CN105869635A - Speech recognition method and system - Google Patents

Speech recognition method and system Download PDF

Info

Publication number
CN105869635A
CN105869635A CN201610142719.8A CN201610142719A CN105869635A CN 105869635 A CN105869635 A CN 105869635A CN 201610142719 A CN201610142719 A CN 201610142719A CN 105869635 A CN105869635 A CN 105869635A
Authority
CN
China
Prior art keywords
voice
printer
control
speech recognition
terminal
Prior art date
Application number
CN201610142719.8A
Other languages
Chinese (zh)
Inventor
周子棂
Original Assignee
江苏时间环三维科技有限公司
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 江苏时间环三维科技有限公司 filed Critical 江苏时间环三维科技有限公司
Priority to CN201610142719.8A priority Critical patent/CN105869635A/en
Publication of CN105869635A publication Critical patent/CN105869635A/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
    • G10L15/06Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • 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

Abstract

The embodiment of the invention provides a speech recognition method and a speech recognition system, belonging to the technical field of speech recognition. The speech recognition method is applied to a speech recognition terminal, and the speech recognition terminal is connected with a printer. The speech recognition method comprises the following steps: receiving speech control information; detecting the state of the printer; searching for a linguistic model corresponding to the state of the printer, wherein a plurality of linguistic models are prestored in the speech recognition terminal, and correspond to the different states of the printer in a one-to-one correspondence manner; calling the found linguistic model, and carrying out recognition on the received speech control information by adopting the linguistic model, thus obtaining a control instruction corresponding to the speech control information; and sending the control instruction to the printer, so that the printer executes the control instruction. With the adoption of the speech recognition method and the speech recognition system, the customizability and the expandability of the speech recognition system are greatly improved.

Description

一种语音识别方法及系统 A speech recognition method and system

技术领域 FIELD

[0001 ]本发明涉及语音识别技术领域,具体而言,涉及一种语音识别方法及系统。 [0001] The present invention relates to the field of speech recognition technology, and in particular, to a method and system for voice recognition.

背景技术 Background technique

[0002]随着语音识别技术的发展,语音识别系统的应用领域越来越广泛。 [0002] With the development of voice recognition technology, the application field of speech recognition system more widely. 现有技术中的语音识别,只能识别指定的词汇。 Speech recognition in the prior art, only recognizes specific vocabulary. 其中,语音识别本质上是一个基于语言模型运算的过程,而预设的语言模型决定了可以识别什么样的关键字。 Among them, the voice recognition is essentially based on a language model calculation process, and the default language model determines what kind of keywords can be identified. 但是传统的语音识别系统的语言模型是固定的,各类指令均使用同一语言模型进行识别,这严重阻碍了语音识别系统的可定制性和可扩展性。 But the traditional model of language speech recognition system is fixed, various types of instructions are using the same language model to identify, which seriously hampered the speech recognition system can be customized and scalable.

发明内容 SUMMARY

[0003]本发明实施例的目的在于提供一种语音识别方法及系统,旨在有效提高语音识别系统的可定制性和可扩展性。 [0003] The object of embodiments of the present invention to provide a speech recognition method and a system designed to improve the speech recognition system can be customizable and extensible.

[0004]本发明实施例是这样实现的: [0004] Example embodiments of the present invention is implemented as follows:

[0005]第一方面,本发明实施例提供的一种语音识别方法,应用于语音识别终端,所述语音识别终端连接有打印机,所述语音识别方法包括: [0005] In a first aspect, a speech recognition method according to an embodiment of the present invention, voice recognition is applied to the terminal, the terminal is connected to a printer voice recognition, the voice recognition method comprising:

[0006]接收语音控制消息。 [0006] receives a voice message control.

[0007]检测所述打印机的状态。 [0007] detecting the state of the printer.

[0008]查找出与所述打印机的状态相对应的语言模型,所述语音识别终端中预存有多个语言模型,所述多个语言模型分别与所述打印机的不同状态一一对应。 [0008] The language model to find out the status of the printer corresponding to the voice recognition terminal plurality prestored language model, the language model respectively the plurality of different states of the printer correspond.

[0009]调用查找出的所述语言模型对接收到的所述语音控制消息进行识别,得到与所述语音控制消息相对应的控制指令。 The voice [0009] Calling the language model to find out the received control message identification to obtain the voice and the control command corresponding to the control message.

[0010]将所述控制指令发送给所述打印机,以使所述打印机执行所述控制指令。 [0010] The control command is sent to the printer, causing the printer to execute the control instruction.

[0011 ]优选地,所述语音识别方法还包括: [0011] Preferably, the speech recognition method further comprises:

[0012]接收由所述打印机发送的控制指令执行反馈,所述控制指令执行反馈中包括执行所述控制指令之后所述打印机的状态。 [0012] receives feedback control command transmitted by the printer, the control command execution state comprises performing feedback control after the instruction of the printer.

[0013]切换为与执行所述控制指令之后所述打印机的状态相对应的语言模型。 [0013] After performing the handover to the state of the printer control commands corresponding to the language model.

[0014]优选地,所述将所述控制指令发送给所述打印机的步骤包括: Said step of transmitting to the printer [0014] Preferably, the said control instructions comprising:

[0015] 监测所述语音识别终端和所述打印机之间的通信链路是否连通,如果未连通,则对所述控制指令进行缓存,如果连通,则将所述控制指令发送给所述打印机。 [0015] Monitoring the communication link between the terminal and the speech recognition printer is in communication, if the communication is not, then the instruction cache control, if the communication, then the control commands to the printer.

[0016]优选地,所述语音识别方法还包括: [0016] Preferably, the speech recognition method further comprises:

[0017]接收语音播报指令。 [0017] The broadcast receiving voice commands.

[0018]查找与所述语音播报指令相对应的语音文件,对所述语音文件进行语音播报,所述语音识别终端中预存有与所述语音播报指令对应的语音文件。 [0018] Finding the instruction corresponding to the voice announcement voice file, the voice file broadcast voice, the voice recognition terminal with the pre-stored voice announcement voice file corresponding to the command.

[0019]优选地,所述调用查找出的所述语言模型对接收到的所述语音控制消息进行识另IJ,得到与所述语音控制消息相对应的控制指令的步骤包括: Step [0019] Preferably, the voice call to find out the language model of the received control message identifying another IJ, and obtain the voice control command corresponding to the control message comprises:

[0020]调用查找出的所述语言模型对接收到的所述语音控制消息进行计算,以获得所述语音控制消息的特征参数,将所述特征参数进行转换得到与所述语音控制消息相对应的控制指令。 [0020] the voice call to find out the language model received control message is calculated to obtain the characteristic parameters of the speech control message, convert the characteristic parameters obtained with the voice message corresponding to the control the control commands.

