle anti-theft control device having a voice control function, characterized in that: it includes: a remote controller, the controller and the car to start voice collecting unit; launch vehicle which is controlled by a remote control receiving unit, a voice codec, a voice prompting unit, the DSP CPU, a storage unit, relays and ignition circuit connected to the car power source; said voice collecting unit converts the voice signal into an analog signal to the input speech codec, via a digital output of the decoder transmitting the voice signal to the DSP central processing unit, a current signal output from the processor to the input terminal of the relay ignition circuit, its normally open contact connected in series to the automobile starter motor circuit, a central processor DSP serial output terminal connected voice prompt unit and a storage unit; said remote control signal receiving unit receives the remote control, the central processor DSP signal output to the ignition circuit via a relay.
2.按权利要求1所述一种具有语音控制功能的汽车防盗控制装置,其特征在于:所述语音编解码器采用立体声音频编解码芯片TLV320AIC23。 1 2. The vehicle anti-theft control device having a voice control according to claim, wherein: said speech codec uses stereo audio codec chip TLV320AIC23.
3.按权利要求1或2所述一种具有语音控制功能的汽车防盗控制装置,其特征在于: 所述DSP中央处理器采用芯片TMS320C5509A。 1 or 3. The vehicle anti-theft control device 2 having a voice control according to claim, wherein: said central processor DSP chip TMS320C5509A.
4.按权利要求1所述一种具有语音控制功能的汽车防盗控制装置,其特征在于:所述语音采集单元采用拾音器CS-07。 1 4. The vehicle anti-theft control device having a voice control according to claim, wherein: said pickup unit uses voice collecting CS-07.
5.按权利要求1所述一种具有语音控制功能的汽车防盗控制装置,其特征在于:所述遥控接收单元采用304M接收模块。 1 5. The vehicle anti-theft control device having a voice control according to claim, wherein: said remote control receiving unit uses reception module 304M.
6.按权利要求1所述一种具有语音控制功能的汽车防盗控制装置,其特征在于:所述语音提示单元采用芯片为ISD4003-04M,该单元输出端信号通过扬声器输出语音提示。 1 6. The vehicle anti-theft control device having a voice control according to claim, wherein: said voice prompt unit uses chip ISD4003-04M, the signal at the output unit outputs a voice prompts through a speaker.
CN 201120045800 2011-02-18 2011-02-18 Theftproof control device with sound control function for automobile CN201998942U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201120045800 CN201998942U (en) 2011-02-18 2011-02-18 Theftproof control device with sound control function for automobile

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201120045800 CN201998942U (en) 2011-02-18 2011-02-18 Theftproof control device with sound control function for automobile

Publications (1)

Publication Number Publication Date
CN201998942U true CN201998942U (en) 2011-10-05

Family

ID=44701698

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201120045800 CN201998942U (en) 2011-02-18 2011-02-18 Theftproof control device with sound control function for automobile

Country Status (1)

Country Link
CN (1) CN201998942U (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102582576A (en) * 2012-03-15 2012-07-18 福州海景科技开发有限公司 Vehicular burglary prevention and personal safety protection system based on voice recognition technique
CN103448632A (en) * 2012-05-28 2013-12-18 百度在线网络技术(北京)有限公司 Automobile control method and device
CN103573093A (en) * 2013-07-31 2014-02-12 周志敏 Control system for vehicle trunk lid capable of being opened and closed through speech control
CN104679683A (en) * 2015-03-20 2015-06-03 四川特伦特科技股份有限公司 DSP (Digital Signal Processor) processing plate with remote-controlled opening function
CN105227555A (en) * 2015-09-30 2016-01-06 广州汽车集团股份有限公司 Equipment starting method and system
CN105292130A (en) * 2014-07-21 2016-02-03 广州汽车集团股份有限公司 Method and system for imbedding voice standard data, and method and system for controlling vehicles to start through voice
CN106204855A (en) * 2016-08-09 2016-12-07 福建省汽车工业集团云度新能源汽车股份有限公司 A kind of Application on Voiceprint Recognition automobile accessing method
TWI581992B (en) * 2014-11-26 2017-05-11 鴻海精密工業股份有限公司 Vehicle intelligent key system

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102582576A (en) * 2012-03-15 2012-07-18 福州海景科技开发有限公司 Vehicular burglary prevention and personal safety protection system based on voice recognition technique
CN103448632A (en) * 2012-05-28 2013-12-18 百度在线网络技术(北京)有限公司 Automobile control method and device
CN103448632B (en) * 2012-05-28 2015-11-25 百度在线网络技术(北京)有限公司 Automobile control method and device
CN103573093A (en) * 2013-07-31 2014-02-12 周志敏 Control system for vehicle trunk lid capable of being opened and closed through speech control
CN105292130A (en) * 2014-07-21 2016-02-03 广州汽车集团股份有限公司 Method and system for imbedding voice standard data, and method and system for controlling vehicles to start through voice
TWI581992B (en) * 2014-11-26 2017-05-11 鴻海精密工業股份有限公司 Vehicle intelligent key system
CN104679683A (en) * 2015-03-20 2015-06-03 四川特伦特科技股份有限公司 DSP (Digital Signal Processor) processing plate with remote-controlled opening function
CN104679683B (en) * 2015-03-20 2018-01-05 四川特伦特科技股份有限公司 A kind of DSP process plates with remote control open function
CN105227555A (en) * 2015-09-30 2016-01-06 广州汽车集团股份有限公司 Equipment starting method and system
CN106204855A (en) * 2016-08-09 2016-12-07 福建省汽车工业集团云度新能源汽车股份有限公司 A kind of Application on Voiceprint Recognition automobile accessing method

Similar Documents

Publication Publication Date Title
CN1220176C (en) Method for training or adapting to a phonetic recognizer
US8483854B2 (en) Systems, methods, and apparatus for context processing using multiple microphones
US9542933B2 (en) Microphone circuit assembly and system with speech recognition
US8285545B2 (en) Voice command acquisition system and method
EP1171870B1 (en) Spoken user interface for speech-enabled devices
EP1732352A1 (en) Detection and suppression of wind noise in microphone signals
US6671669B1 (en) combined engine system and method for voice recognition
US20110153326A1 (en) System and method for computing and transmitting parameters in a distributed voice recognition system
CN1228761C (en) System and method for noise-compensated speech recognition
US8560313B2 (en) Transient noise rejection for speech recognition
EP1933303A1 (en) Speech dialog control based on signal pre-processing
EP1054390A2 (en) Method and apparatus for addressing voice controlled devices
EP1054389A2 (en) Method and apparatus for machine to machine communication using speech recognition
US7676363B2 (en) Automated speech recognition using normalized in-vehicle speech
US20020193989A1 (en) Method and apparatus for identifying voice controlled devices
US20070033020A1 (en) Estimation of noise in a speech signal
US20060206320A1 (en) Apparatus and method for noise reduction and speech enhancement with microphones and loudspeakers
US20030130852A1 (en) Headset with radio communication function for speech processing system using speech recognition
CN101437449B (en) Method and apparatus for characterizing acoustical outer ear
KR100923896B1 (en) Method and apparatus for transmitting speech activity in distributed voice recognition systems
US5706399A (en) Speech controlled vehicle alarm system
US8112280B2 (en) Systems and methods of performing speech recognition with barge-in for use in a bluetooth system
CN100476949C (en) Multichannel voice detection in adverse environments
CN1244907C (en) High frequency intensifier coding method for broadband speech coder and decoder and apparatus
CN101681619B (en) Improved voice activity detector

Legal Events

Date Code Title Description
C14 Granted