CN103871419B - An information processing method and an electronic device - Google Patents

An information processing method and an electronic device Download PDF

Info

Publication number
CN103871419B
CN103871419B CN 201210534978 CN201210534978A CN103871419B CN 103871419 B CN103871419 B CN 103871419B CN 201210534978 CN201210534978 CN 201210534978 CN 201210534978 A CN201210534978 A CN 201210534978A CN 103871419 B CN103871419 B CN 103871419B
Authority
CN
Grant status
Grant
Patent type
Prior art keywords
sound
information
vibration
obtaining
corresponding
Prior art date
Application number
CN 201210534978
Other languages
Chinese (zh)
Other versions
CN103871419A (en )
Inventor
李凡智
刘旭国
Original Assignee
联想(北京)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
Grant date

Links

Abstract

本发明提供了一种信息处理方法及电子设备,该方法包括:获得通过振动检测单元检测与第一声音对应的第一振动信息,以及获得通过一声音采集单元采集获得包含第一声音的第二声音,然后解析第一振动信息,获得与第一声音对应的第一声纹信息,以及解析第二声音,获得与第一声音对应的第二声纹信息,基于第一声纹信息与第二声纹信息,获得第三声纹信息,将第三声纹信息转换为与第一声音对应的第三声音信息,用以解决现有技术中存在噪声去除方式会滤除到用户的声音或者是外界环境中的声音滤除不完整,从而导致电子设备中的声音处理不精确,并且噪音去除方式单一的技术问题。 The present invention provides an information processing method and an electronic device, the method comprising: obtaining a first vibration information detected by the vibration detecting unit and the sound corresponding to the first, second and obtaining comprises obtaining a first sound by the sound acquisition unit sound then parse the first vibration information to obtain first sound pattern information corresponding to the first sound and a second sound parsed to obtain the first sound corresponding to the second sound pattern information and the second information based on the first sound pattern voiceprint information, obtaining third sound pattern information and converting the third sound pattern information is information corresponding to the first to third sound voice, to solve the prior art there is noise removal mode filters out the user's voice or sound external environment to filter out incomplete, leading to electronic devices sound processing imprecise, and single mode noise removal technology issues.

Description

一种信息处理方法及电子设备 An information processing method and an electronic device

技术领域 FIELD

[0001] 本发明涉及电子技术领域,尤其涉及一种信息处理方法及电子设备。 [0001] The present invention relates to electronic technologies, and in particular, relates to an information processing method and an electronic device.

背景技术 Background technique

[0002] 随着电子技术的不断发展,现有技术中的电子设备也变得功能多种多样,比如说现有技术中的手机一般都会同时设置有两个麦克风,其中,当用户在使用手机进行通话时, 其中第一麦克风用于接收用户发出的声音,而第二麦克风用于接收外界环境中的声音,当然两个麦克风是设置在手机的两端,当用户在通话的过程中,手机会同时处理第一麦克风以及第二麦克风所接收到的声音信息,并且会将第二麦克风接收到的声音中去除第一麦克风的声音信息,从而可以使手机在噪音较大的环境中仍然能够准确的传输用户的声音信息。 [0002] With the continuous development of electronic technology, the prior art electronic devices become diverse functions, such as prior art mobile phones simultaneously usually provided with two microphones which, when using your phone when a call, wherein a first microphone for receiving voice uttered by a user, a second microphone for receiving ambient sound in the environment, of course, two microphones are disposed at both ends of the phone, when the user during a call, the phone simultaneously processing the first microphone and the second microphone sound information received, and the second will be received by the microphone voice sound information removed first microphone, which can make the phone still accurately in large noisy environments voice information transmission users.

[0003] 但是,本申请发明人在实施本发明的过程中发现现有技术存在如下技术问题或缺陷: [0003] However, the present inventors found that in the practice of the present invention has the following technical problems or drawbacks of the prior art:

[0004] 现有技术中去除外界噪声的方法主要是通过在电子设备中设置多个声音采集装置,并且通过对所有声音采集装置采集到的声音信息进行处理以及过滤,从而可以将外界环境中的噪声去除,而只保留该电子设备对应用户的声音,但是,该方式是在采集到的声音信息中滤除环境噪声,因此,在噪音的滤除过程中会滤除掉用户的声音,或者是在滤除噪音的过程中会出现对外界环境中的噪音滤除不完整,从而导致电子设备对声音处理不精确的技术问题。 [0004] The method of removing the external noise in the prior art is mainly provided by a plurality of sound collection devices in an electronic device, and means to collect the sound information is processed and filtered by collecting all the sounds to the outside environment may be in noise removal, leaving only the electronic device corresponding to the user's voice, however, this method is to filter ambient noise in the acquired audio information, and therefore, in the process of filtering out noise in the user's voice will be filtered out, or It will appear on the external environment noise filtering process to filter out incomplete in noise, resulting in inaccurate electronic equipment for sound processing technical problems.

发明内容 SUMMARY

[0005] 本发明提供了一种信息处理方法及电子设备,用于解决现有技术中存在的电子设备对声音处理不精确的技术问题,其具体技术方案如下: [0005] The present invention provides an information processing method and an electronic apparatus for solving the technical problems present in the prior art sound processing electronic apparatus imprecise, specific technical solutions are as follows:

[0006] —种信息处理方法,应用于一电子设备,所述方法包括: [0006] - information processing method, applied to an electronic device, the method comprising:

[0007] 在一用户在预设位置佩戴有一用于检测用户发声时产生的振动的振动检测单元, 且所述用户发出第一声音的过程中,获得通过所述振动检测单元检测与所述第一声音对应的第一振动信息,以及获得通过一声音采集单元采集获得的包含所述第一声音的第二声音; [0007] In a user in a predetermined position for wearing a vibration detection unit detecting vibration generated when the user utterance, and the user issues the first sound process, is obtained with the first detection unit detects the vibration by a first vibration corresponding to the sound information, and obtaining the second sound collecting unit collecting sound obtained by comprising a first said sound;

[0008] 解析所述第一振动信息,获得与所述第一声音对应的第一声纹信息,以及解析所述第二声音,获得与所述第二声音对应的第二声纹信息; [0008] parsing the first vibration information to obtain first sound pattern information corresponding to the first sound and the second sound parsing obtain second sound pattern information corresponding to the second sound;

[0009] 基于所述第一声纹信息与所述第二声纹信息,获得第三声纹信息; [0009] Based on the first sound pattern information and the second sound pattern information, obtaining a third sound pattern information;

[0010] 将所述第三声纹信息转换为与所述第一声音对应的第三声音信息。 [0010] converting the third sound pattern information and sound information to a third corresponding to the first sound.

[0011] 其中,所述基于所述第一声纹信息以及所述第二声纹信息,获得第三声纹信息,具体包括: [0011] wherein, based on the first sound of the second sound pattern information and the pattern information to obtain third sound pattern information comprises:

[0012] 将所述第一声纹信息与所述第二声纹信息进行声纹匹配; [0012] The first sound pattern information and the second acoustic matching voice print pattern information;

[0013] 获取所述第二声纹信息与所述第一声纹信息皆包含的声纹信息作为所述第三声纹信息。 [0013] The second sound acquiring the voiceprint information pattern information and the first sound pattern information are included as the third sound pattern information.