[0021]第二方面,本发明实施例提供的一种语音识别系统,包括语音识别终端,所述语音识别终端连接有打印机,所述语音识别终端包括: [0021] In a second aspect, the present invention provides A speech recognition system of the embodiment, the terminal includes a voice recognition, the voice recognition terminal is connected to a printer, the voice recognition terminal comprising:

[0022]第一接收单元,用于接收语音控制消息。 [0022] a first receiving means for receiving voice control messages.

[0023]第一检测单元,用于检测所述打印机的状态。 [0023] The first detecting means for detecting a state of the printer.

[0024]第一查找单元,用于查找出与所述打印机的状态相对应的语言模型,所述语音识别终端中预存有多个语言模型,所述多个语言模型分别与所述打印机的不同状态一一对应。 [0024] The first searching unit configured to search the language of the printer model corresponding to the state of the voice recognition terminal plurality of prestored language models, each of said plurality of different language models of the printer state correspondence.

[0025]识别单元,用于调用查找出的所述语言模型对接收到的所述语音控制消息进行识另Ij,得到与所述语音控制消息相对应的控制指令。 The speech language model of the [0025] identification unit configured to find out the call control messages received identifying another Ij, to give a control command to the voice message corresponding to the control.

[0026]发送单元,用于将所述控制指令发送给所述打印机,以使所述打印机执行所述控制指令。 [0026] The transmitting unit for transmitting the control command to the printer to cause the printer to perform the control instruction.

[0027]优选地,所述语音识别终端还包括: [0027] Preferably, the voice recognition terminal further comprises:

[0028]第二接收单元,用于接收由所述打印机发送的控制指令执行反馈,所述控制指令执行反馈中包括执行所述控制指令之后所述打印机的状态。 [0028] The second receiving unit configured to receive control commands sent by the printer to perform feedback, the feedback control comprises performing instruction execution state after the control commands of the printer.

[0029]切换单元,用于切换为与执行所述控制指令之后所述打印机的状态相对应的语言模型。 [0029] The switching unit for switching the state after executing the control instruction corresponding to the printer language model.

[0030]优选地,所述发送单元用于监测所述语音识别终端和所述打印机之间的通信链路是否连通,如果未连通,则对所述控制指令进行缓存,如果连通,则将所述控制指令发送给所述打印机。 [0030] Preferably, the transmission means for monitoring a communication link between the terminal and the speech recognition printer is in communication, if the communication is not, then the instruction cache control, if the communication, then the said control commands to the printer.

[0031 ]优选地,所述语音识别终端还包括: [0031] Preferably, the voice recognition terminal further comprises:

[0032]第三接收单元,用于接收语音播报指令。 [0032] The third receiving unit for receiving a broadcast voice commands.

[0033]第二查找单元,用于查找与所述语音播报指令相对应的语音文件。 [0033] The second searching unit configured to search the voice announcement voice file corresponding to the instruction.

[0034]播报单元,用于对所述语音文件进行语音播报,所述语音识别终端中预存有与所述语音播报指令对应的语音文件。 [0034] The broadcast unit configured to broadcast the audio file voice, the voice recognition terminal with the pre-stored voice announcement voice file corresponding to the command.

[0035]优选地,所述识别单元用于调用查找出的所述语言模型对接收到的所述语音控制消息进行计算,以获得所述语音控制消息的特征参数,将所述特征参数进行转换得到与所述语音控制消息相对应的控制指令。 [0035] Preferably, the means for identifying the voice call to find out the language model received control message is calculated to obtain the characteristic parameters of the speech control message, the characteristic parameter conversion to give a control command to the voice message corresponding to the control.

[0036]本发明实施例提供的语音识别方法及系统,通过在语音识别终端中预存多个语言模型且多个语言模型分别与打印机的不同状态一一对应,使得可以针对性地调用与在打印机不同状态下发出的语音控制消息所对应的语言模型进行控制指令的识别,大大提高了语音识别系统的可定制性和可扩展性。 [0036] The embodiment of the present invention a speech recognition method and system provided by the plurality of language models stored language model and a plurality of speech recognition terminal respectively correspond to different states of the printer, so that the call can be targeted in the printer voice uttered under different state control message corresponding to the language model identification control command, greatly improving the speech recognition system can be customizable and extensible.

附图说明 BRIEF DESCRIPTION

[0037]为了更清楚地说明本发明实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,应当理解,以下附图仅示出了本发明的某些实施例,因此不应该看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。 [0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings are briefly introduced as required for use in the embodiments describing the embodiments, it should be understood that the appended drawings illustrate only certain embodiments of the present invention. , and therefore should not be construed as limiting the scope of those of ordinary skill in the art is concerned, without creative efforts may still obtain other drawings according to these drawings.

[0038]图1为本发明实施例提供的语音识别终端与打印机进行交互的示意图。 [0038] FIG. 1 is a schematic view of the interactive speech recognition terminal and a printer according to an embodiment of the present invention.

[0039]图2为本发明实施例提供的语音识别终端的方框示意图。 [0039] FIG. 2 is a block schematic diagram of a voice recognition terminal according to an embodiment of the present invention.

[0040]图3为本发明实施例提供的语音识别方法的流程图。 [0040] FIG. 3 is a flowchart of speech recognition method according to an embodiment of the present invention.

[0041 ]图4为本发明实施例提供的另一种语音识别方法的流程图。 [0041] FIG 4 is a flowchart of another method of speech recognition according to an embodiment of the present invention.

[0042]图5为本发明实施例提供的另一种语音识别方法的流程图。 [0042] FIG 5 is a flowchart of another method of speech recognition according to an embodiment of the present invention.

[0043]图6为本发明实施例提供的语音识别系统的功能模块示意图。 [0043] FIG. 6 is a schematic diagram of a speech recognition system provided in the embodiment of the present invention the functional module.

[0044]图7为本发明实施例提供的另一种语音识别系统的功能模块示意图。 [0044] FIG. 7 is a schematic of another embodiment of a speech recognition system provided in the function module according to the present invention.

[0045]图8为本发明实施例提供的另一种语音识别系统的功能模块示意图。 [0045] Figure 8 a schematic view of another embodiment of a speech recognition system provided in the function module according to the present invention.

[0046]附图标记汇总: [0046] Summary reference numerals:

[0047] 语音识别终端100;打印机200;存储器300;存储控制器400;处理器500;外设接口600 ;输入输出单元700 ;音频单元800 ;显示单元900 ;第一接收单元101 ;第一检测单元102 ;第一查找单元103;识别单元104;发送单元105;第二接收单元201;切换单元202;第三接收单元301 ;第二查找单元302 ;播报单元303。 [0047] The speech recognition terminal 100; the printer 200; memory 300; a memory controller 400; 500 processor; peripheral interface 600; input-output unit 700; an audio unit 800; a display unit 900; a first receiving unit 101; a first detector unit 102; a first searching unit 103; the recognition unit 104; a transmission unit 105; a second receiving unit 201; a switching unit 202; a third receiving unit 301; a second searching unit 302; broadcast unit 303.

