CN104954532A - Voice recognition method, voice recognition device and mobile terminal - Google Patents
Voice recognition method, voice recognition device and mobile terminal Download PDFInfo
- Publication number
- CN104954532A CN104954532A CN201510346867.7A CN201510346867A CN104954532A CN 104954532 A CN104954532 A CN 104954532A CN 201510346867 A CN201510346867 A CN 201510346867A CN 104954532 A CN104954532 A CN 104954532A
- Authority
- CN
- China
- Prior art keywords
- sound characteristic
- caller
- contact person
- characteristic sample
- incoming call
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Landscapes
- Telephone Function (AREA)
Abstract
The invention provides a voice recognition method, a voice recognition device and a mobile terminal. The method comprises the following steps: acquiring voice of a caller; extracting voice characteristic parameters of the caller; comparing the voice characteristic parameters with a voice characteristic sample prestored in a voice characteristic sample library; transmitting prompt information about the identity of the caller according to the comparison result. According to the voice recognition method, the voice recognition device and the mobile terminal provided by the invention, whether the voice characteristic sample consistent with the voice characteristic parameters of the caller exists or not is judged by acquiring the voice of the caller, extracting the voice characteristic parameters of the caller and accordingly comparing the voice characteristic parameters with the prestored voice characteristic sample library, so as to prevent a user from being cheated. By the adoption of the technical scheme of the invention, the identity of the caller can be recognized reliably and effectively, and a corresponding prompt is made, so that the possibility that the user is cheated in an incoming call conversation is reduced, and the safety of the incoming call conversation of the user is further improved.
Description
Technical field
The present invention relates to communication technique field, particularly relate to a kind of method of speech recognition and device and mobile terminal.
Background technology
Mobile terminal as mobile phone can make person to person at any time or anywhere conversed by mobile terminal, thus understand information each other, for interpersonal interchange is provided convenience.Therefore mobile terminal has become the necessary article of a lot of modern work, life.
Existing mobile terminal can storing phone number and use the name of people of this telephone number, just can very fast calling as long as call address list when calling; When connecting phone, the information such as caller ID and address name corresponding to this caller ID can be shown by mounted software, and then contrast with the information that stores in address list; If include this caller ID in address list, now, screen can show this caller ID and address name corresponding to this caller ID, can determine that this caller is non-stranger.If when not including this caller ID in address list, now, screen only can show this caller ID and then can judge that incoming call is as Stranger Calls.
But, realizing in process of the present invention, inventor finds at least there is following shortcoming in prior art: in prior art, caller can forge the number in user communication record by high-tech, the caller ID that user is seen is the number of the contact person in address list, gains the trust of user by cheating; Or caller, by imitating the sound of someone or using high-tech voice changer to disguise oneself as into the sound of the people that user is familiar with, gains the trust of user by cheating.Therefore no matter mobile terminal points out this incoming call to be contact person's incoming call in address list, or the Stranger Calls outside address list, all likely causes user to be cheated in incoming call call.
Summary of the invention
The invention provides a kind of method of speech recognition and device and mobile terminal, to overcome the identity that user accurately and reliably cannot distinguish caller in incoming call call, cause user can cheated problem in incoming call call.
The invention provides a kind of audio recognition method, described method comprises:
Gather the sound of caller;
Extract the sound characteristic parameter of described caller;
Sound characteristic sample in the sound characteristic Sample Storehouse of described sound characteristic parameter and pre-stored is compared; Described sound characteristic sample comprises the sound characteristic parameter of the contact person in address list;
According to comparing result, send the information of the identity of described caller.
The present invention also provides a kind of speech recognition equipment, and described device comprises:
Acquisition module, for gathering the sound of caller;
Extraction module, for extracting the sound characteristic parameter of described caller;
Comparing module, for comparing the sound characteristic sample in the sound characteristic Sample Storehouse of described sound characteristic parameter and pre-stored; Described sound characteristic sample comprises the sound characteristic parameter of the contact person in address list;
Reminding module, for according to comparing result, sends the information of the identity of described caller.