[0014] 可选的,所述解析所述第一振动信息,获得与所述第一声音对应的第一声纹信息, 具体包括: [0014] Optionally, the analysis of the first vibration information to obtain first sound pattern information corresponding to the first sound, comprises:

[0015] 解析所述第一振动信息,获取所述第一振动信息对应的第一振动频率; [0015] parsing the first vibration information, the first obtaining a first oscillation frequency corresponding to the vibration information;

[0016] 根据所述第一振动频率,获取所述第一振动频率对应的所述第一声纹信息。 [0016] The oscillation frequency of the first, the first sound acquiring pattern information corresponding to the frequency of the first vibration.

[0017] 可选的,所述获得通过所述振动检测单元检测与所述第一声音对应的第一振动信息,以及获得通过一声音采集单元获得的包含所述第一声音的第二声音,具体为: [0017] Optionally, the first vibration information obtained by said vibration detecting unit detects sound corresponding to the first, second and obtaining a sound unit obtained by the sound collection comprising said first sound, Specifically:

[0018] 获取一第一预设时间内的通过所述振动检测单元检测与所述第一声音对应的所述第一振动信息;以及 [0018] acquiring a predetermined first detected by said vibration detecting means within a time corresponding to the first sound of the first vibration information;

[0019] 获取所述第一预设时间内获得通过所述声音采集单元采集的包含所述第一声音的所述第二声音。 [0019] the obtaining comprises obtaining the first sound of the sound through the second sound acquisition unit within the first predetermined time.

[0020] 可选的,在所述将所述三声纹信息转换为与所述第一声音对应的第三声音信息之后,所述方法还包括: After [0020] Alternatively, the three in the voiceprint information into a third voice sound information corresponding to the first, said method further comprising:

[0021] 通过所述电子设备中的声音输出装置输出所述第三声音信息。 [0021] information via the sound output means of the electronic apparatus in a third sound.

[0022] 一种电子设备,所述电子设备包括: [0022] An electronic device, said electronic device comprising:

[0023] 第一获得单元,用于在用户发出第一声音的过程中,获得所述第一声音对应的第一振动信息; [0023] a first obtaining unit, configured to process the first sound issued by the user to obtain a first vibration information corresponding to the first sound;

[0024] 第二获得单元,用于获得包含第一声音的第二声音; [0024] a second obtaining unit for obtaining the second sound comprises a first sound;

[0025] 解析单元,用于解析所述第一振动信息,获得与所述第一声音对应的第一声纹信息,以及解析所述第二声音,获得与所述第二声音对应的第二声纹信息; [0025] The parsing unit configured to parse the first vibration information to obtain first sound pattern information corresponding to the first sound and the second sound parsing, obtaining the second sound corresponding to the second voiceprint information;

[0026] 第三获得单元,用于基于所述第一声纹信息与所述第二声纹信息,获得第三声纹信息; [0026] The third obtaining unit, based on the first sound pattern information and the second sound pattern information, obtaining a third sound pattern information;

[0027] 转换单元,用于将所述第三声纹信息转换为与所述第一声音对应的第三声音信息。 [0027] conversion unit for converting the third sound pattern information and sound information to a third corresponding to the first sound.

[0028] 其中,所述第三获得单元具体包括: [0028] wherein said third obtaining unit comprises:

[0029] 匹配模块,用于将所述第一声纹信息与所述第二声纹信息进行声纹匹配; [0029] The matching module, the first sound pattern information and the second sound pattern information is used to perform a voiceprint match;

[0030] 获得模块,用于获取所述第二声纹信息与所述第一声纹信息皆包含的声纹信息作为所述第二声纹彳曰息。 [0030] obtaining module, configured to obtain the voiceprint information with the second sound pattern information of the first sound pattern information are contained in said left foot, as the second sound pattern information.

[0031] 可选的,所述解析单元具体包括: [0031] Optionally, the analyzing unit comprises:

[0032] 解析模块,用于解析所述第一振动信息,获取所述第一振动信息对应的第一振动频率; [0032] The parsing module configured to parse the first vibration information, acquiring a first vibration information corresponding to the first vibration frequency;

[0033] 声纹获得模块,用于根据所述第一振动频率,获取所述第一振动频率对应的所述第一声纹信息。 [0033] voiceprint obtaining module, for the first sound of the first vibration pattern information corresponding to the frequency of the first vibration frequency, obtained according to.

[0034] 可选的,所述第一获得单元具体用于获取一第一预设时间内的与所述第一声音对应的所述第一振动信息;以及获取所述第一预设时间内包含所述第一声首的所述第二声音。 [0034] Optionally, the first obtaining unit configured to obtain the first sound and the corresponding first predetermined time in a first vibration information; and obtaining the first predetermined time the first contains the first sound of the second sound.

[0035] 可选的,所述电子设备还包括: [0035] Optionally, the electronic device further comprising:

[0036] 输出单元,用于输出所述第三声音伯息。 [0036] output means for outputting said third primary sound information.

[0037] 本发明提供的一个或者多个实施例至少存在如下技术效果或优点: [0037] One or more embodiments of the present invention provides the following technical effects or advantages embodiment at least:

[0038] 通过本发明实施例中将用户发声部位振动信息转换为第一声纹信息并同时将采集到的声音转换为第二声纹信息,从而根据第一声纹信息以及第二声纹信息得到对应用用户声纹的第三声纹信息,并将该第三声纹信息转换为对应的第三声音信息,也就是说电子设备会第一声纹信息作为标准,然后在第二声纹信息中提出去与第一声纹信息匹配的声纹信息,由于第一声纹信息是由用户发声部位的振动得到的,因此该第一声纹信息是用户发声后的准确声纹,因此可以清晰的得到用户的声音信息,并可以将外界环境中的噪声直接滤除,从而解决了现有技术中存在电子设备对声音处理不精确的技术问题,从而实现了电子设备对采集到的声音中的噪声进行准确的去除,得到用户准确的声音,进而提升了电子设备声音处理的准确度,并且也大大的增加的用户的体 In the embodiment of a user utterance site vibration pattern information into first acoustic information, and simultaneously the collected sound into a second sound pattern information, so that the information in accordance with the first sound pattern information and the second sound pattern [0038] embodiment of the present invention third acoustic pattern information to obtain the voiceprint of the user application, and the third sound pattern information is converted into information corresponding to the third sound, i.e. first sound pattern information of an electronic appliance as a standard, then the second acoustic groove information presented in the voiceprint information to the first acoustic matching pattern information, since the first sound pattern vibration sound information obtained by the user site, so that the first sound pattern information is accurate after the user utterance voice print, can be to give a clear user's voice information, and may be ambient noise filtered directly, thus solving the technical problems existing in the prior art electronic devices imprecise sound processing, thereby realizing an electronic device in the collected sound accurate noise removal, users get accurate sound, thereby enhancing the accuracy of sound processing electronic apparatus, and also greatly increase the user's body 验度。 Experience degrees.

[0039] 在本发明实施例中通过在一预设时间内同时采集第一声音对应的第一振动信息以及采集包含第一声音的第二声音,也就是说电子设备会在采集的信息中标记时钟信号, 因此电子设备在处理采集到的信息是将读取该时钟信号,从而可以保证信息采集的同步性,从而提高了电子设备的对声音处理准确性,并且提高了去除噪音的精确度。 [0039] The embodiments of the present invention by simultaneously acquiring a first sound vibration information corresponding to a first and a second sound collection comprises a first sound in a predetermined time, that is marked in the electronic device in the information collection clock signal, the electronic information processing device is acquired to read the clock signal, thereby ensuring synchronization of information collection, thereby improving the accuracy of the sound processing of the electronic device, and improves the accuracy of noise removal.