具体实施方式 Detailed ways

[0048]为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。 [0048] In order that the invention object, technical solutions, and advantages of the embodiments more clearly, the following the present invention in the accompanying drawings, technical solutions of embodiments of the present invention are clearly and completely described, obviously, the described the embodiment is an embodiment of the present invention is a part, but not all embodiments. 基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。 Based on the embodiments of the present invention, those of ordinary skill in the art to make all other embodiments without creative work obtained by, it falls within the scope of the present invention.

[0049]应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步定义和解释。 [0049] It should be noted: like reference numerals and letters refer to similar items in the following figures, and thus once an item is defined in one figure, then it need not be in the following figures further defined and interpretation. 同时,在本发明的描述中,术语“第一”、“第二”等仅用于区分描述,而不能理解为指示或暗示相对重要性。 Meanwhile, in the description of the present invention, the terms "first", "second," etc. are used merely to distinguish description, and not intended to indicate or imply relative importance.

[0050]如图1所示,是本发明较佳实施例提供的语音识别终端100与打印机200进行交互的示意图。 [0050] As shown in FIG 1, the printer 200 is a schematic diagram 100 interacts with a voice recognition terminal provided by the preferred embodiment of the present invention. 所述语音识别终端100通过网络与一个或多个打印机200进行通信连接,以进行数据通信或交互。 The voice recognition communication terminal 100 connected by a network to one or more printers 200, for data communication or interaction.

[0051]如图2所示,本实施例提供的一种所述语音识别终端100的方框示意图。 [0051] As shown in FIG 2, a block diagram of a voice identification terminal 100 provided in the present embodiment. 所述语音识别终端100包括存储器300、存储控制器400、处理器500、外设接口600、输入输出单元700、音频单元800、显示单元900。 The voice recognition terminal 100 includes a memory 300, a memory controller 400, processor 500, peripheral interface 600, an input output unit 700, an audio unit 800, a display unit 900.

[0052] 所述存储器300、存储控制器400、处理器500、外设接口600、输入输出单元700、音频单元800、显示单元900各元件相互之间直接或间接地电性连接,以实现数据的传输或交互。 [0052] The memory 300, a memory controller 400, processor 500, peripheral interface 600, an input output unit 700, an audio unit 800, a display is directly or indirectly electrically connected to each other between the respective unit elements 900 to enable data transmission or interaction. 例如,这些元件相互之间可通过一条或多条通讯总线或信号线实现电性连接。 For example, these elements can be achieved electrically connected via one or more communication buses or signal lines with each other.

[°°53] 其中,存储器300可以是,但不限于,随机存取存储器300(Random Access Memory,RAM),只读存储器300(Read Only Memory ,ROM),可编程只读存储器300 (ProgrammableRead-Only Memory,PR0M),可擦除只读存储器300(Erasable Programmable Read-OnlyMemory,EPR0M),电可擦除只读存储器300(Electric Erasable Programmable Read-OnlyMemory,EEPR0M)等。 [°° 53] wherein, the memory 300 may be, but is not limited to, a random access memory 300 (Random Access Memory, RAM), read-only memory 300 (Read Only Memory, ROM), programmable read-only memory 300 (ProgrammableRead- Only memory, PR0M), erasable programmable read only memory 300 (erasable Programmable Read-OnlyMemory, EPR0M), electrically erasable programmable read only memory 300 (electric erasable Programmable Read-OnlyMemory, EEPR0M) and the like. 其中,存储器300用于存储程序,所述处理器500在接收到执行指令后,执行所述程序,前述本发明实施例任一实施例揭示的流程定义的语音识别终端100所执行的方法可以应用于处理器500中,或者由处理器500实现。 Wherein the memory 300 for storing a program, the processor 500 after receiving the execution instruction, executes the program, the present embodiment of the invention, the method according to any embodiment disclosed embodiment a process definition of the embodiment of the voice recognition performed by the terminal 100 may be applied in processor 500 or implemented by the processor 500.

[0054] 处理器500可能是一种集成电路芯片,具有信号的处理能力。 [0054] The processor 500 may be an integrated circuit chip having signal processing capability. 上述的处理器500可以是通用处理器500,包括中央处理器500(Central Processing Unit,简称CPU)、网络处理器500(Network Processor,简称NP)等;还可以是数字信号处理器500(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。 The processor 500 described above may be a general purpose processor 500, includes a central processor 500 (Central Processing Unit, referred to as the CPU), a network processor 500 (Network Processor, referred to as NP) and the like; may also be a digital signal processor 500 (the DSP) specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. 可以实现或者执行本发明实施例中的公开的各方法、步骤及逻辑框图。 It may implement or execute the methods disclosed embodiment, the steps and logic diagram of the present embodiment of the invention. 通用处理器500可以是微处理器500或者该处理器500也可以是任何常规的处理器500等。 A general purpose processor may be a microprocessor 500 or 500 the processor 500 may be any conventional processor 500 and the like.

[0055] 所述外设接口600将各种输入/输入装置耦合至处理器500以及存储器300。 [0055] The peripheral interface 600 to various input / output devices coupled to the processor 500 and a memory 300. 在一些实施例中,外设接口600,处理器500以及存储控制器400可以在单个芯片中实现。 In some embodiments, the peripherals interface 600, a processor 500 and a memory controller 400 may be implemented in a single chip. 在其他一些实例中,他们可以分别由独立的芯片实现。 In some other instances, they may be implemented by separate chips, respectively.

[0056]输入输出单元700用于提供给用户输入数据实现用户与所述语音识别终端100(或打印机200)的交互。 [0056] The input-output unit 700 for providing user input data to a user interact with the voice recognition terminal 100 (or the printer 200). 所述输入输出单元700可以是,但不限于,鼠标和键盘等。 The input-output unit 700 may be, but is not limited to, a mouse and a keyboard.

[0057]音频单元800向用户提供音频接口,其可包括一个或多个麦克风、一个或者多个扬声器以及音频电路。 [0057] The audio unit 800 provide an audio interface to the user, which may include one or more microphones, speakers, and one or more audio circuit.

[0058]显示单元900在所述服务器(或本地终端)与用户之间提供一个交互界面(例如用户操作界面)或用于显示图像数据给用户参考。 [0058] The display unit 900 provides an interface (e.g. user interface) between the server (or local terminal) with the user or to a user for displaying an image data reference. 在本实施例中,所述显示单元900可以是液晶显示器或触控显示器。 In the present embodiment, the display unit 900 may be a liquid crystal display or a touch display. 若为触控显示器,其可为支持单点和多点触控操作的电容式触控屏或电阻式触控屏等。 If a touch display, a capacitive touch screen which can support single and multi-touch operation of resistive touch screen or the like. 支持单点和多点触控操作是指触控显示器能感应到来自该触控显示器上一个或多个位置处同时产生的触控操作,并将该感应到的触控操作交由处理器500进行计算和处理。 Support single and multi-touch operation of the touch display means can sense a touch operation or from a plurality of simultaneously generating at positions on the touch display, and the touch sensing operation referred to processor 500 and calculation process.