Storage module, for storing described sound characteristic Sample Storehouse, described sound characteristic Sample Storehouse comprises the sound characteristic parameter of the contact person in address list.
The present invention also provides a kind of mobile terminal, and described mobile terminal is provided with speech recognition equipment as above.
The method of speech recognition of the present invention and device and mobile terminal, by gathering the sound of caller, and extract the sound characteristic parameter of caller, thus the sound characteristic Sample Storehouse of contrast pre-stored, judge whether to there is the sound characteristic sample with the sound characteristic parameter of caller, and then send the information of identity of described caller, cheated to prevent user.Adopt the technical scheme of the present embodiment, reliably and the effective identity differentiating caller, and corresponding prompting can be made, can be cheated in incoming call call to reduce user, the fail safe that the incoming call further increasing user is conversed.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the flow chart of an embodiment of audio recognition method of the present invention;
Fig. 2 is the flow chart of another embodiment of audio recognition method of the present invention;
Fig. 3 is the structural representation of an embodiment of speech recognition equipment of the present invention;
Fig. 4 is the structural representation of another embodiment of speech recognition equipment of the present invention.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 is the flow chart of an embodiment of audio recognition method of the present invention.As shown in Figure 1, the method for the present embodiment can comprise:
101, the sound of caller is gathered;
Such as, when there being incoming call, the sound of caller can be recorded, realizing the sound gathering caller.
102, the sound characteristic parameter of caller is extracted;
Sound is the vibrations being caused vocal cords by the contraction of muscle of throat, then sends after the sympathetic response of oral cavity, nasal cavity.Everyone vocal cords feature is different, the sound spectrum sent during vibrations as people fingerprint, hardly with exist identical.Wherein the frequency of sound may be used for uniquely characterizing sound characteristic.Such as, in the present embodiment, the frequency of sound can be adopted as sound characteristic parameter.From the sound of the caller gathered, extract the frequency of sound characteristic parameter as sound, with reference to related art, can not repeat them here in detail.
103, the sound characteristic sample in the sound characteristic Sample Storehouse of sound characteristic parameter and pre-stored is compared.
The sound characteristic parameter of the All Contacts in address list can be comprised in this sound characteristic sample.Therefore, user can when with Affiliate sessions in address list, record the sound of contact person, and then extract the sound characteristic parameter of contact person, and preserve the sound characteristic sample of contact person, set up and contact person's sound characteristic sample one to one, thus the sound characteristic sample of contact person in mobile phone in the whole address list of pre-stored, generate a sound characteristic Sample Storehouse.When there being incoming call, by the sound characteristic parameter of caller and sound characteristic Sample Storehouse in all sound characteristic samples compare one by one.
104, according to comparing result, the information of the identity of caller is sent.
Such as, the result of contrast is the sound characteristic Sample Storehouse of pre-stored in mobile phone when there is the sample consistent with the sound characteristic parameter of caller, sends the information that this caller is a contact person in address list; Such user can lose vigilance.When the sound characteristic Sample Storehouse that comparing result is pre-stored in mobile phone does not exist the sample consistent with the sound characteristic parameter of caller, send the information that this caller is the stranger beyond address list, such user can enhance your vigilance, and prevents from having dust thrown into the eyes.
The audio recognition method of the present embodiment, by gathering the sound of caller, and extract the sound characteristic parameter of caller, thus the sound characteristic Sample Storehouse of contrast pre-stored, judge whether to there is the sound characteristic sample with the sound characteristic parameter of caller, and then send the information of identity of described caller, achieve the prompting to contact person and stranger, cheated to prevent user.Adopt the technical scheme of the present embodiment, reliably and the effective identity differentiating caller, and corresponding prompting can be made, can be cheated in incoming call call to reduce user, the fail safe that the incoming call further increasing user is conversed.
On the basis of above-mentioned technical scheme embodiment illustrated in fig. 1, after step 102 " extracts the sound characteristic parameter of caller ", step 103 can also comprise as follows before " being compared by the sound characteristic sample in the sound characteristic Sample Storehouse of sound characteristic parameter and pre-stored ": whether the incoming call judging caller according to address list is Stranger Calls; And determine that the incoming call of caller is Stranger Calls.