附图说明 BRIEF DESCRIPTION

[0040] 图1所示为本发明实施例中一种信息处理方法的流程图; A flowchart of an information processing method of the present embodiment shown in [0040] embodiment of the invention FIG 1;

[0041]图2所示为本发明实施例中一种电子设备的具体结构示意图; [0041] FIG. 2 is a particular schematic structure of an electronic apparatus in the embodiment of the invention shown;

[0042]图3所示为本发明实施例中第三获得的具体结构示意图; It shows the specific configuration of the present embodiment is obtained as shown in the third [0042] embodiment of the invention FIG 3;

[0043]图4所示为本发明实施例中解析单元的具体结构示意图。 Specific structural diagram of the analysis unit of the present embodiment shown in [0043] FIG. 4 embodiment of the invention.

具体实施方式 detailed description

[0044]本发明提供了一种信息处理方法及电子设备,该方法包括:在用户在预设位置佩戴有一用于检测用户发声时产生振动的振动检测单元,且用户发出第一声音的过程中,获得通过振动检测单元检测与第一声音对应的第一振动信息,以及获得通过一声音采集单元采集获得包含第一声音的第二声音,然后解析第一振动信息,获得与第一声音对应的第一声纹信息,以及解析第二声音,获得与第一声音对应的第二声纹信息,基于第一声纹信息与第二声纹信息,获得第三声纹信息,将第三声纹信息转换为与第一声音对应的第三声音信息,用以解决现有技术电子设备对声音处理不精确的技术问题。 [0044] The present invention provides an information processing method and an electronic device, the method comprising: in a predetermined position in a user wearing a vibration detecting means for detecting vibration of the user utterance, and the user issues the first sound process to obtain a first detecting vibration information corresponding to the first sound by the vibration detecting unit, and a sound obtained by obtaining the second sound collecting unit comprises a first sound, and then parse the first vibration information, the first sound corresponding to obtain first sound pattern information, and to resolve the second sound, the first sound corresponding to obtain second sound pattern information, based on the first sound pattern information and second sound pattern information, pattern information to obtain the third tone, the third tone pattern third audio information is converted into information corresponding to the first sound, to solve the technical problems of the prior art sound processing electronic apparatus inaccurate.

[0045]简单的来说,当用户发出声音时,发声部位也将对应的产生振动,因此,在本发明实施例中,需要在用户的预设位置佩戴对应的用于检测用户发声时产生振动的振动检测单元,该振动检测单元能够检测到发声部位的振动信息,从而根据振动信息能够获得用户声音对应的振动,从而根据该振动在电子设备采集到的声音中提取出用户的声音,从而能够使得电子设备能够更加精确的识别用户的声音。 When vibration is generated [0045] In simple terms, when the user issues a sound utterance portion corresponding vibration also, therefore, in the embodiment of the present invention, a user needs to wear for detecting in a predetermined position corresponding to the utterance of the user vibration detection means, the vibration detection unit can detect the vibration information sounding site, thereby obtaining the user's voice corresponding to vibrate according to the vibration information, thereby extracting the electronic device collected sound of the user's voice according to the vibration, thereby enable the electronic device to more accurately recognize the user's voice.

[0046]下面通过附图以及具体实施例对本发明技术方案做详细的说明,应当理解本发明实施例以及实施例中的具体技术特征只是对本发明技术方案的说明,而并不是对本发明技术方案的限定,在不冲突的情况下,本发明实施例以及实施例中的具体技术特征可以相互组合。 [0046] Next, the drawings and in particular embodiments a detailed description of the technical solution of the present invention, it should be understood that embodiments of the invention and the specific technical features are merely illustrative of the technical solution of the present invention in embodiments, and not the technical solution of the present invention. defining, in the case of no conflict, the embodiments of the invention and the specific technical features of the embodiments may be combined with each other.

[0047]首先来将,在本发明实施例中为了能够采集到用户发声时,发声部位的振动信息, 本发明实施例中的电子设备连接有一振动检测单元,该振动检测单元需要佩戴在用户预设位置上,该预设位置就为用户的发声位置,从而当用户在发出声音时,该振动检测单元能够及时的检测到用户发声部位的振动信息,本发明实施例中的信息处理方法具体包括如下步骤: [0047] First to be, in the embodiment of the invention in order to capture the user utterance, utterance site vibration information is connected to a vibration detection unit embodiment of an electronic apparatus according to the present invention, the vibration detecting unit needs to be worn at the user pre set position, the position of the predetermined position on the user's utterance, so that when the user is a sound, the vibration detection unit detecting vibration of the timely information of the user utterance site, the information processing method of the present invention in embodiments comprises the steps of:

[0048] 如图1所示为本发明实施例中一种信息处理方法的流程图,该方法包括: [0048] As shown in Figure 1 of the present embodiment, a flowchart of a processing method of the embodiment of the invention the information, the method comprising:

[0049] 步骤101,获得通过第一声音对应的第一振动信息,以及包含第一声音的第二声音。 [0049] Step 101, to obtain the first sound vibration information corresponding to the first, comprising a first and a second audio sound.

[0050] 在本发明实施例中的电子设备除了连接有振动检测单元以外,该电子设备中还设置有声音采集单元,当用户发出第一声音时,与该电子设备连接的振动检测单元就能够检测到第一声音对应的对振动信息,在振动检测单元检测第一声音对应的第一振动信息的同时,电子设备中的声音采集单元还将采集获得包含第一声音的第二声音。 [0050] In the electronic apparatus according to the embodiment of the present invention in addition to the vibration detection unit is connected, the electronic device is also provided with a sound collection unit, when the user issues the first sound, vibration detection unit connected to the electronic device can be a first sound corresponding to the detected vibration information, while the first vibration information in a first vibration detection unit detects sound corresponding to the electronic device in the sound collection unit further comprises a first voice collecting obtain a second sound.

[0051] 在此需要说明的是,在本发明实施例中该声音采集单元采集的是外界环境中的声音,因此,除了用户发出的第一声音还有外界环境中噪声,进而电子设备采集到的并不是纯净的用户声音,在现有技术中电子设备中都是设置有两个声音采集单元,一个声音采集单元主要用于采集用户的声音以及外界环境的声音,而另一个声音采集单元主要是用户采集外界环境中的噪声。 [0051] It should be noted here that, in the embodiment of the present invention is a sound acquisition unit sound external environment, and therefore, in addition to the first voice, and ambient noise given by the user, and thus the electronic device to capture the user's voice is not pure, in the prior art electronic device is provided with two sound collection unit, a sound collection unit for collecting a sound mainly, and the sound of the user's external environment, the other main sound collection unit the user is capturing ambient noise in the environment.