[0059]如图3所示,是本发明较佳实施例提供的应用于图2所示的语音识别终端100的语音识别方法的流程图。 [0059] FIG. 3 is a flowchart of embodiment 2, a speech recognition method of the speech recognition is applied to the terminal 100 shown in FIG preferred embodiment of the present invention. 所述语音识别方法应用于语音识别终端100,所述语音识别终端100连接有打印机200,所述语音识别方法包括以下步骤。 The voice recognition method used in speech recognition terminal 100, terminal 100 connected to the voice recognition printer 200, the voice recognition method comprising the following steps.

[0060] SlOl:接收语音控制消息。 [0060] SlOl: receiving a voice control messages.

[0061 ]其中,所述语音识别终端100接收用户发送的语音控制消息,所述语音控制消息包括对所述打印机200的控制内容。 [0061] wherein a user 100 receives the voice recognition control terminal transmits a voice message, the voice message comprises control content 200 of the printer control.

[0062] S102:检测所述打印机200的状态。 [0062] S102: detecting the state of the printer 200.

[0063]具体地,所述打印机200将当前所处的状态信息发送给所述语音识别终端100。 [0063] Specifically, the printer 200 sends status information to the current at which the voice recognition terminal 100. 所述语音识别终端100对接收到的所述状态信息进行检测以获得所述打印机200的状态。 The state of the voice recognition terminal 100 detects the received information to obtain the status of the printer 200.

[0064] S103:查找出与所述打印机200的状态相对应的语言模型,所述语音识别终端100中预存有多个语言模型,所述多个语言模型分别与所述打印机200的不同状态一一对应。 [0064] S103: find out the state of the language model corresponding to a printer 200, a plurality of pre-stored in the language model 100 of the terminal voice recognition, the language model with the plurality of different states of a printer 200, respectively a correspondence.

[0065]具体地,所述语音识别终端100对所述语音控制消息进行提取,得到与所述语音控制消息相对应的关键词。 [0065] In particular, the voice recognition control terminal 100 pairs of the voice message is extracted, and the voice control message to obtain the corresponding keywords. 所述语音识别终端100根据所述关键词查找出与所述打印机200的状态相对应的语言模型。 The terminal voice recognition language model 100 to find out the state of the printer 200 according to the corresponding keyword. 而在所述语音识别终端100中预存有多个语言模型,所述打印机200的不同状态分别对应着不同的所述语言模型。 While in the voice recognition terminal 100 with a plurality of prestored language models, the printer 200 correspond to different states of the different language model.

[0066] S104:调用查找出的所述语言模型对接收到的所述语音控制消息进行识别,得到与所述语音控制消息相对应的控制指令。 [0066] S104: the voice call to find out the language model received a control message to identify, obtain and the voice control command corresponding to the control message.

[0067]具体地,在查找出的所述语言模型中预存有与所述打印机200的状态相对应的控制内容。 [0067] In particular, in the language model to find out the state pre-stored in the printer 200 corresponding to the control content. 所述语音识别终端100根据所述语言模型中的所述控制内容对接收到的所述语音控制消息进行识别,从而得到与所述语音控制消息相对应的控制指令。 The voice recognition of the voice terminal 100 received a control message identifying the language model in accordance with the control content, to give a control command to the voice message corresponding to the control.

[0068] S105:将所述控制指令发送给所述打印机200,以使所述打印机200执行所述控制指令。 [0068] S105: transmitting the control command to the printer 200, the printer 200 to execute the control instruction.

[0069]其中,所述语音识别终端100将得到的所述控制指令发送给所述打印机200,所述打印机200接收到所述控制指令之后便执行所述控制指令。 [0069] wherein, the terminal 100 transmits the voice recognition obtained control commands to the printer 200, the printer executes the control instruction after the control instruction 200 is received.

[0070]实施时,所述打印机200的控制指令包括打印、复印、暂停、停止、启动、删除和翻页。 [0070] When the embodiments, the printer control command 200 includes print, copy, pause, stop, start, and delete page.

[0071 ]如图4所示,所述语音识别方法还包括: [0071] As shown in FIG. 4, the voice recognition method further comprises:

[0072] S201:接收由所述打印机200发送的控制指令执行反馈,所述控制指令执行反馈中包括执行所述控制指令之后所述打印机200的状态。 [0072] S201: control command received by the printer 200 performs feedback of the transmission, the feedback control comprises performing instruction execution state after the control commands of the printer 200.

[0073]其中,所述打印机200执行所述控制指令之后还会将所述控制指令执行后的状态反馈给所述语音识别终端100。 [0073] wherein, after the printer 200 executes the control command will be executed after the state feedback the control instruction to the voice recognition terminal 100. 所述语音识别终端100接收所述控制指令执行反馈,以确保准确获得所述打印机200的当前状态。 The terminal 100 receives the speech recognition instruction performs feedback control to ensure the accuracy of the obtained current status of the printer 200.

[0074] S202:切换为与执行所述控制指令之后所述打印机200的状态相对应的语言模型。 [0074] S202: After switching state to execute the control instruction and the printer 200 corresponding to the language model.

[0075]其中,所述语音识别终端100根据所述打印机200反馈的执行所述控制指令的状态信息,将所述语言模型切换为与所述打印机200当前的状态相对应的语言模型,既能够掌握所述打印机200的执行情况,又能够通过对语言模型的及时切换,快速响应下一个语音控制消息。 [0075] wherein the voice recognition terminal 100 performs the control instruction to the printer 200 according to the state feedback information, the language model to a language model corresponding to the current status of the printer 200, both to the printer control 200 is performed, but also can be promptly switched by the language model, a rapid response to the voice message control.

[0076]进一步地,所述将所述控制指令发送给所述打印机200的步骤包括: The printer 200 in step [0076] Further, the instruction is sent to the control comprising:

[0077] 监测所述语音识别终端100和所述打印机200之间的通信链路是否连通,如果未连通,则对所述控制指令进行缓存,如果连通,则将所述控制指令发送给所述打印机200。 [0077] The monitoring terminal 100 and the voice recognition printer 200 whether the communication link between the communication, if the communication is not, then the instruction cache control, if the communication, then the control commands to the 200 printer.

[0078]在所述语音识别终端100和所述打印机200之间存在一通信链路。 [0078] The presence of a communication link between the voice recognition terminal 100 and the printer 200. 所述语音识别终端100始终对所述通信链路的连接状态进行检测。 The voice recognition terminal 100 is always connected state of the communication link is detected. 当所述通信链路处于未连通的状态时,所述语音识别终端100则对所述控制指令进行缓存。 When the communication link is in non-communication state, the voice recognition control terminal 100 pairs of the instruction cache. 当所述通信链路处于连通状态时,所述语音识别终端100直接将控制指令发送给所述打印机200,当存在缓存的控制指令时,则将缓存的控制指令进行发送。 When the communication link is in communication state, the voice recognition terminal 100 to send control commands directly to the printer 200, when there is a cache control instruction, the control instruction is cached transmitted.