Particularly, can by judging the telephone number whether comprising caller in address list, if comprise, determine that incoming call is non-Stranger Calls, namely incoming call is the incoming call of the first contact person in address list; If otherwise do not comprise, determine that incoming call is Stranger Calls.
Further, on the technical scheme basis of above-described embodiment, after determining the incoming call of sending a telegram here as the contact person in address list, can also comprise the steps:
(1) the sound characteristic sample of the first contact person in the sound characteristic parameter of caller and sound characteristic Sample Storehouse is compared; When the sound characteristic parameter of caller is identical with the sound characteristic sample of the first contact person, perform step (2); Otherwise when the sound characteristic parameter of caller is not identical with the sound characteristic sample of the first contact person, perform step (3);
Particularly, the first contact person in the corresponding address list of this caller ID, from sound characteristic Sample Storehouse, obtain sound characteristic sample corresponding to this caller ID by according to the caller ID of caller, from sound characteristic Sample Storehouse, namely obtain the sound characteristic sample of the first contact person.Then the sound characteristic parameter of caller and the sound characteristic sample of this first contact person are compared.
(2) information that caller is the first contact person is sent;
(3) information that caller is stranger is sent.
Further, on the technical scheme basis of above-described embodiment, step 104 " according to comparing result; send the information of the identity of caller ", specifically can comprise: when sound characteristic Sample Storehouse comprises the sound characteristic sample identical with the sound characteristic parameter of caller, extract the information of the second contact person corresponding to the sound characteristic sample identical with sound characteristic parameter, such as, can extract the name of the second contact person, or also to extract the telephone number of this second contact person further; And send the information that electric person is the second contact person.
Or when sound characteristic Sample Storehouse does not comprise the sound characteristic sample identical with the sound characteristic parameter of caller, send the information that caller is stranger.
The audio recognition method of above-described embodiment, by adopting such scheme, reliably and the identity of effective resolution caller, and corresponding prompting can be made, can be cheated in incoming call call to reduce user, be further increased the fail safe of the incoming call call of user.
Fig. 2 is the flow chart of another embodiment of audio recognition method of the present invention.The audio recognition method of the present embodiment, on the basis of above-described embodiment, describes technical scheme of the present invention further in further detail.As shown in Figure 2, the audio recognition method of the present embodiment, specifically can comprise:
201, the sound of caller is gathered;
202, the sound characteristic parameter of caller is extracted;
Such as extract the frequency of the sound of caller.
203, judge whether the incoming call of caller is Stranger Calls according to address list; When being Stranger Calls, perform step 204; Otherwise when not being Stranger Calls, perform step 206;
Particularly, when there being incoming call, the contact number one by one in contrast address list and the caller ID of caller, judge whether to there is the contact number consistent with caller ID; When it is present, determine that this incoming call is the incoming call of the contact person in address list, i.e. non-stranger's incoming call; When not existing, determine that this incoming call is Stranger Calls.Such as, caller is the contact person in address list, but employs other number, and in fact caller is not stranger, but this incoming call is Stranger Calls.Therefore need other telephone number judging whether to store caller in address list, and then prove that caller is the contact person in address list.
204, determine that the incoming call of caller is Stranger Calls; Perform step 205;
205, all sound characteristic samples in the sound characteristic Sample Storehouse of sound characteristic parameter and pre-stored are compared; When sound characteristic Sample Storehouse comprises the sound characteristic sample identical with the sound characteristic parameter of caller, perform step 208; When not comprising the sound characteristic sample identical with the sound characteristic parameter of caller in sound characteristic Sample Storehouse, perform step 210; After judging that incoming call is as Stranger Calls, all sound characteristic samples in the sound characteristic parameter of caller and the sound characteristic Sample Storehouse of pre-stored are compared one by one.When caller is still a contact person in address list.Now, associated person information corresponding to the sound characteristic sample identical with sound characteristic parameter is extracted; Send the information that caller is contact person.