[0052] 比如说,该电子设备为手机,该手机连接有一振动检测器,该振动检测设置于用户的发声部位,当用户发声时该发声部位也将对应的发出振动,此时该振动检测器将采集到该振动部位的振动信息,当然该振动将会持续一定的时间,该振动检测器也将持续的检测在该段时间内的振动信息,在此同时该电子设备中的麦克风将检测预设区域内的声音,当然在该声音中就包括了用户发出的声音以及外界环境中的其他声音,另外,在检测到该振动信息之后,该振动检测器会将该振动信息发送给手机,因此,该手机在采集声音的同时还将接收到振动传感器发送的振动信息。 [0052] For example, the electronic device is a handset that is connected to a vibration sensor, the vibration detecting portion provided in the user's utterance, the user utterance when the utterance portion corresponding to vibrate will also, at this time the vibration detector the collected vibration information to the vibration part, the vibration will of course continues for a certain time, the vibration detector will continue to detect the vibration information within the period of time, at the same time the electronic device is a microphone pre-detection sound in the region provided, of course, the sound including voice and other sounds in the external environment given by the user, Further, after detecting the vibration information, the vibration of the vibration detector will send messages to mobile phones, so the phone also while acquiring the received sound vibration information transmitted from the vibration sensor.

[0053] 在接收到振动信息以及采集到声音信息之后,该电子设备将执行步骤102。 [0053] After receiving the vibration information and sound information collected by the electronic device performs step 102.

[0054] 步骤102,解析第一振动信息,获得与第一声音对应的第一声纹信息,以及解析第二声音,获得与第一声音对应的第二声纹信息。 [0054] Step 102, parsing the first vibration information to obtain first sound pattern information corresponding to the first sound and a second sound parsed to obtain second sound pattern information corresponding to the first sound.

[0055] 在本发明实施例中,该电子设备在接收到第一振动信息之后,该电子设备将解析该第一振动信息,由于采集的是一段时间内的振动信息,因此,可以根据该段时间的第一振动信息获取第一振动信息对应的第一振动频率,然后根据该第一振动频率就能够得到该第一振动频率对应的第一声纹信息。 [0055] In an embodiment of the present invention, the electronic device after receiving the first vibration information, the electronic device will resolve the first vibration information, the vibration due to the collection of information within a period of time, thus, the segment can a first time information acquiring a first vibration frequency of the first vibration corresponding to vibration information, and then based on the first oscillation frequency can be obtained first sound pattern information corresponding to the first vibration frequency.

[0056] 具体来讲,在本发明实施例中,该电子设备接收到第一振动信息之后,该电子设备将首先解析该第一振动信息中的振动频率,该振动频率是包括了一段时间内的所有振动过程,因此,会是所有时间点的振动频率组合,进而该电子设备就能够根据该时间内的所有振动频率组合得到该第一振动信息的振动频率分布图,进而根据该振动频率分布图就能够得到对应该振动频率部分图的声纹图像,从而根据该声纹图像就能够得到该第一振动信息对应的第一声纹信息。 [0056] Specifically, in the embodiment of the present invention, after the electronic device receives a first vibration information, the first electronic device parses the vibration frequency of the first vibration information, the vibration frequency is a period of time comprising All vibration process, therefore, the vibration frequency may be a combination of all time points, and thus the electronic device can be obtained the vibration frequency of the first vibration information distribution according to all frequencies within the combined vibration time to be distributed based on the oscillation frequency FIG should can be obtained on the image voiceprint vibration frequency portion of the graph, so that the image based on the voiceprint information can be obtained first sound pattern corresponding to the first vibration information.

[0057]在此需要说明的是第一振动信息的采集与第二声音的采集需要同时进行,也就是说在第一预设时间内获取通过振动检测单元检测与第一声音对应的第一振动信息,同时在第一预设时间内获取通过声音采集单元采集的包含第一声音的第二声音,这样就能够保证声音信息与振动信息的同步性,这样可提高后续声音去噪的准确性。 [0057] It should be noted here that acquisition of the second sound collection and the first vibration information is required at the same time, that is acquired by the vibration of the first vibration detection unit detects the first sound corresponding to the first predetermined time information, while acquiring the second sound by the sound acquisition unit comprises a first sound in a first predetermined time, so that it is possible to ensure the synchronization of audio information and vibration information, which can improve the accuracy of the subsequent sound denoising.

[0058] 在解析到第一振动信息对应的第一声纹信息之后,该电子设备还将对声音采集单元采集到的第二声音进行解析,其具体的解析方式就是将采集到的第二声音通过电子设备中的声纹解析设备进行解析,从而得到该第二声音对应的第二声纹新。 [0058] After parsing the first acoustic vibration pattern information corresponding to the first information, the electronic device also to the second acquisition unit for analyzing the voice sound, and specific analytical methods is to collect second sound analyzed by the electronic device voiceprint analyzing apparatus, whereby the second acoustic new second pattern corresponding to the sound.

[0059] 在获取到第一声纹信息以及第二声纹信息之后,该电子设备将执行步骤103。 [0059] After acquiring the first sound pattern information and the second sound pattern information, the electronic device performs step 103.

[0060] 步骤103,基于第一声纹信息以及第二声纹信息,获得第三声纹信息。 [0060] Step 103, based on the first sound pattern information and the second sound pattern information, pattern information to obtain the third tone.

[0061] 在步骤102中,在该电子设备获取第一声纹信息以及第二声纹信息之后,该电子设备会将第一声纹信息与第二声纹信息进行匹配,从而获得第二声纹信息与第一声纹信息皆包含的声纹信息作为第三声纹信息。 [0061] In step 102, the electronic apparatus after the first sound acquiring a second sound pattern information and pattern information, the pattern information of the electronic device will first acoustic matching with the second sound pattern information to obtain a second sound voiceprint information first sound pattern information and pattern information are included as a third tone pattern information.

[0062] 具体来讲,在本发明实施例中该电子设备得到的第一声纹信息以及第二声纹就是两张对应的声纹图像,也就是第一声纹图像以及第二声纹图像,此时该电子设备会将第一声纹图像与第二声纹图像进行匹配,该匹配的过程主要就是通过声纹图像的识别,从而根据对两张声纹图像的识别,该电子设备将确定第一声纹图像中与第二声纹图像相同的声纹图像,从而将该声纹图像对应的声纹信息作为第三声纹信息。 [0062] Specifically, in the first sound pattern information and the second acoustic groove embodiment of the electronic device of the embodiment of the present invention is obtained corresponding voiceprint two images, i.e. the first sound and a second acoustic relief image relief image in this case the electronic device will first acoustic matching second acoustic relief image relief image, the matching process is mainly through the voiceprint identifying image, so that voice recognition based on two relief image, the electronic device determining a second acoustic image of the same pattern of the first acoustic image voiceprint relief image, whereby the voiceprint information voiceprint pattern corresponding to the image information as the third tone.

[0063] 进一步,在本发明实施例中为了进一步的得到更加精确的第三声纹信息以及避免在声纹信息匹配的过程中出现噪声匹配到第三声纹信息中,因此,在本发明实施例中在进行匹配的过程中第一声纹图像与第二声纹图像中相同的声纹信息的持续时间需要达到的预设时间,也就是说相同的声纹信息需要持续到一定的时间才能作为最后的第三声纹信息,这样可以有效的滤除掉外接的杂音。 [0063] Further, in the embodiment of the present invention in order to further obtain more accurate information and to avoid third sound pattern during the voiceprint information matches the third acoustic matching pattern noise information, and therefore, in the embodiment of the present invention, process in a preset time during the match in the first tone pattern image and the second acoustic pattern image in the same duration voiceprint information needs to be achieved, that is to say the same voiceprint information you need some time to continue to as a final third sound pattern information, which can effectively filter out external noise.