[0079]如图5所示,所述语音识别方法还包括: [0079] As shown in FIG 5, the voice recognition method further comprises:

[0080] S301:接收语音播报指令。 [0080] S301: receiving a broadcast voice commands.

[0081]实施时,所述打印机200可以发送与自身状态相对应的语音播报指令。 [0081] When the embodiment, the printer 200 can transmit its state corresponding to the voice broadcast commands. 所述语音识别终端100接收所述语音播报指令。 The terminal 100 receives the speech recognition instruction voice announcement. 在所述语音识别终端100中预存有与所述语音播报指令对应的语音文件。 In the voice recognition terminal 100 with the pre-stored voice announcement voice file corresponding to the command. 所述语音识别终端100根据所述语音播报指令查找出与所述语音播报指令相对应的语音文件。 The voice recognition terminal 100 to find out the voice announcement voice file corresponding to the instruction based on the voice announcement instruction. 优选通过声卡驱动触发声卡对所述语音文件进行播报。 Preferably the voice trigger sound file broadcast through the sound card driver.

[0082]进一步地,所述调用查找出的所述语言模型对接收到的所述语音控制消息进行识另IJ,得到与所述语音控制消息相对应的控制指令的步骤包括: Step [0082] Further, the voice call to find out the model of the language control messages received identifying another IJ, and obtain the voice control command corresponding to the control message comprises:

[0083]调用查找出的所述语言模型对接收到的所述语音控制消息进行计算和识别,以获得所述语音控制消息的特征参数,将所述特征参数进行转换得到与所述语音控制消息相对应的控制指令。 [0083] the voice call to find out the language model received a control message identification and calculation to obtain the characteristic parameters of the speech control message, convert the characteristic parameters obtained with the voice message control corresponding to the control command.

[0084]优选所述语音识别终端100调用查找出的所述语言模型,根据所述语言模型对接收到所述语音控制消息进行特征参数的提取,并对所述特征参数进行转换以得到与所述语音控制消息相对应的控制指令。 [0084] Preferably, the speech recognition to find out the calling terminal 100 of the language model, the language model according to the received control message to extract the voice characteristic parameters and the characteristic parameters transformed to obtain the said voice control message corresponding to the control command.

[0085]在上述基础上,本发明实施例还提供了一种语音识别系统,其实现原理及产生的技术效果和前述方法实施例相同,为简要描述,系统实施例部分未提及之处,可参考前述方法实施例中相应内容。 [0085] Based on the above, embodiments of the present invention further provides a speech recognition system, the technical effects and the same implementation principles and methods to produce embodiment, as briefly described, the system is not mentioned in the Examples section embodiment, reference Example respective content can foregoing method embodiments.

[0086]如图6所示,本发明实施例提供的一种语音识别系统,包括语音识别终端100,所述语音识别终端100连接有打印机200。 [0086] As shown in FIG. 6, A speech recognition system according to an embodiment of the present invention, the terminal 100 includes a voice recognition, the voice recognition terminal 100 is connected to a printer 200. 所述语音识别终端100包括第一接收单元101、第一检测单元102、第一查找单元103、识别单元104和发送单元105。 The voice recognition terminal 100 includes a first receiving unit 101, a first detection unit 102, the first searching unit 103, the recognition unit 104 and the transmission unit 105.

[0087]所述第一接收单元101用于接收用户发送的语音控制消息,所述语音控制消息包括对所述打印机200的控制内容。 [0087] The first receiving unit 101 for receiving a control message sent by a user's voice, the voice message includes a control content of the control of the printer 200. 关于所述第一接收单元101的描述具体可参对图3中步骤SlOl的描述。 Described with respect to the first receiving unit 101 may be a reference specifically described in step 3 of SlOl FIG. 也即,所述步骤SlOl可以由所述第一接收单元101来执行。 That is, step SlOl can be performed by the first receiving unit 101.

[0088]所述第一检测单元102用于对接收到的所述语音控制消息进行检测,同时根据所述检测结果得到所述打印机200的状态。 [0088] The first state detection unit 102 for controlling the voice message received is detected, and based on the obtained detection result of the printer 200. 关于所述第一检测单元102的描述具体可参对图3中步骤S102的描述。 Description of the first detection unit 102 may specifically be described with reference to step 3 S102 of FIG. 也即,所述步骤S102可以由所述第一检测单元102来执行。 That is, the step S102 may be performed by the first detecting unit 102.

[0089]所述第一查找单元103用于根据所述关键词查找出与所述打印机200的状态相对应的语言模型。 [0089] The first searching unit 103 for finding out the state of the language model corresponding to the printer 200 according to the keyword. 而在所述语音识别终端100中预存有多个语言模型,所述打印机200的不同状态分别对应着不同的所述语言模型。 While in the voice recognition terminal 100 with a plurality of prestored language models, the printer 200 correspond to different states of the different language model. 关于所述第一查找单元103的描述具体可参对图3中步骤S103的描述。 The description of the first searching unit 103 may specifically reference the description of step S103 of FIG. 3. 也即,所述步骤S103可以由所述第一查找单元103来执行。 That is, the step S103 may be a first lookup is performed by the unit 103.

[0090]所述识别单元104用于对接收到的所述语音控制消息进行识别,从而得到与所述语音控制消息相对应的控制指令。 [0090] The voice recognition unit 104 for the received control message identification to obtain the voice and the control command corresponding to the control message. 其中,在查找出的所述语言模型中预存有与所述打印机200的状态相对应的控制内容。 Wherein, in the language model to find out the state of said pre-stored in the printer 200 corresponding to the control content. 关于所述识别单元104的描述具体可参对图3中步骤S104的描述。 The recognition unit 104 described with respect to detailed description of the parameters may be the step of FIG. 3 S104. 也即,所述步骤SI 04可以由所述识别单元104来执行。 That is, the step SI 04 may be performed by the recognition unit 104.

[0091]所述发送单元105用于将得到的所述控制指令发送给所述打印机200,使得所述打印机200接收到所述控制指令之后便执行所述控制指令。 The [0091] transmitting unit 105 for the resulting control commands to the printer 200, so that the printer 200 receives the control instruction is executed after the control instruction. 关于所述发送单元105的描述具体可参对图3中步骤S105的描述。 Description of the transmission unit 105 may specifically reference in the description of step 3 S105 of FIG. 也即,所述步骤S105可以由所述发送单元105来执行。 That is, the step S105 may be performed 105 by the transmission unit.

[0092]进一步地,如图7所示,所述语音识别系统还包括第二接收单元201和切换单元202。 [0092] Further, as shown in Figure 7, the speech recognition system further comprises a second receiving unit 201 and the switching unit 202.