When sound characteristic Sample Storehouse does not comprise the sound characteristic sample identical with the sound characteristic parameter of caller, then caller is stranger.Now, the information that caller is stranger is sent.
206, the incoming call of sending a telegram here as the first contact person in address list is determined; Perform step 207;
When the contact number in address list exists the number consistent with the caller ID of caller, determine that the incoming call of caller is first contact person's incoming call.
207, the sound characteristic sample of this first contact person in the sound characteristic parameter of caller and sound characteristic Sample Storehouse is compared; When the sound characteristic parameter of caller is identical with the sound characteristic sample of the first contact person, perform step 211; Otherwise when the sound characteristic parameter of caller is not identical with the sound characteristic sample of the first contact person, perform step 205;
After judging that the sound characteristic parameter of caller is not identical with the sound characteristic sample of this first contact person, step 205 can be performed; Particularly, because step 207 is by the sound characteristic parameter of caller, the sound characteristic sample of first contact person corresponding in address list with the caller ID of this caller in sound characteristic Sample Storehouse is compared, therefore, when execution step 205, the sound characteristic sample that can save the first contact person corresponding in address list with the caller ID of this caller in sound characteristic Sample Storehouse is compared again.
208, the second associated person information corresponding to the sound characteristic sample identical with sound characteristic parameter is extracted; Perform step 209;
Such as specifically can extract the name of the second contact person corresponding to the sound characteristic sample identical with sound characteristic parameter, or the telephone number of this second contact person can also be extracted further.
209, send the information that this caller is this second contact person, terminate.
Such as this prompting can comprise the name of this contact person, or can also comprise the phone of this contact person in address list.And further prompting can be done, prompting user is stored in this contact person of address list under one's name the need of by the telephone number of this incoming call.
210, send the information that this caller is stranger, terminate.
Such as specifically can make the mark that this caller is stranger in prompting, with vigilant user, this incoming call may be fraudulent call.And further a swindle label can be set to the telephone number of this incoming call; And the label of this caller ID and correspondence is stored in telephone number management holder according to corresponding relation, with when next time, this caller ID was sent a telegram here again, corresponding prompting can be made to user according to the swindle label of this telephone number in telephone number management holder, if user sees for fraudulent call, can directly rejection.
211, send the information that this caller is the contact person in address list, terminate.
The present embodiment audio recognition method, by judging the incoming call of caller, when not being Stranger Calls, extracting the sound characteristic sample of contact person in sound characteristic Sample Storehouse and comparing with the sound characteristic parameter of caller, judging whether caller is this contact person; When caller is this contact person, send the information that caller is contact person.When caller is not this contact person or incoming call is Stranger Calls, all sound characteristic samples in the sound characteristic parameter of caller and the sound characteristic Sample Storehouse of pre-stored are compared one by one.When sound characteristic Sample Storehouse comprises the sound characteristic sample identical with the sound characteristic parameter of caller, then caller is still a contact person in address list; Now, associated person information corresponding to the sound characteristic sample identical with sound characteristic parameter is extracted; Send the information that caller is contact person.Adopt the technical scheme of the present embodiment, reliably and the effective identity differentiating caller, and corresponding prompting can be made, can be cheated in incoming call call to reduce user, the fail safe that the incoming call further increasing user is conversed.
Fig. 3 is the structural representation of an embodiment of speech recognition equipment of the present invention.As shown in Figure 3, the speech recognition equipment of the present embodiment, specifically can comprise: acquisition module 11, extraction module 12, comparing module 13, reminding module 14 and storage module 15.
The speech recognition equipment of the present embodiment, acquisition module 11 is for gathering the sound of caller; Extraction module 12 is connected with acquisition module 11, and extraction module 12, for the sound of caller gathered according to acquisition module 11, extracts the sound characteristic parameter of caller as the frequency of sound from this sound.Storage module 15 is for stored sound feature samples storehouse, and this sound characteristic Sample Storehouse comprises the sound characteristic parameter of the contact person in address list.In the present embodiment, this storage module 15 is specifically as follows memory.Comparing module 13 is connected with extraction module 12 and storage module 15 respectively, and comparing module 13 is compared for the sound characteristic sample in the sound characteristic Sample Storehouse of the sound characteristic parameter extracted by extraction module 12 and storage module 15 pre-stored.Reminding module 14 is connected with comparing module 13, and reminding module 14, for the comparing result according to comparing module 13, sends the information of the identity of caller.