[0064] 在获取到第三声纹信息之后,该电子设备将执行步骤104。 [0064] After obtaining the third sound pattern information, the electronic device performs step 104.

[0065] 步骤104,将第三声纹信息转换为第一声音对应的第三声音信息。 [0065] Step 104, converts the third tone pattern information of the first information to the third sound corresponding to the sound.

[0066] 在获取到第三声纹信息之后,该电子设备将该第三声纹信息发送到该电子设备中的声纹信息解析装置中进行声纹信息与声音信息之间的转换,该转换为过程就是将匹配得到的第三声纹信息转换为第三声音信息。 [0066] After obtaining the third sound pattern information, the electronic device transmits the information to the third sound pattern conversion between the voiceprint information to the sound information voiceprint information analysis means in the electronic device, the conversion It is a process that converts the third acoustic matching voiceprint information obtained as a third audio information.

[0067]因此,通过本发明实施例中将用户发声部位振动信息转换为第一声纹信息并同时将采集到的声音转换为第二声纹信息,从而根据第一声纹信息以及第二声纹信息得到对应用用户声纹的第三声纹信息,并将该第三声纹信息转换为对应的第三声音信息,因此可以将外界环境中的噪声直接滤除,从而解决了现有技术中存在噪声去除方式会滤除到用户的声音或者是外界环境中的声音滤除不完整,从而导致电子设备中的声音处理不精确,并且噪音去除方式单一的技术问题,从而实现了电子设备对采集到的声音中的噪声进行准确的去除,得到用户准确的声音,进而提升了电子设备声音处理的准确度,并且也大大的增加的用户的体验度。 [0067] Accordingly, the present invention will be illustrated by the portion of the user utterance information into the first sound vibration pattern information and simultaneously collected sound into a second sound pattern information, so according to the first sound pattern information and the second acoustic third sound pattern information to obtain the user profile application voiceprint information, and the third sound pattern information into a third voice information corresponding to the external environment can therefore be directly filtered noise, thereby solving the prior art in the presence of noise removal mode filters out the user's voice or a sound external environment to filter out incomplete, leading to electronic devices sound processing imprecise, and single mode noise removal technology issues, enabling electronic devices experience of the collected sound accurate noise removal, users get accurate sound, thereby enhancing the accuracy of sound processing electronic apparatus, and also greatly increases the user.

[0068]下面通过具体的应用场景对本发明是实施例做进一步的说明。 [0068] below with specific application scenarios of the present invention is further illustrated embodiment.

[0069] 在该实施例中以电子设备为手机进行说明,当然,在该案中电子设备除了可以是手机以外还可以耳机、笔记本电脑或者掌上电脑等电子设备,此处只是以手机进行说明。 [0069] In this embodiment, the electronic device to be described as a mobile phone, of course, in that case may be a device other than the electronic phone can headsets, laptop or handheld computers and other electronic equipment, will be described herein only to the phone. [0070]首先来说,该手机是与振动检测器连接,该振动检测器需要放置在用户的发声部位,然后当用户发声时,比如说用户的说话内容为“明天公园见”,该手机首先是会通过手机中的麦克风采集声音,此时该麦克风采集到的声音中就包括了用户的说话声以及外界环境中的其他噪声,比如说电视中发出的“智能手机中上的网功能”以及用户的说话内容“明天公园见”,并且将该采集到的声音发送给手机中的声音处理芯片,同时,用于用户发声时,在用户的发声部位将会有对应的振动,因此,该振动检测器将采集到用户在该段时间内的振动信息,然后该振动检测器会将该振动信息发发送给手机中的处理芯片,该处理芯片将解析该振动信息,并且将得到该振动信息中的振动频率,最后将根据该振动频率得到该振动频率度对应的第一声纹信息,也就是该手 [0070] First of all, the phone is connected to a vibration sensor, the vibration detector needs to be placed in the vocal part of the user, and then when the user utterance, such as the content of speech user to "see the park tomorrow," the first mobile phone will pick up sound through the phone's microphone, at which point the microphone to collect voice including the voices of users and other noise in the external environment, such as television issued a "network functions on the smartphone" and user's speech content "tomorrow see Park", and transmits the collected voice to the voice processing chip in the phone, while, when a user utterance, the part of the user's utterance will have a corresponding vibration, and therefore, the vibration detector will collect vibration information to the user in that period of time, then the vibration detector sends the vibration information will be sent to the processing chip in the phone, the chip will parse the vibration information, the vibration and the information obtained vibration frequency, the vibration frequency is finally obtained first sound pattern corresponding to the information of the oscillation frequency according to the hand i.e. 将得到用户说话内容“明天公园见,,对应的第一声纹信息。 Users will get the content of speech "Tomorrow Park ,, see the first sound pattern corresponding to the information.

[0071]此时,该手机中的声音处理芯片也将对采集到的声音进行处理得到该声音对应的第二声纹信息,也就是说该手机将解析得到“智能手机中的上网功能”以及“明天公园见,'所对应的声纹信息,然后该手机会将第一声纹信息与第二声纹信息进行匹配得到第一声纹信息与第二声纹信息相同的第三声纹信息,其实也就是根据第一声纹信息去找出在第二声纹3息中与第一声纹信息相同的声纹信息,当找出该声纹信息时,则将该声纹信息确定为第三声纹信息,比如说,手机会根据“明天公园见”对应的声纹信息去匹配“智能手机中的上网功能”以及“明天公园见”对应的声纹信息,从而可以得到匹配的声纹信息为“明天公园见” 对应的声纹信息。 [0071] At this time, the phone will sound processing chips collected sound obtained by processing the second sound corresponding to the sound pattern information, that is obtained through parsing the handset "smartphone Internet access" and "tomorrow Park see 'voiceprint information corresponds, then the handset will first sound pattern information and the second acoustic matching pattern information to obtain the first sound pattern information and the second sound pattern information as the third sound pattern information when, in fact, is based on the first acoustic pattern information to identify the groove 3 in the second acoustic information with the same first sound pattern information of the voiceprint information, to find out when the voiceprint information, the information is determined to be the voiceprint third tone pattern information, for example, the phone will be based on "parks see you tomorrow" corresponding voiceprint information to match the "smart phone Internet access" and "tomorrow park see" corresponding voiceprint information can be obtained acoustic matching pattern information is "park see you tomorrow" corresponding voiceprint information.