[0093]具体地,所述第二接收单元201用于接收所述控制指令执行反馈,以确保准确获得所述打印机200的当前状态。 [0093] In particular, the second receiving unit 201 for receiving the instruction execution control feedback to ensure accurate obtain the current status of the printer 200. 其中,所述打印机200执行所述控制指令之后还会将所述控制指令执行后的状态反馈给所述语音识别终端100 O而所述控制指令执行反馈中包括执行所述控制指令之后所述打印机200的状态。 Wherein, after the printer 200 performs the control instruction will be executed after the state feedback the control instruction to the instruction execution control the speech recognition feedback terminal 100 O after the control instruction comprises executing the printer state 200.

[0094]所述切换单元202用于将所述语言模型切换为与所述打印机200的状态相对应的语言模型。 [0094] The switching unit 202 for switching the language model with language model to the printer 200 corresponding to the state. 其中,所述语音识别终端100根据所述打印机200反馈的执行所述控制指令的状态ί目息O Wherein the voice recognition terminal 100 performs the control instruction to the printer 200 according to a state feedback information mesh ί O

[0095] 进一步地,所述语音识别终端100还包括监测单元。 [0095] Further, the voice recognition terminal 100 also includes a monitoring unit. 所述监测单元用于监测所述语音识别终端100和所述打印机200之间的通信链路是否连通,如果未连通,则对所述控制指令进行缓存,如果连通,则将所述控制指令发送给所述打印机200。 The monitoring unit for monitoring the voice recognition terminal 100 and the printer 200 whether the communication link between the communication, if the communication is not, then the instruction cache control, if the communication, then the control instructions 200 to the printer. 其中,在所述语音识别终端100和所述打印机200之间存在一通信链路。 Wherein there is a communication link between the voice recognition terminal 100 and the printer 200. 所述语音识别终端100始终对所述通信链路的连接状态进行检测。 The voice recognition terminal 100 is always connected state of the communication link is detected. 当所述通信链路处于未连通的状态时,所述语音识别终端100则对所述控制指令进行缓存。 When the communication link is in non-communication state, the voice recognition control terminal 100 pairs of the instruction cache. 当所述通信链路处于连通状态时,所述语音识别终端100将缓存的控制指令或者是直接将控制指令发送给所述打印机200。 When the communication link is in communication state, the voice recognition terminal 100 to the cache control command or a control command transmitted directly to the printer 200.

[0096]进一步地,如图8所示,所述语音识别终端100还包括第三接收单元301、第二查找单元302和播报单元303。 [0096] Further, as shown in FIG. 8, the voice recognition terminal 100 further includes a third receiving unit 301, the second searching unit 302 and the broadcast unit 303.

[0097]具体地,所述第三接收单元301接收所述语音播报指令。 [0097] In particular, the third receiving unit 301 receives the broadcast voice commands. 其中,所述打印机200将发送与自身状态相对应的语音播报指令。 Wherein, the printer 200 transmits its state corresponding to the voice broadcast commands. 而在所述语音识别终端100中预存有与所述语音播报指令对应的语音文件。 While in the voice recognition terminal 100 with the pre-stored voice announcement voice file corresponding to the command.

[0098]所述第二查找单元302用于根据所述语音播报指令查找出与所述语音播报指令相对应的语音文件。 [0098] The second searching unit 302 is used to find out the command based on the voice announcement voice announcement voice file corresponding to the instruction.

[0099]优选所述播报单元303用于通过声卡驱动触发声卡对所述语音文件进行播报。 [0099] Preferably, the broadcast through the sound card driving unit 303 for triggering the voice sound file broadcast.

[0100] 进一步地,所述语音识别终端100还包括第二识别单元。 [0100] Further, the voice recognition terminal 100 also includes a second identification unit.

[0101]具体地,所述第二识别单元用于根据所述语言模型对接收到的所述语音控制消息进行计算以识别出所述语音控制消息。 [0101] In particular, the second identification means for controlling the voice message according to the language model is calculated in the received control message identifying the voice. 其中,所述语音识别终端100调用查找出的所述语言模型,对识别出的所述语音控制消息进行特征参数的提取,并对所述特征参数进行转换以得到与所述语音控制消息相对应的控制指令。 Wherein the speech recognition to find out the calling terminal 100 of the language model, the speech recognition of a control message extracting characteristic parameters and the characteristic parameters transformed to obtain the voice and the control message corresponding to the control commands.

[0102]本发明实施例提供的语音识别方法及系统,通过在语音识别终端中预存有多个语言模型且多个语言模型分别与打印机的不同状态一一对应,使得可以针对性地调用与在打印机不同状态下发出的语音控制消息所对应的语言模型进行控制指令的识别,大大提高了语音识别系统的可定制性和可扩展性。 [0102] Speech recognition method and system according to the embodiment of the present invention, by pre-stored in the speech recognition terminal and a plurality of language models are more language models correspond to different states of the printer, so that the call can be targeted in voice messages from the control language model corresponding to a control command identifying different states of the printer, greatly improving the speech recognition system can be customizable and extensible.

[0103]需要说明的是,在本申请所提供的几个实施例中,应该理解到,所揭露装置和方法,可以通过其它的方式实现。 [0103] Incidentally, the present application provides a few examples, it should be understood that the embodiments, the disclosed apparatus and methods may be implemented in other manners. 以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。 Means the above-described embodiments are merely illustrative in nature, e.g., the cell division is merely logical function division, there may be other division in actual implementation.

[0104]所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。 [0104] Those skilled in the art may clearly understand that, for convenience and brevity of description, detailed working process and apparatus elements described above, can refer to the corresponding process in the foregoing method embodiments, not described herein again.

[0105]在本申请所提供的几个实施例中,应该理解到,所揭露的装置和方法,可以通过其它的方式实现。 [0105] In several embodiments provided herein present embodiment, it should be understood that the apparatus and methods disclosed may be implemented in other manners. 以上所描述的装置实施例仅仅是示意性的,例如,附图中的流程图和框图显示了根据本发明的多个实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。 Means the above-described embodiments are merely illustrative, e.g., flowchart and block diagrams in the Figures illustrate the architecture according to the present invention, a plurality of embodiments of the apparatus, methods and computer program products may implement the functions and operating. 在这点上,流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分,所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。 In this regard, the flowchart or block diagrams may represent a portion of each block in a module, segment, or portion of code, a module, segment, or portion of code that comprises one or more devices for implementing the specified logical function executable instructions. 也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。 It should also be noted that, in some implementations Alternatively, the functions noted in the block may be different from the order noted in the figures occur. 例如,两个连续的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。 For example, two consecutive blocks may in fact be executed substantially concurrently, they may sometimes be executed in the reverse order, depending upon the functionality involved may be. 也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或动作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。 Also it is noted that each block of the flowchart in block diagram, as well as combinations and / or block diagrams and / or flowchart block may perform the specified functions or acts dedicated hardware-based systems implemented with , or may be special purpose hardware and computer instructions to implement.