The speech recognition equipment of the present embodiment, by the realization mechanism adopting above-mentioned module to realize speech recognition, identical with the realization mechanism of embodiment of the method shown in Fig. 1 and technique effect, with reference to above-mentioned record embodiment illustrated in fig. 1, can not repeat them here in detail.
Fig. 4 is the structural representation of another embodiment of speech recognition equipment of the present invention.As shown in Figure 4, the speech recognition equipment of the present embodiment, on the basis of above-mentioned technical scheme embodiment illustrated in fig. 3, comprises following technical scheme further.
As shown in Figure 4, in the speech recognition equipment of the present embodiment, also comprise judge module 16 and determination module 17.Wherein judge module 16 is for judging according to address list whether the incoming call of caller is Stranger Calls; In order to easy to operate, this judge module 16 starts after specifically can being arranged on extraction module 12, such as, extract the sound characteristic parameter of caller in the sound of extraction module 12 caller after, can trigger judge module 16 and start.
Determination module 17 is connected with judge module 16, and determination module 17, for the judged result according to judge module 16, determines that the incoming call of caller is Stranger Calls.
Further alternatively, the determination module 17 in the speech recognition equipment of the present embodiment, also for the judged result according to judge module 16, determines that this incoming call is the incoming call of the first contact person in address list.Further, comparing module 13 is also connected with determination module 17, and the sound characteristic sample of this first contact person that comparing module 13 is also determined for determination module 17 in the sound characteristic Sample Storehouse that stores in the sound characteristic parameter of caller extracted by extraction module 12 and storage module 15 is compared; Such as particularly, the result that comparing module 13 is first determined according to determination module 17, obtains the first contact person of this incoming call correspondence in address list; Then from the sound characteristic Sample Storehouse that storage module 15 stores, sound characteristic sample corresponding to this first contact person is obtained; The sound characteristic sample that the sound characteristic parameter of the caller finally extracted by extraction module 12 is corresponding with this first contact person is compared.
Further, reminding module 14, also for the comparison result according to comparing module 13, when the sound characteristic parameter of caller is identical with the sound characteristic sample of the first contact person, sends the information that caller is the first contact person; Or reminding module 14 is also for when the sound characteristic parameter of caller is not identical with the sound characteristic sample of the first contact person, send the information that caller is stranger.
Or further alternatively, reminding module 14 in the speech recognition equipment of the present embodiment is specifically for the comparison result according to comparing module 13, when sound characteristic Sample Storehouse comprises the sound characteristic sample identical with the sound characteristic parameter of caller, extract the information of the second contact person corresponding to the sound characteristic sample identical with sound characteristic parameter, the such as name of the second contact person, or also comprise the telephone number of the second contact person further; And send the information that electric person is this second contact person;
Or reminding module 14 is also for the comparison result according to comparing module 13, when sound characteristic Sample Storehouse does not comprise the sound characteristic sample identical with the sound characteristic parameter of caller, send the information that caller is stranger.
Further alternatively, in the speech recognition equipment of the present embodiment, judge module 16 is specifically for judging the telephone number whether comprising caller in address list, if comprise, determine that incoming call is non-Stranger Calls, namely incoming call is the incoming call of the contact person in address list; If otherwise do not comprise, determine that incoming call is Stranger Calls.
The speech recognition equipment of the present embodiment, by the realization mechanism adopting above-mentioned module to realize speech recognition, identical with the realization mechanism of embodiment of the method shown in Fig. 2 and technique effect, with reference to above-mentioned record embodiment illustrated in fig. 2, can not repeat them here in detail.
The present invention also provides a kind of mobile terminal, this mobile terminal is provided with above-mentioned Fig. 3 or speech recognition device embodiment illustrated in fig. 4, and above-mentioned Fig. 1 or audio recognition method embodiment illustrated in fig. 2 can be adopted to realize speech recognition, with reference to the relevant record of above-described embodiment, can not repeat them here in detail.
One of ordinary skill in the art will appreciate that: all or part of step realizing above-mentioned each embodiment of the method can have been come by the hardware that program command is relevant.Aforesaid program can be stored in a computer read/write memory medium.This program, when performing, performs the step comprising above-mentioned each embodiment of the method; And aforesaid storage medium comprises: ROM, RAM, magnetic disc or CD etc. various can be program code stored medium.
Last it is noted that above each embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to foregoing embodiments to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein some or all of technical characteristic; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (10)
1. an audio recognition method, is characterized in that, described method comprises:
Gather the sound of caller;
Extract the sound characteristic parameter of described caller;
Sound characteristic sample in the sound characteristic Sample Storehouse of described sound characteristic parameter and pre-stored is compared; Described sound characteristic sample comprises the sound characteristic parameter of the contact person in address list;
According to comparing result, send the information of the identity of described caller.
2. method according to claim 1, is characterized in that, after extracting the sound characteristic parameter of described caller, before being compared by the sound characteristic sample in the sound characteristic Sample Storehouse of described sound characteristic parameter and pre-stored, described method also comprises:
Whether the incoming call judging described caller according to described address list is Stranger Calls;
And determine that the incoming call of described caller is Stranger Calls.
3. method according to claim 2, is characterized in that, after judging whether the incoming call of described caller is Stranger Calls according to described address list, described method also comprises:
Determine that described incoming call is the incoming call of the first contact person in described address list;
Further, described method also comprises:
The sound characteristic sample of the first contact person described in the described sound characteristic parameter of described caller and described sound characteristic Sample Storehouse is compared;
When the described sound characteristic parameter of described caller is identical with the sound characteristic sample of described first contact person, send the information that described caller is described first contact person; Otherwise when the described sound characteristic parameter of described caller is not identical with the sound characteristic sample of described first contact person, send the information that described caller is stranger.
4. method according to claim 2, is characterized in that, judges whether the incoming call of described caller is Stranger Calls, specifically comprise according to described address list:
Judge the telephone number whether comprising described caller in described address list, if comprise, determine that described incoming call is non-Stranger Calls, namely described incoming call is the incoming call of the contact person in described address list; If otherwise do not comprise, determine that described incoming call is Stranger Calls.
5. the method according to claim 2 or 4, is characterized in that, according to comparing result, sends the information of the identity of described caller, specifically comprises:
When described sound characteristic Sample Storehouse comprises the sound characteristic sample identical with the described sound characteristic parameter of described caller, extract the information of the second contact person corresponding to the described sound characteristic sample identical with described sound characteristic parameter;
Send the information that described caller is described second contact person;
Or when described sound characteristic Sample Storehouse does not comprise the sound characteristic sample identical with the described sound characteristic parameter of described caller, send the information that described caller is stranger.
6. a speech recognition equipment, is characterized in that, described device comprises:
Acquisition module, for gathering the sound of caller;
Extraction module, for extracting the sound characteristic parameter of described caller;
Comparing module, for comparing the sound characteristic sample in the sound characteristic Sample Storehouse of described sound characteristic parameter and pre-stored;
Reminding module, for according to comparing result, sends the information of the identity of described caller;
Storage module, for storing described sound characteristic Sample Storehouse, described sound characteristic Sample Storehouse comprises the sound characteristic parameter of the contact person in address list.
7. device according to claim 6, is characterized in that, described device also comprises:
Judge module, for judging according to described address list whether the incoming call of described caller is Stranger Calls;
Determination module, for the judged result according to described judge module, determines that the incoming call of described caller is Stranger Calls.
8. device according to claim 7, is characterized in that, described determination module, also for determining that described incoming call is the incoming call of the first contact person in described address list;
Further, described comparing module, also for being compared by the sound characteristic sample of the first contact person described in the described sound characteristic parameter of described caller and described sound characteristic Sample Storehouse;
Described reminding module, also for when the described sound characteristic parameter of described caller is identical with the sound characteristic sample of described first contact person, sends the information that described caller is described first contact person; Or also for when the described sound characteristic parameter of described caller is not identical with the sound characteristic sample of described first contact person, send the information that described caller is stranger.