[0072]在得到第三声纹信息之后,该手机会将该第三声纹信息转换为第三声音输出,在第二声音中只是包含了用户的声音,也就是“明天公园见”的声音,而外界环境中的噪声将被准确的滤除掉,从而提升了手机的噪声去除准确度,并且提升了手机的声音处理功能。 [0072] After obtaining the third sound pattern information, the phone will be the third sound pattern information into a third sound output, the sound only in the second contains the user's voice, which is "to see the park tomorrow," the voice , while the external environment in the noise to be accurately filtered out, so as to enhance the accuracy of the phone to remove noise and enhance the phone's voice processing functions. [^73] 对应本发明一种信息处理的方法,本发明实施例还提供了一种电子设备,如图2所示为本发明一种电子设备的具体结构示意图,该电子设备包括: [^ 73] corresponds to an information processing method of the present invention, embodiments of the present invention further provides an electronic device, particularly a schematic structure of an electronic apparatus of the present invention shown in FIG. 2, the electronic device comprising:

[0074] 第一获得单元201,用于在用户发出第一声音的过程中,获得所述第一声音对应的第一振动信息; [0074] a first obtaining unit 201, configured to process the first sound issued by the user to obtain a first vibration information corresponding to the first sound;

[0075]第二获得单元202,用于获得包含第一声音的第二声音; [0075] The second obtaining unit 202 for obtaining the second sound comprises a first sound;

[0076] 解析单元203,用于解析所述第一振动信息,获得与所述第一声音对应的第一声纹信息,以及解析所述第二声音,获得与所述第一声音对应的第二声纹信息; [0076] The parsing unit 203 is configured to parse the first vibration information to obtain first sound pattern information corresponding to the first sound and the second sound parsed to obtain the first sound corresponding to the first two voiceprint information;

[0077]第三获得单元204,用于基于所述第一声纹信息与所述第二声纹信息,获得第三声纹信息; [0077] The third obtaining unit 204, based on the first sound pattern information and the second sound pattern information, obtaining a third sound pattern information;

[0078] 转换单元205,用于将所述第三声纹信息转换为与所述第一声音对应的第三声音息。 [0078] conversion unit 205 for converting the third sound pattern information and the first sound corresponding to the third audio information.

[0079]输出单元206,用于输出所述第三声音信息 [0079] The output unit 206 configured to output the third audio information

[00S0] 其中,第一获取单元201与第二获得单元202是同时在采集信息,第一获得单元2〇1 是用于获得第一声音对应的第一振动信息,第二获得单元202是用于获得包含第一声音的第二声音,然后该电子设备中的解析单元203将接收第一振动信息以及第二声音,并同时对第一振动信息以及第二声音进行解析,从而得到第一振动信息对应的第一声纹信息,以及获第二声音对应的第二声纹信息,然后该电子设备中的第三获得单元2〇4将基于第一声纹信息以及第二声纹信息的得到第三声纹信息,然后该第三获得单元2〇4将第三声纹信息发送给转换单元205,从而转换单元205将所述第三声纹信息转换为与所述第一声音对应的第二尸首"[目息,最后该电子设备中的输出单兀206将输出所述桌二尸曰彳曰息。 [00S0] wherein the first acquisition unit 201 and second unit 202 are simultaneously obtained in the acquisition information, the first obtaining unit for obtaining a first 2〇1 vibration information corresponding to the first sound, the second obtaining unit 202 is to obtain a second sound comprises a first sound analysis unit 203 and the electronic device will receive the first vibration and the second audio information, while the first and the second vibration information analyzing sound, whereby the first vibration a first sound pattern corresponding to the information, and the second sound corresponding to the sound pattern information is eligible for the second, and the third electronic device obtaining unit to obtain a first sound pattern information and the pattern information based on the second sound 2〇4 third sound pattern information, and the third obtaining unit transmits the third sound pattern 2〇4 information to the conversion unit 205, so that the conversion unit 205 converts the first to third sound pattern information and sound corresponding to the first two corpses "[head interest, the final output of the electronic device 206 outputs the single Wu two tables dead said information said left foot.

[0081] 其中,该电子设备的第三获得单元204包括如图3所示的具体结构,该第三获得单元204包括: [0081] wherein the third obtaining unit of the electronic device 204 includes the particular arrangement shown in FIG. 3, the third obtaining unit 204 comprises:

[0082]匹配模块301,用于将所述第一声纹信息与所述第二声纹信息进行声纹匹配; [0082] The matching module 301, for the first sound pattern information and the second acoustic matching voice print pattern information;

[0083] 获得模块3〇2,用于获取所述第二声纹信息与所述第一声纹侣息皆包含的声纹侣息作为所述第三声纹信息。 [0083] 3〇2 obtaining module, configured to obtain the voiceprint information companion second sound pattern information and the first sound pattern information Lu are contained as the third sound pattern information. _ 一 _ one

[0084] 该电子设备的解析单元203包括如图4所示的具体结构,该解析单元203包括: [0084] The parsing unit 203 of the electronic device comprises a specific configuration shown in Figure 4, the analysis unit 203 comprises:

[0085] 解析模块401,用于解析所述第一振动信息,获取所述第一振动信息对应的第一振动频率; [0085] The parsing module 401, configured to parse the first vibration information, the first obtaining a first oscillation frequency corresponding to the vibration information;

[0086] 声纹获得模块402,用于根据所述第一振动频率,获取所述第一振动频率对应的所述第一声纹信息。 [0086] obtaining the voiceprint module 402, for the first sound of the first vibration pattern information corresponding to the frequency of the first vibration frequency, obtained according to.

[0087] 需要说明的是,该电子设备中的第一获得单元201具体用于获取一第一预设时间内的与所述第一声音对应的所述第一振动信息;以及获取所述第一预设时间内包含所述第一声音的所述第二声音。 [0087] Incidentally, the first obtaining unit 201 of the electronic device for acquiring the specific sound corresponding to the first within a first predetermined time a first vibration information; and acquiring the second within a predetermined time comprising the first sound of the second sound.

[0088] 本发明提供的一个或者多个实施例至少存在如下技术效果或优点: [0088] One or more embodiments of the present invention provides the following technical effects or advantages embodiment at least:

[0089] 通过本发明实施例中将用户发声部位振动信息转换为第一声纹信息并同时将采集到的声音转换为第二声纹信息,从而根据第一声纹信息以及第二声纹信息得到对应用用户声纹的第三声纹信息,并将该第三声纹信息转换为对应的第三声音信息,也就是说电子设备会第一声纹信息作为标准,然后在第二声纹信息中提出去与第一声纹信息匹配的声纹信息,由于第一声纹信息是由用户发声部位的振动得到的,因此该第一声纹信息是用户发声后的准确声纹,因此可以清晰的得到用户的声音信息,并可以将外界环境中的噪声直接滤除,从而解决了现有技术中存在电子设备对声音处理不精确的技术问题,从而实现了电子设备对采集到的声音中的噪声进行准确的去除,得到用户准确的声音,进而提升了电子设备声音处理的准确度,并且也大大的增加的用户的体 In the embodiment of a user utterance site vibration pattern information into first acoustic information, and simultaneously the collected sound into a second sound pattern information, so that the information in accordance with the first sound pattern information and the second sound pattern [0089] embodiment of the present invention third acoustic pattern information to obtain the voiceprint of the user application, and the third sound pattern information is converted into information corresponding to the third sound, i.e. first sound pattern information of an electronic appliance as a standard, then the second acoustic groove information presented in the voiceprint information to the first acoustic matching pattern information, since the first sound pattern vibration sound information obtained by the user site, so that the first sound pattern information is accurate after the user utterance voice print, can be to give a clear user's voice information, and may be ambient noise filtered directly, thus solving the technical problems existing in the prior art electronic devices imprecise sound processing, thereby realizing an electronic device in the collected sound accurate noise removal, users get accurate sound, thereby enhancing the accuracy of sound processing electronic apparatus, and also greatly increase the user's body 验度。 Experience degrees.

[0090] 在本发明实施例中通过在一预设时间内同时采集第一声音对应的第一振动信息以及采集包含第一声音的第二声音,也就是说电子设备会在采集的信息中标记时钟信号, 因此电子设备在处理采集到的信息是将读取该时钟信号,从而可以保证信息采集的同步性,从而提高了电子设备的对声音处理准确性,并且提高了去除噪音的精确度。 [0090] The embodiments of the present invention by simultaneously acquiring a first sound vibration information corresponding to a first and a second sound collection comprises a first sound in a predetermined time, that is marked in the electronic device in the information collection clock signal, the electronic information processing device is acquired to read the clock signal, thereby ensuring synchronization of information collection, thereby improving the accuracy of the sound processing of the electronic device, and improves the accuracy of noise removal.

[0091]本领域内的技术人员应明白,本发明的实施例可提供为方法、系统、或计算机程序产品。 [0091] skilled in the art should understand that the embodiments of the present invention may provide a method, system, or computer program product. 因此,本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。 Thus, embodiments of the present invention may be employed entirely hardware embodiment, an entirely software embodiment, or an embodiment in conjunction with the form of software and hardware aspects. 而且,本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。 Further, the present invention may take the form of a computer program product embodied in one or more of which comprises a computer usable storage medium having computer-usable program code (including but not limited to, disk storage, CD-ROM, optical memory, etc.).

[0092]本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。 [0092] The present invention has been described in accordance with the method of Example of the present invention, apparatus (systems) and computer program products flowchart and / or block diagrams described. 应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。 It should be understood and implemented by computer program instructions and block, and the flowchart / or block diagrams each process and / or flowchart illustrations and / or block diagrams of processes and / or blocks. 可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。 These computer program instructions may be provided to a processor a general purpose computer, special purpose computer, embedded processor or other programmable data processing apparatus to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing apparatus generating in a device for implementing the flow chart or more flows and / or block diagram block or blocks in a specified functions. [0093]这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。 [0093] These computer program instructions may also be stored in a computer can direct a computer or other programmable data processing apparatus to function in a particular manner readable memory produce an article of manufacture such that the storage instruction means comprises a memory in the computer-readable instructions the instruction means implemented in a flowchart or more flows and / or block diagram block or blocks in a specified function.

[0094] 这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。 [0094] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps on the computer or other programmable apparatus to produce a computer implemented so that the computer or other programmable apparatus execute instructions to provide processes for implementing a process or flows and / or block diagram block or blocks a function specified step.

[0095] 显然,本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。 [0095] Obviously, those skilled in the art can make various modifications and variations to the invention without departing from the spirit and scope of the invention. 这样,倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内,则本发明也意图包含这些改动和变型在内。 Thus, if these modifications and variations of the present invention fall within the claims of the invention and the scope of equivalents thereof, the present invention intends to include these modifications and variations.

Claims (8)

1.一种信息处理方法,应用于一电子设备,其特征在于,所述方法包括: 在一用户在预设位置佩戴有一用于检测用户发声时产生的振动的振动检测单元,且所述用户发出第一声音的过程中,获得通过所述振动检测单元检测与所述第一声音对应的第一振动信息,以及获得通过一声音采集单元采集获得的包含所述第一声音的第二声音; 解析所述第一振动信息,获得与所述第一声音对应的第一声纹信息,以及解析所述第二声音,获得与所述第二声音对应的第二声纹信息; 基于所述第一声纹信息与所述第二声纹信息,获得第三声纹信息; 将所述第三声纹信息转换为与所述第一声音对应的第三声音信息; 其中,所述基于所述第一声纹信息以及所述第二声纹信息,获得第三声纹信息,具体包括: 将所述第一声纹信息与所述第二声纹信息进行声纹匹配; 获取 1. An information processing method applied to an electronic apparatus, wherein, said method comprising: a user in a predetermined position for wearing a vibration detection unit detecting vibration generated when the user utterance, and the user first sound emitted in the process, the first vibration information obtained by said vibration detecting unit detects sound corresponding to the first, second and obtaining a sound collecting unit collecting sound obtained by comprising a first said sound; parsing the first vibration information to obtain first sound pattern information corresponding to the first sound and the second sound parsing, obtaining the second sound corresponding to the second sound pattern information; based on the first voiceprint information with the second sound pattern information, obtaining a third sound pattern information; converting the third sound pattern information and sound information to a third corresponding to the first sound; wherein, based on said a first sound pattern information and the second sound pattern information, obtaining a third sound pattern information comprises: the first sound pattern information and the second acoustic matching voice print pattern information; Get 述第二声纹信息与所述第一声纹信息皆包含的声纹信息作为所述第三声纹信肩、。 Said second sound pattern information voiceprint information and the first sound pattern information are included as the third sound pattern letter shoulder.
2. 如权利要求1所述的方法,其特征在于,所述解析所述第一振动信息,获得与所述第一声音对应的第一声纹信息,具体包括: 解析所述第一振动信息,获取所述第一振动信息对应的第一振动频率; 根据所述第一振动频率,获取所述第一振动频率对应的所述第一声纹信息。 2. The method according to claim 1, characterized in that the analysis of the first vibration information, obtain the first sound information corresponding to the first sound pattern, comprises: parsing the first vibration information obtaining a first oscillation frequency corresponding to said first vibration information; according to the first vibration frequency, the first sound acquiring pattern information corresponding to the frequency of the first vibration.
3. 如权利要求1所述的方法,其特征在于,所述获得通过所述振动检测单元检测与所述第一声音对应的第一振动信息,以及获得通过一声音采集单元获得的包含所述第一声音的第二声音,具体为: 获取一第一预设时间内的通过所述振动检测单元检测与所述第一声音对应的所述第一振动信息;以及获取所述第一预设时间内获得通过所述声音采集单元采集的包含所述第一声音的所述第二声音。 3. The method according to claim 1, wherein said first vibration information obtained by said vibration detecting unit detects sound corresponding to the first, and access means comprising a sound collection obtained by the a second first audio, specifically: obtained by said vibration detection unit detects the first sound corresponding to the first vibration information in a first predetermined time; and obtaining the first preset obtaining the second sound by the sound acquisition unit comprises a first sound of the time.
4. 如权利要求1〜3任一权项所述的方法,其特征在于,在所述将所述三声纹信息转换为与所述第一声音对应的第三声音信息之后,所述方法还包括: 通过所述电子设备中的声音输出装置输出所述第三声音信息。 After Item 4. The method according to any one of a weight of claims 1~3, wherein, the three in the voiceprint information into a third voice sound information corresponding to the first, said method further comprising: a sound output means for outputting information of the electronic apparatus in the third sound.
5. —种电子设备,其特征在于,所述电子设备包括: 第一获得单元,用于在用户发出第一声音的过程中,获得所述第一声音对应的第一振动信息; 第二获得单元,用于获得包含第一声音的第二声音; 解析单元,用于解析所述第一振动信息,获得与所述第一声音对应的第一声纹信息,以及解析所述第二声音,获得与所述第二声音对应的第二声纹信息; 第三获得单元,用于基于所述第一声纹信息与所述第二声纹信息,获得第三声纹信息; 转换单元,用于将所述第三声纹信息转换为与所述第一声音对应的第三声音信息; 其中,所述第三获得单元具体包括: 匹配模块,用于将所述第一声纹信息与所述第二声纹信息进行声纹匹配; 获得模块,用于获取所述第二声纹信息与所述第一声纹信息皆包含的声纹信息作为所述第二声纹倡息。 The - electronic device, wherein the electronic device comprises: a first obtaining unit, configured to process a first sound issued by the user, obtaining the first sound corresponding to the first vibration information; second obtaining means for obtaining the second sound comprises a first sound; parsing unit configured to parse the first vibration information to obtain first sound pattern information corresponding to the first sound and the second sound parsing, obtaining second sound pattern information corresponding to the second sound; third obtaining unit based on the first sound pattern information and the second sound pattern information, obtaining a third sound pattern information; conversion means with to the third sound pattern information into the first information with the third sound corresponding to the sound; wherein the third obtaining unit comprises: a matching module for converting the first sound pattern information with said second acoustic matching voiceprint information pattern; obtaining module, configured to obtain the voiceprint information with the second sound pattern information comprising the first sound pattern information are advocated as the second sound pattern information.
6. 如权利要求5所述的电子设备,其特征在于,所述解析单元具体包括: 解析模块,用于解析所述第一振动信息,获取所述第一振动信息对应的第一振动频率; 声纹获得模块,用于根据所述第一振动频率,获取所述第一振动频率对应的所述第一声纹信息。 6. The electronic apparatus according to claim 5, characterized in that the parsing means comprises: a parsing module configured to parse the first vibration information, the first obtaining a first oscillation frequency corresponding to the vibration information; voiceprint obtaining module, for the first sound of the first vibration pattern information corresponding to the frequency of the first vibration frequency, obtained according to.
7. 如权利要求5所述的电子设备,其特征在于,所述第一获得单元具体用于获取一第一预设时间内的与所述第一声音对应的所述第一振动信息;以及获取所述第一预设时间内包含所述第一声音的所述第二声音。 7. The electronic device according to claim 5, wherein the first obtaining unit is configured to obtain the first sound corresponding to a first predetermined time in a first vibration information; It comprises obtaining the said first predetermined time within the first second sound sound.
8. 如权利要求5所述的电子设备,其特征在于,所述电子设备还包括: 输出单元,用于输出所述第三声音信息。 8. The electronic apparatus according to claim 5, wherein the electronic device further comprising: an output unit configured to output the third audio information.
CN 201210534978 2012-12-11 2012-12-11 An information processing method and an electronic device CN103871419B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201210534978 CN103871419B (en) 2012-12-11 2012-12-11 An information processing method and an electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201210534978 CN103871419B (en) 2012-12-11 2012-12-11 An information processing method and an electronic device

Publications (2)

Publication Number Publication Date
CN103871419A true CN103871419A (en) 2014-06-18
CN103871419B true CN103871419B (en) 2017-05-24

Family

ID=50909882

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201210534978 CN103871419B (en) 2012-12-11 2012-12-11 An information processing method and an electronic device

Country Status (1)

Country Link
CN (1) CN103871419B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105469806A (en) * 2014-09-12 2016-04-06 联想(北京)有限公司 Sound processing method, device and system
CN104601825A (en) * 2015-02-16 2015-05-06 联想(北京)有限公司 Control method and control device
CN105611061A (en) * 2015-12-31 2016-05-25 宇龙计算机通信科技(深圳)有限公司 Voice transmission method and device and mobile terminal
CN106326698A (en) * 2016-08-11 2017-01-11 上海青橙实业有限公司 Working state setting method for terminal and terminal

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1750123A (en) * 2004-09-17 2006-03-22 微软公司 Method and apparatus for multi-sensory speech enhancement
CN101199006A (en) * 2005-06-20 2008-06-11 微软公司 Multi-sensory speech enhancement using a clean speech prior
CN101887728A (en) * 2003-11-26 2010-11-17 微软公司 Method and apparatus for multi-sensory speech enhancement
CN102084668A (en) * 2008-05-22 2011-06-01 伯恩同通信有限公司 A method and a system for processing signals
CN102411936A (en) * 2010-11-25 2012-04-11 歌尔声学股份有限公司 Speech enhancement method and device as well as head de-noising communication earphone

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2609757A4 (en) * 2010-08-27 2016-04-06 Nokia Technologies Oy A microphone apparatus and method for removing unwanted sounds
FR2976111B1 (en) * 2011-06-01 2013-07-05 Parrot Audio equipment comprising means for denoising of a speech signal by filtering a fractional delay, including a telephony system "hands free"

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101887728A (en) * 2003-11-26 2010-11-17 微软公司 Method and apparatus for multi-sensory speech enhancement
CN1750123A (en) * 2004-09-17 2006-03-22 微软公司 Method and apparatus for multi-sensory speech enhancement
CN101199006A (en) * 2005-06-20 2008-06-11 微软公司 Multi-sensory speech enhancement using a clean speech prior
CN102084668A (en) * 2008-05-22 2011-06-01 伯恩同通信有限公司 A method and a system for processing signals
CN102411936A (en) * 2010-11-25 2012-04-11 歌尔声学股份有限公司 Speech enhancement method and device as well as head de-noising communication earphone

Also Published As

Publication number Publication date Type
CN103871419A (en) 2014-06-18 application

Similar Documents

Publication Publication Date Title
Lu et al. Speakersense: Energy efficient unobtrusive speaker identification on mobile phones
JP2005244968A (en) Method and apparatus for speech enhancement by multi-sensor on mobile device
US20150332667A1 (en) Analyzing audio input for efficient speech and music recognition
US20130080169A1 (en) Audio analysis system, audio analysis apparatus, audio analysis terminal
US20130304243A1 (en) Method for synchronizing disparate content files
WO2011148594A1 (en) Voice recognition system, voice acquisition terminal, voice recognition distribution method and voice recognition program
CN103095911A (en) Method and system for finding mobile phone through voice awakening
US20130090926A1 (en) Mobile device context information using speech detection
US20120253807A1 (en) Speaker state detecting apparatus and speaker state detecting method
JP2007264473A (en) Voice processor, voice processing method, and voice processing program
JP2007288242A (en) Operator evaluation method, device, operator evaluation program, and recording medium
JP2008076676A (en) Sound signal processing method, sound signal processing device and computer program
Mittal et al. Effect of glottal dynamics in the production of shouted speech
US20150025881A1 (en) Speech signal separation and synthesis based on auditory scene analysis and speech modeling
EP2643981B1 (en) A device comprising a plurality of audio sensors and a method of operating the same
CN101345819A (en) Speech control system used for set-top box
US20150310878A1 (en) Method and apparatus for determining emotion information from user voice
US9401153B2 (en) Multi-mode audio recognition and auxiliary data encoding and decoding
US20150162021A1 (en) Spectral Comb Voice Activity Detection
JP2007248534A (en) Speech recognition device, frequency spectrum acquiring device and speech recognition method
US9153229B2 (en) Methods and systems for adapting grammars in hybrid speech recognition engines for enhancing local SR performance
CN103578470A (en) Telephone recording data processing method and system
CN101819758A (en) System of controlling screen display by voice and implementation method
JP2011191423A (en) Device and method for recognition of speech
JP2013007764A (en) Voice data repeating device, terminal, voice data repeating method, and voice recognition system

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
GR01