[0106]所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。 [0106] The unit described as separate components may be or may not be physically separate, parts displayed as units may be or may not be physical units, i.e. may be located in one place, or may be distributed to a plurality of networks unit. 可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。 You can select some or all of the units according to actual needs to achieve the object of the solutions of the embodiments.

[0107]另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。 [0107] Additionally, functional units may be integrated in various embodiments of the present invention in a processing unit, separate units may be physically present, may be two or more units are integrated into one unit.

[0108]所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。 [0108] If the function is implemented as a separate product sold or used in the form of a software functional unit may be stored in a computer-readable storage medium. 基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。 Based on such understanding, the technical solutions of the present invention per se or contributing to the prior art or part of the technical solutions may be embodied in a software product, which computer software product is stored in a storage medium, comprising several instructions that enable a computer device (may be a personal computer, a server, or network device) to perform all or part of the steps of the methods of the various embodiments of the present invention. 而前述的存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。 The storage medium includes: U disk, mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access various memories (RAM, Random Access Memory), a magnetic disk, or an optical medium can store program codes .

[0109]需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。 [0109] Incidentally, herein, relational terms such as first and second and the like are only used to distinguish one entity or operation from another entity or action without necessarily requiring or implying these entities the presence of any such actual relationship or order between or operations. 而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素。 Further, the term "comprising", "containing" or any other variation thereof are intended to cover a non-exclusive inclusion, such that the article or device comprising a series of elements includes not only these elements but also other elements not expressly listed. 在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的物品或者设备中还存在另外的相同要素。 Without more constraints, by the wording "include a ......" defined does not exclude the existence of additional identical elements in the element comprising article, or apparatus.

[0110]以上所述,仅为本发明的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本发明的保护范围之内。 [0110] The above are only specific embodiments of the present invention, but the scope of the present invention is not limited thereto, any skilled in the art in the art within the technical scope of the present invention is disclosed, variations may readily occur or Alternatively, it shall fall within the protection scope of the present invention. 因此,本发明的保护范围应所述以权利要求的保护范围为准。 Accordingly, the scope of the present invention should be in the scope of the claims and their equivalents.

Claims (10)

1.一种语音识别方法,应用于语音识别终端,所述语音识别终端连接有打印机,其特征在于,所述语音识别方法包括: 接收语音控制消息; 检测所述打印机的状态; 查找出与所述打印机的状态相对应的语言模型,所述语音识别终端中预存有多个语言模型,所述多个语言模型分别与所述打印机的不同状态一一对应; 调用查找出的所述语言模型对接收到的所述语音控制消息进行识别,得到与所述语音控制消息相对应的控制指令; 将所述控制指令发送给所述打印机,以使所述打印机执行所述控制指令。 1. A speech recognition method used in speech recognition terminal, the voice recognition terminal is connected with a printer, wherein said speech recognition method comprising: receiving a voice control message; detecting a state of the printer; and to find out the said state corresponding to the printer language model, the speech recognition terminal in a plurality of prestored language model, the language model respectively the plurality of different states of the printer correspond; call to find out the language model the speech received control message identification to obtain the voice and the control command corresponding to the control message; transmitting the control commands to the printer to cause the printer to perform the control instruction.
2.根据权利要求1所述的语音识别方法,其特征在于,所述语音识别方法还包括: 接收由所述打印机发送的控制指令执行反馈,所述控制指令执行反馈中包括执行所述控制指令之后所述打印机的状态; 切换为与执行所述控制指令之后所述打印机的状态相对应的语言模型。 The voice recognition method according to claim 1, wherein said speech recognition method further comprises: receiving a control command transmitted by the printer to perform feedback, the feedback control includes the instruction execution control instruction is executed after the states of the printer; switching state and after the execution of the control command corresponding to the printer language model.
3.根据权利要求1所述的语音识别方法,其特征在于,所述将所述控制指令发送给所述打印机的步骤包括: 监测所述语音识别终端和所述打印机之间的通信链路是否连通,如果未连通,则对所述控制指令进行缓存,如果连通,则将所述控制指令发送给所述打印机。 The voice recognition method according to claim 1, wherein the transmitting the control command to the printer comprises the step of: monitoring a communication link between the terminal and the speech recognition printer is communication, if the communication is not, then the instruction cache control, if the communication, then the control commands to the printer.
4.根据权利要求1所述的语音识别方法,其特征在于,所述语音识别方法还包括: 接收语音播报指令; 查找与所述语音播报指令相对应的语音文件,对所述语音文件进行语音播报,所述语音识别终端中预存有与所述语音播报指令对应的语音文件。 The voice recognition method according to claim 1, wherein said speech recognition method further comprises: receiving a broadcast voice commands; voice announcement to find the voice file corresponding to the instruction, the voice file voice broadcast, the voice recognition terminal with the pre-stored voice announcement voice file corresponding to the command.
5.根据权利要求1所述的语音识别方法,其特征在于,所述调用查找出的所述语言模型对接收到的所述语音控制消息进行识别,得到与所述语音控制消息相对应的控制指令的步骤包括: 调用查找出的所述语言模型对接收到的所述语音控制消息进行计算,以获得所述语音控制消息的特征参数,将所述特征参数进行转换得到与所述语音控制消息相对应的控制指令。 The voice recognition method according to claim 1, wherein the voice call to find out the model of the language of the received control messages to identify, obtain and control the voice message corresponding to the control instructions include the step of: calling the voice of the language model to find out the received control message is calculated to obtain the characteristic parameters of the speech control message, convert the characteristic parameters obtained with the voice message control corresponding to the control command.
6.一种语音识别系统,包括语音识别终端,所述语音识别终端连接有打印机,其特征在于,所述语音识别终端包括: 第一接收单元,用于接收语音控制消息; 第一检测单元,用于检测所述打印机的状态; 第一查找单元,用于查找出与所述打印机的状态相对应的语言模型,所述语音识别终端中预存有多个语言模型,所述多个语言模型分别与所述打印机的不同状态一一对应; 识别单元,用于调用查找出的所述语言模型对接收到的所述语音控制消息进行识别,得到与所述语音控制消息相对应的控制指令; 发送单元,用于将所述控制指令发送给所述打印机,以使所述打印机执行所述控制指令。 A speech recognition system comprising a speech recognition terminal, the voice recognition terminal is connected to a printer, wherein the voice recognition terminal comprising: a first receiving means for receiving voice control message; a first detection means, for detecting the state of the printer; a first search unit configured to search the language of the printer model corresponding to the state of the voice recognition terminal plurality of prestored language models, each of the plurality of language models with different states of the printer correspond; identifying means for calling the voice of the language model to find out the received control messages to identify, obtain and the voice control command corresponding to the control message; transmitting means for transmitting the control command to the printer to cause the printer to execute the control instruction.
7.根据权利要求6所述的语音识别系统,其特征在于,所述语音识别终端还包括: 第二接收单元,用于接收由所述打印机发送的控制指令执行反馈,所述控制指令执行反馈中包括执行所述控制指令之后所述打印机的状态; 切换单元,用于切换为与执行所述控制指令之后所述打印机的状态相对应的语言模型。 The speech recognition system according to claim 6, characterized in that the voice recognition terminal further comprises: a second receiving means for receiving control commands sent by the printer to perform feedback, the feedback control executed instruction It includes an execution state after the control commands of the printer; a switching unit for switching the state after the execution of the control command corresponding to the printer language model.
8.根据权利要求6所述的语音识别系统,其特征在于,所述发送单元用于监测所述语音识别终端和所述打印机之间的通信链路是否连通,如果未连通,则对所述控制指令进行缓存,如果连通,则将所述控制指令发送给所述打印机。 8. The speech recognition system according to claim 6, wherein the sending unit is configured to monitor a communication link between the terminal and the speech recognition printer is in communication, if the communication is not, then the cache control instruction, if the communication, then the control commands to the printer.
9.根据权利要求6所述的语音识别系统,其特征在于,所述语音识别终端还包括: 第三接收单元,用于接收语音播报指令; 第二查找单元,用于查找与所述语音播报指令相对应的语音文件; 播报单元,用于对所述语音文件进行语音播报,所述语音识别终端中预存有与所述语音播报指令对应的语音文件。 9. The speech recognition system according to claim 6, characterized in that the voice recognition terminal further comprising: a third receiving unit for receiving a voice broadcast command; and a second search unit configured to search the voice announcement voice file corresponding to the instruction; broadcast unit configured to broadcast the audio file voice, the voice recognition terminal with the pre-stored voice announcement voice file corresponding to the command.
10.根据权利要求6所述的语音识别系统,其特征在于,所述识别单元,用于调用查找出的所述语言模型对接收到的所述语音控制消息进行计算,以获得所述语音控制消息的特征参数,将所述特征参数进行转换得到与所述语音控制消息相对应的控制指令。 10. The speech recognition system according to claim 6, characterized in that the identification unit, the voice call for the language model to find out the received control message is calculated to obtain the voice control characteristic parameters of the message, the characteristic parameters of the converted control command to the voice message corresponding to the control.
CN201610142719.8A 2016-03-14 2016-03-14 Speech recognition method and system CN105869635A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610142719.8A CN105869635A (en) 2016-03-14 2016-03-14 Speech recognition method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610142719.8A CN105869635A (en) 2016-03-14 2016-03-14 Speech recognition method and system