9. device according to claim 7, it is characterized in that, described reminding module, during specifically for comprising the sound characteristic sample identical with the described sound characteristic parameter of described caller when described sound characteristic Sample Storehouse, extract the information of the second contact person corresponding to the described sound characteristic sample identical with described sound characteristic parameter; Send the information that described caller is described second contact person;
Or described reminding module, time also for not comprising the sound characteristic sample identical with the described sound characteristic parameter of described caller when described sound characteristic Sample Storehouse, sends the information that described caller is stranger.
10. a mobile terminal, is characterized in that, described mobile terminal is provided with the arbitrary described speech recognition equipment of as above claim 6-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510346867.7A CN104954532B (en) | 2015-06-19 | 2015-06-19 | The method and device and mobile terminal of speech recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510346867.7A CN104954532B (en) | 2015-06-19 | 2015-06-19 | The method and device and mobile terminal of speech recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104954532A true CN104954532A (en) | 2015-09-30 |
| CN104954532B CN104954532B (en) | 2018-08-31 |
Family
ID=54168872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510346867.7A Expired - Fee Related CN104954532B (en) | 2015-06-19 | 2015-06-19 | The method and device and mobile terminal of speech recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104954532B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105376143A (en) * | 2015-12-03 | 2016-03-02 | 小天才科技有限公司 | Method and device for identifying sender identity |
| CN105869630A (en) * | 2016-06-27 | 2016-08-17 | 上海交通大学 | Method and system for detecting voice spoofing attack of speakers on basis of deep learning |
| CN105933493A (en) * | 2016-04-20 | 2016-09-07 | 乐视控股（北京）有限公司 | Strange incoming call processing method, device and mobile terminal |
| CN106101388A (en) * | 2016-05-30 | 2016-11-09 | 珠海市魅族科技有限公司 | A kind of communication identifier storage method and device |
| CN107666583A (en) * | 2017-09-07 | 2018-02-06 | 宇龙计算机通信科技(深圳)有限公司 | Call handling method and terminal |
| CN109920450A (en) * | 2017-12-13 | 2019-06-21 | 北京回龙观医院 | Information processing unit and information processing method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1558648A (en) * | 2003-12-16 | 2004-12-29 | 威艾德通讯技术（深圳）有限公司 | A method for displaying locus name of incoming call numbers on telephone set |
| US20070071206A1 (en) * | 2005-06-24 | 2007-03-29 | Gainsboro Jay L | Multi-party conversation analyzer & logger |
| CN101301240A (en) * | 2008-05-21 | 2008-11-12 | 清华大学深圳研究生院 | Electric cochlea Chinese fixed electric stimulation amplitude changing pattern in vitro voice processing equipment |
| CN101944359A (en) * | 2010-07-23 | 2011-01-12 | 杭州网豆数字技术有限公司 | Voice recognition method facing specific crowd |
| CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
| CN102800315A (en) * | 2012-07-13 | 2012-11-28 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted voice control method and system |
| CN103700371A (en) * | 2013-12-13 | 2014-04-02 | 江苏大学 | Voiceprint identification-based incoming call identity identification system and identification method |
| CN104010060A (en) * | 2013-02-27 | 2014-08-27 | 联想(北京)有限公司 | Method and electronic device for recognizing identity of incoming caller |
-
2015
- 2015-06-19 CN CN201510346867.7A patent/CN104954532B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1558648A (en) * | 2003-12-16 | 2004-12-29 | 威艾德通讯技术（深圳）有限公司 | A method for displaying locus name of incoming call numbers on telephone set |
| US20070071206A1 (en) * | 2005-06-24 | 2007-03-29 | Gainsboro Jay L | Multi-party conversation analyzer & logger |
| CN101301240A (en) * | 2008-05-21 | 2008-11-12 | 清华大学深圳研究生院 | Electric cochlea Chinese fixed electric stimulation amplitude changing pattern in vitro voice processing equipment |
| CN101944359A (en) * | 2010-07-23 | 2011-01-12 | 杭州网豆数字技术有限公司 | Voice recognition method facing specific crowd |
| CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
| CN102800315A (en) * | 2012-07-13 | 2012-11-28 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted voice control method and system |
| CN104010060A (en) * | 2013-02-27 | 2014-08-27 | 联想(北京)有限公司 | Method and electronic device for recognizing identity of incoming caller |
| CN103700371A (en) * | 2013-12-13 | 2014-04-02 | 江苏大学 | Voiceprint identification-based incoming call identity identification system and identification method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105376143A (en) * | 2015-12-03 | 2016-03-02 | 小天才科技有限公司 | Method and device for identifying sender identity |
| CN105933493A (en) * | 2016-04-20 | 2016-09-07 | 乐视控股（北京）有限公司 | Strange incoming call processing method, device and mobile terminal |
| WO2017181615A1 (en) * | 2016-04-20 | 2017-10-26 | 乐视控股（北京）有限公司 | Method and device for processing unfamiliar incoming call, and mobile terminal |
| CN106101388A (en) * | 2016-05-30 | 2016-11-09 | 珠海市魅族科技有限公司 | A kind of communication identifier storage method and device |
| CN105869630A (en) * | 2016-06-27 | 2016-08-17 | 上海交通大学 | Method and system for detecting voice spoofing attack of speakers on basis of deep learning |
| CN105869630B (en) * | 2016-06-27 | 2019-08-02 | 上海交通大学 | Speaker's voice spoofing attack detection method and system based on deep learning |
| CN107666583A (en) * | 2017-09-07 | 2018-02-06 | 宇龙计算机通信科技(深圳)有限公司 | Call handling method and terminal |
| CN107666583B (en) * | 2017-09-07 | 2020-09-11 | 宇龙计算机通信科技(深圳)有限公司 | Call processing method and terminal |
| CN109920450A (en) * | 2017-12-13 | 2019-06-21 | 北京回龙观医院 | Information processing unit and information processing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104954532B (en) | 2018-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104954532A (en) | Voice recognition method, voice recognition device and mobile terminal | |
| US10062268B2 (en) | Terminal alarm method and apparatus | |
| JP4310749B2 (en) | Telephone equipment | |
| US7920680B2 (en) | VoIP caller authentication by voice signature continuity | |
| CN104159229B (en) | Incoming call processing method and device | |
| CN102546890B (en) | Information detection method and information detection terminal | |
| CN103401987A (en) | Privacy protection method and system for mobile terminal incoming call answering | |
| JP2017529711A (en) | Method, apparatus and system for voice confirmation | |
| CN102316203A (en) | Method for preventing crank call based on cloud computing, device and terminal | |
| CN103391359A (en) | Mobile terminal and voice recognition processing method thereof | |
| CN104023110A (en) | Voiceprint recognition-based caller management method and mobile terminal | |
| CN105554223A (en) | Connection establishment method and mobile terminal | |
| CN106657547A (en) | Method and system for preventing crank calls | |
| CN106714178A (en) | Abnormal call judgment method and device | |
| CN107112030A (en) | Analyze the method and apparatus of the situation of called end and realize this method and the program of device | |
| EP3244294A1 (en) | Voiceprint-recognition-based security protection method and device | |
| WO2016161750A1 (en) | Terminal call control method and device, and computer storage medium | |
| EP2472915A1 (en) | Method and device for detecting whether missed call is effective | |
| JP2020053967A (en) | Systems and methods for detecting communication fraud attempts | |
| CN109474734A (en) | Recognition methods, device and the terminal of type of call | |
| WO2016141697A1 (en) | Temporary contact storing method and device | |
| CN104010060A (en) | Method and electronic device for recognizing identity of incoming caller | |
| CN103546613A (en) | Contact person recording method, contact person recording device and mobile terminal | |
| CN108777749B (en) | Fraud call identification method and device | |
| CN108924330A (en) | Information processing method, device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180831 Termination date: 20190619 |