Publications (1)

Publication Number Publication Date
CN105869635A true CN105869635A (en) 2016-08-17

Family

ID=56624699

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610142719.8A CN105869635A (en) 2016-03-14 2016-03-14 Speech recognition method and system

Country Status (1)

Country Link
CN (1) CN105869635A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1971500A (en) * 2005-11-24 2007-05-30 富士施乐株式会社 Printing apparatus and control method therefor, and printing system
US20080215329A1 (en) * 2002-03-27 2008-09-04 International Business Machines Corporation Methods and Apparatus for Generating Dialog State Conditioned Language Models
CN102074231A (en) * 2010-12-30 2011-05-25 万音达有限公司 Voice recognition method and system
CN202798910U (en) * 2012-09-20 2013-03-13 艾塔斯科技(镇江)有限公司 Scanner capable of being controlled by speeches
CN103430232A (en) * 2011-01-21 2013-12-04 谷歌公司 Speech recognition using device docking context
CN203480601U (en) * 2013-09-18 2014-03-12 杭州九聚科技有限公司 Self-service equipment based on voice interaction
JP2015009630A (en) * 2013-06-27 2015-01-19 庸 菊池 Vehicle inspection recording unit
CN105022595A (en) * 2015-07-01 2015-11-04 苏州奥莱维信息技术有限公司 Speech printing method
CN105094717A (en) * 2015-07-15 2015-11-25 百度在线网络技术(北京)有限公司 Printing method, printing device and printer based on voice input

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080215329A1 (en) * 2002-03-27 2008-09-04 International Business Machines Corporation Methods and Apparatus for Generating Dialog State Conditioned Language Models
CN1971500A (en) * 2005-11-24 2007-05-30 富士施乐株式会社 Printing apparatus and control method therefor, and printing system
CN102074231A (en) * 2010-12-30 2011-05-25 万音达有限公司 Voice recognition method and system
CN103430232A (en) * 2011-01-21 2013-12-04 谷歌公司 Speech recognition using device docking context
CN202798910U (en) * 2012-09-20 2013-03-13 艾塔斯科技(镇江)有限公司 Scanner capable of being controlled by speeches
JP2015009630A (en) * 2013-06-27 2015-01-19 庸 菊池 Vehicle inspection recording unit
CN203480601U (en) * 2013-09-18 2014-03-12 杭州九聚科技有限公司 Self-service equipment based on voice interaction
CN105022595A (en) * 2015-07-01 2015-11-04 苏州奥莱维信息技术有限公司 Speech printing method
CN105094717A (en) * 2015-07-15 2015-11-25 百度在线网络技术(北京)有限公司 Printing method, printing device and printer based on voice input

Similar Documents

Publication Publication Date Title
CN102007493B (en) Universal language input
US8648838B2 (en) Information processing apparatus, information processing method, and program
CN101526879B (en) Speech input interface on a device
US9798718B2 (en) Incremental multi-word recognition
KR20130133629A (en) Method and apparatus for executing voice command in electronic device
US6532003B2 (en) Data processing apparatus having control element for detecting false touch
US20190080696A1 (en) Speech recognition using electronic device and server
US20140232656A1 (en) Method and apparatus for responding to a notification via a capacitive physical keyboard
US9449600B2 (en) Character data entry
CN103714816A (en) Electronic appratus, server and control method thereof
US10304448B2 (en) Environmentally aware dialog policies and response generation
CN102163098A (en) Information processing device, information processing method and computer-readable recording medium
CN108604448A (en) Voice commands across devices
KR20160061349A (en) Actionable content displayed on a touch screen
US9007314B2 (en) Method for touch processing and mobile terminal
US20120029902A1 (en) Mode supporting multiple language input for entering text
CN102929505B (en) Adaptive switching input language
KR101716013B1 (en) Handling speech synthesis of content for multiple languages
KR101376286B1 (en) Touchscreen text input
US8782549B2 (en) Incremental feature-based gesture-keyboard decoding
CN100530085C (en) Method and apparatus for implementing a virtual push-to-talk function
US10048748B2 (en) Audio-visual interaction with user devices
CN104346127B (en) Implementation of voice input, and a terminal device
CN104360990A (en) Content editing method
CN102414994B (en) Input processing method of mobile terminal and device for performing same

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination