CN104954532B - The method and device and mobile terminal of speech recognition - Google Patents
The method and device and mobile terminal of speech recognition Download PDFInfo
- Publication number
- CN104954532B CN104954532B CN201510346867.7A CN201510346867A CN104954532B CN 104954532 B CN104954532 B CN 104954532B CN 201510346867 A CN201510346867 A CN 201510346867A CN 104954532 B CN104954532 B CN 104954532B
- Authority
- CN
- China
- Prior art keywords
- caller
- sound characteristic
- sound
- incoming call
- contact person
- 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.)
- Expired - Fee Related
Links
Landscapes
- Telephone Function (AREA)
Abstract
The present invention provides a kind of method and device and mobile terminal of speech recognition.The method includes：Acquire the sound of caller；Extract the sound characteristic parameter of the caller；The sound characteristic parameter is compared with the sound characteristic sample in pre-stored sound characteristic sample database；According to comparing result, the prompt message of the identity of the caller is sent out.The method and device and mobile terminal of the speech recognition of the present invention, by the sound for acquiring caller, and extract the sound characteristic parameter of caller, to the pre-stored sound characteristic sample database of comparison, judge whether the sound characteristic sample with the sound characteristic parameter of caller, and then the prompt message of the identity of the caller is sent out, to prevent user to be spoofed.Technical solution using the present invention can reliably and effectively differentiate the identity of caller, and make corresponding prompt, can be spoofed in incoming call is conversed with reducing user, further improve the safety of the incoming call call of user.
Description
Technical field
The present invention relates to communication technique field more particularly to the method and devices and mobile terminal of a kind of speech recognition.
Background technology
Mobile terminal such as mobile phone can make person to person at any time or anywhere passes through mobile terminal and converses,
To the information between understanding, provide convenience for interpersonal exchange.Therefore mobile terminal has become many existing
The generation artificial necessary article made, lived.
Existing mobile terminal can store telephone number and the name of the people using the telephone number, when making a phone call
As long as calling address list making a phone call quickly；When connecting phone, incoming call can be shown by mounted software
The information such as number and the corresponding address name of the incoming number, and then compared with the information stored in address list；If communication
Include the incoming number in record, at this point, can show the incoming number and the corresponding user's surname of the incoming number on screen
Name, it may be determined that the caller is non-stranger.If when in address list not including the incoming number, at this point, on screen
It can only show the incoming number and then may determine that incoming call is Stranger Calls.
But in the implementation of the present invention, inventor has found at least to have the disadvantage that in the prior art：Existing skill
In art, caller can forge the number in user communication record by high-tech so that the incoming number that user sees is
The number of contact person in address list gains the trust of user by cheating；Either sound or use of the caller by imitation someone
High-tech voice changer disguises oneself as into the sound of people known to user, gains the trust of user by cheating.Therefore no matter mobile terminal prompt is somebody's turn to do
Incoming call is the Stranger Calls except contact person's incoming call or address list in address list, and it is logical in incoming call to be likely to result in user
It is spoofed in words.
Invention content
The present invention provides a kind of method and device and mobile terminal of speech recognition, to overcome user's nothing in incoming call is conversed
Method accurately and reliably distinguishes the identity of caller, causes user can cheated problem in incoming call is conversed.
The present invention provides a kind of audio recognition method, the method includes：
Acquire the sound of caller；
Extract the sound characteristic parameter of the caller；
The sound characteristic parameter is compared with the sound characteristic sample in pre-stored sound characteristic sample database；Institute
State the sound characteristic parameter that sound characteristic sample includes the contact person in address list；
According to comparing result, the prompt message of the identity of the caller is sent out.
The present invention also provides a kind of speech recognition equipment, described device includes：
Acquisition module, the sound for acquiring caller；
Extraction module, the sound characteristic parameter for extracting the caller；
Comparing module is used for the sound characteristic parameter and the sound characteristic sample in pre-stored sound characteristic sample database
Originally it is compared；The sound characteristic sample includes the sound characteristic parameter of the contact person in address list；
Reminding module, for according to comparing result, sending out the prompt message of the identity of the caller.
Storage module, for storing the sound characteristic sample database, the sound characteristic sample database includes in address list
The sound characteristic parameter of contact person.
The present invention also provides a kind of mobile terminal, speech recognition equipment as described above is provided on the mobile terminal.
The method and device and mobile terminal of the speech recognition of the present invention by acquiring the sound of caller, and are extracted and
The sound characteristic parameter of electric person judges whether the sound with caller to the pre-stored sound characteristic sample database of comparison
The sound characteristic sample of characteristic parameter, and then the prompt message of the identity of the caller is sent out, to prevent user to be spoofed.It adopts
With the technical solution of the present embodiment, the identity of caller can reliably and be effectively differentiated, and make corresponding prompt, to subtract
Few user can be spoofed in incoming call is conversed, and further improve the safety of the incoming call call of user.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments for those of ordinary skill in the art without having to pay creative labor, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is the flow chart of an embodiment of the audio recognition method of the present invention；
Fig. 2 is the flow chart of another embodiment of the audio recognition method of the present invention；
Fig. 3 is the structural schematic diagram of an embodiment of the speech recognition equipment of the present invention；
Fig. 4 is the structural schematic diagram of another embodiment of the speech recognition equipment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the flow chart of an embodiment of the audio recognition method of the present invention.As shown in Figure 1, the method for the present embodiment
May include：
101, the sound of caller is acquired；
For example, when there is incoming call, the sound of caller can be recorded, realizes the sound of acquisition caller.
102, the sound characteristic parameter of caller is extracted；
Sound is the vibrations for causing vocal cords by the contraction of muscle of throat, using oral cavity, nasal cavity sympathetic response after send out.Each
The vocal cords feature of people is different, and the sound spectrum that whens vibrations sends out is the same as the fingerprint of people, hardly with there are identical.Wherein sound
The frequency of sound can be used for uniquely characterizing sound characteristic.For example, in the present embodiment, the frequency of sound may be used as sound spy
Levy parameter.The frequency of sound characteristic parameter such as sound is extracted from the sound of the caller of acquisition, can be referred in detail related existing
There is technology, details are not described herein.
103, sound characteristic parameter is compared with the sound characteristic sample in pre-stored sound characteristic sample database.
It may include the sound characteristic parameter of the All Contacts in address list in the sound characteristic sample.Therefore, user
The sound of contact person can be recorded, and then extract the sound characteristic parameter of contact person when with Affiliate sessions in address list,
And the sound characteristic sample of contact person is preserved, foundation and the one-to-one sound characteristic sample of contact person, to pre- in mobile phone
The sound characteristic sample of the contact person in entire address list is stored, a sound characteristic sample database is generated.When there is incoming call, in the future
The sound characteristic parameter of electric person with sound characteristic sample database in all sound characteristic samples be compared one by one.
104, according to comparing result, the prompt message of the identity of caller is sent out.
Exist and the sound characteristic of caller ginseng for example, the result of comparison is the sound characteristic sample database being pre-stored in mobile phone
When counting consistent sample, the information that the caller is a contact person in address list is sent out；User can lose vigilance in this way.
When comparing result is that the sample consistent with the sound characteristic parameter of caller is not present in the sound characteristic sample database being pre-stored in mobile phone
This when, sends out the information that the caller is the stranger other than address list, and such user can enhance your vigilance, prevent from being taken in by
It deceives.
The audio recognition method of the present embodiment by acquiring the sound of caller, and extracts the sound characteristic ginseng of caller
Number judges whether and the sound of the sound characteristic parameter of caller spy to the pre-stored sound characteristic sample database of comparison
Sample is levied, and then sends out the prompt message of the identity of the caller, the prompt to contact person and stranger is realized, to prevent
User is spoofed.Using the technical solution of the present embodiment, the identity of caller can reliably and be effectively differentiated, and make phase
The prompt answered can be spoofed with reducing user in incoming call is conversed, and further improve the safety of the incoming call call of user.
On the basis of the technical solution of above-mentioned embodiment illustrated in fig. 1, in the step 102 " sound characteristic of extraction caller
After parameter ", step 103 " carries out sound characteristic parameter and the sound characteristic sample in pre-stored sound characteristic sample database
Compare " before, can also include as follows：Judge whether the incoming call of caller is Stranger Calls according to address list；And determine incoming call
The incoming call of person is Stranger Calls.
Specifically, it can determine that incoming call is by judging whether include the telephone number of caller in address list, if including
Non- Stranger Calls, i.e. incoming call are the incoming call of the first contact person in address list；If otherwise not including, determine that incoming call is strange next
Electricity.
Further, it on the basis of the technical solution of above-described embodiment, sends a telegram here as the contact person's in address list when determining
After incoming call, it can also include the following steps：
(1) by the sound characteristic sample of the first contact person in the sound characteristic parameter of caller and sound characteristic sample database into
Row compares；When the sound characteristic parameter of caller is identical as the sound characteristic sample of the first contact person, step (2) is executed；It is no
Then when the sound characteristic sample of the sound characteristic parameter of caller and the first contact person differs, step (3) is executed；
Specifically, which corresponds to the first contact person in address list, by according to the incoming number of caller from sound
The corresponding sound characteristic sample of the incoming number is obtained in sound feature samples library, i.e., obtains first from sound characteristic sample database
It is the sound characteristic sample of people.Then the sound characteristic sample of the sound characteristic parameter of caller and first contact person are carried out
It compares.
(2) prompt message that caller is the first contact person is sent out；
(3) prompt message that caller is stranger is sent out.
Further, on the basis of the technical solution of above-described embodiment, step 104 " according to comparing result, sends out caller
Identity prompt message ", can specifically include：When sound characteristic sample database includes the sound characteristic parameter phase with caller
With sound characteristic sample when, extract the letter of corresponding second contact person of identical with sound characteristic parameter sound characteristic sample
Breath, such as the name of the second contact person can be extracted, or also further to extract the telephone number of second contact person；Concurrently
Go out the prompt message that caller is the second contact person.
Or when not including sound characteristic sample identical with the sound characteristic parameter of caller in sound characteristic sample database
When, send out the prompt message that caller is stranger.
The audio recognition method of above-described embodiment can reliably and effectively differentiate incoming call by using said program
The identity of person, and corresponding prompt is made, it can be spoofed in incoming call is conversed with reducing user, further improve coming for user
The safety of electricity call.
Fig. 2 is the flow chart of another embodiment of the audio recognition method of the present invention.The audio recognition method of the present embodiment
On the basis of the above embodiments, further it is described more fully technical scheme of the present invention.As shown in Fig. 2, the present embodiment
Audio recognition method, can specifically include：
201, the sound of caller is acquired；
202, the sound characteristic parameter of caller is extracted；
Such as the frequency of the sound of extraction caller.
203, judge whether the incoming call of caller is Stranger Calls according to address list；When being Stranger Calls, step is executed
204；Otherwise when not being Stranger Calls, step 206 is executed；
Specifically, when there is incoming call, the incoming number of the contact number and caller in address list is compared one by one, is judged
With the presence or absence of the contact number consistent with incoming number；When it is present, determine that the incoming call comes for the contact person in address list
Electricity, i.e., non-stranger's incoming call；When it be not present, determine that the incoming call is Stranger Calls.For example, caller is the contact in address list
People, but other numbers have been used, actually caller is not stranger, but the incoming call is Stranger Calls.Therefore it needs to sentence
Other telephone numbers of caller whether are stored in disconnected 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；Execute step 205；
205, sound characteristic parameter and all sound characteristic samples in pre-stored sound characteristic sample database are compared
It is right；When sound characteristic sample database includes sound characteristic sample identical with the sound characteristic parameter of caller, step is executed
208；When in sound characteristic sample database not including sound characteristic sample identical with the sound characteristic parameter of caller, step is executed
Rapid 210；When judgement incoming call for Stranger Calls after, will the sound characteristic parameter of caller in pre-stored sound characteristic sample database
All sound characteristic samples be compared one by one.When caller is still a contact person in address list.At this point, extraction and sound
The corresponding associated person information of the identical sound characteristic sample of sound characteristic parameter；Send out the prompt message that caller is contact person.
When in sound characteristic sample database not including sound characteristic sample identical with the sound characteristic parameter of caller, then
Caller is stranger.At this point, sending out the prompt message that caller is stranger.
206, determine that incoming call is the incoming call of the first contact person in address list；Execute step 207；
When the contact number in address list has the number consistent with the incoming number of caller, determine caller's
Incoming call is that the first contact person sends a telegram here.
207, by the sound characteristic sample of first contact person in the sound characteristic parameter of caller and sound characteristic sample database
Originally it is compared；When the sound characteristic parameter of caller is identical as the sound characteristic sample of the first contact person, step is executed
211；Otherwise when the sound characteristic sample of the sound characteristic parameter of caller and the first contact person differs, step 205 is executed；
It, can be with after the sound characteristic sample of sound characteristic parameter and first contact person of judgement caller differ
Execute step 205；Specifically, it since step 207 is by the sound characteristic parameter of caller, is somebody's turn to do with sound characteristic sample database
The incoming number of caller sound characteristic sample of corresponding first contact person in address list is compared, therefore is executing step
When rapid 205, it can save with the incoming number of the caller in sound characteristic sample database corresponding first in address list
The sound characteristic sample of contact person is compared again.
208, corresponding second associated person information of identical with sound characteristic parameter sound characteristic sample is extracted；Execute step
209；
Such as it can specifically extract the surname of corresponding second contact person of identical with sound characteristic parameter sound characteristic sample
Name, or can also further extract the telephone number of second contact person.
209, the prompt message that the caller is second contact person is sent out, is terminated.
Such as the prompt may include the name of the contact person, or can also include the electricity of the contact person in address list
Words.And it further can also be prompted, prompting the user whether to need the telephone number of the incoming call is stored in address list should
Contact person is under one's name.
210, the prompt message that the caller is stranger is sent out, is terminated.
Such as the mark that the caller is stranger can be specifically made in prompt, to be vigilant user, which may
For fraudulent call.And can also a swindle label further be arranged to the telephone number of the incoming call；And by the incoming number
And corresponding label is stored according to correspondence in telephone number management library, with when the next incoming number is sent a telegram here again,
The swindle label that the telephone number in library can be managed according to telephone number makes corresponding prompt to user, if user sees
It, can direct rejection for fraudulent call.
211, the prompt message that the caller is the contact person in address list is sent out, is terminated.
The present embodiment audio recognition method is judged by the incoming call to caller, when not being Stranger Calls, extraction
It the sound characteristic sample of contact person and is compared with the sound characteristic parameter of caller in sound characteristic sample database, judges to send a telegram here
Whether person is the contact person；When caller is the contact person, the prompt message that caller is contact person is sent out.Work as incoming call
When person is not the contact person or incoming call is Stranger Calls, by the sound characteristic parameter of caller and pre-stored sound characteristic sample
All sound characteristic samples in this library are compared one by one.When sound characteristic sample database includes the sound characteristic with caller
When the identical sound characteristic sample of parameter, then caller is still a contact person in address list；At this point, extraction and sound characteristic
The corresponding associated person information of the identical sound characteristic sample of parameter；Send out the prompt message that caller is contact person.Using this reality
The technical solution of example is applied, the identity of caller can reliably and be effectively differentiated, and make corresponding prompt, to reduce user
It can be spoofed in incoming call is conversed, further improve the safety of the incoming call call of user.
Fig. 3 is the structural schematic diagram of an embodiment of the speech recognition equipment of the present invention.As shown in figure 3, the present embodiment
Speech recognition equipment can specifically include：Acquisition module 11, extraction module 12, comparing module 13, reminding module 14 and storage mould
Block 15.
The speech recognition equipment of the present embodiment, acquisition module 11 are used to acquire the sound of caller；Extraction module 12 with adopt
Collect module 11 to connect, the sound for the caller that extraction module 12 is used to be acquired according to acquisition module 11, extracts and from the sound
The frequency of the sound characteristic parameter such as sound of electric person.Storage module 15 is for storing sound characteristic sample database, the sound characteristic sample
This library includes the sound characteristic parameter of the contact person in address list.The storage module 15 is specifically as follows storage in the present embodiment
Device.Comparing module 13 is connect with extraction module 12 and storage module 15 respectively, and comparing module 13 is for extracting extraction module 12
The sound characteristic sample database that is pre-stored of sound characteristic parameter and storage module 15 in sound characteristic sample be compared.Prompt
Module 14 is connect with comparing module 13, and reminding module 14 is used for the comparing result according to comparing module 13, sends out the body of caller
The prompt message of part.
The speech recognition equipment of the present embodiment realizes the realization mechanism of speech recognition by using above-mentioned module, with Fig. 1 institutes
Show that realization mechanism and the technique effect of embodiment of the method are identical, the record of above-mentioned embodiment illustrated in fig. 1 can be referred in detail,
This is repeated no more.
Fig. 4 is the structural schematic diagram of another embodiment of the speech recognition equipment of the present invention.As shown in figure 4, the present embodiment
Speech recognition equipment further comprise following technical solution on the basis of the technical solution of above-mentioned embodiment illustrated in fig. 3.
Further include judgment module 16 and determining module 17 as shown in figure 4, in the speech recognition equipment of the present embodiment.Wherein
Judgment module 16 is used to judge whether the incoming call of caller is Stranger Calls according to address list；In order to easy to operate, the judgement mould
Block 16 can specifically be arranged and start after extraction module 12, such as when extracting caller in the sound of 12 caller of extraction module
Sound characteristic parameter after, can trigger judgment module 16 startup.
Determining module 17 is connect with judgment module 16, and determining module 17 is used for the judging result according to judgment module 16, really
The incoming call for determining caller is Stranger Calls.
Still optionally further, the determining module 17 in the speech recognition equipment of the present embodiment is additionally operable to according to judgment module 16
Judging result, determine the incoming call be address list in the first contact person incoming call.Further, comparing module 13 also with determination
Module 17 connects, and comparing module 13 is additionally operable to the sound characteristic parameter and storage module 15 for the caller for extracting extraction module 12
The sound characteristic sample for first contact person that determining module 17 determines in the sound characteristic sample database of middle storage is compared；Example
As specifically, comparing module 13 is first according to the determination of determining module 17 as a result, obtain incoming call corresponding first in address list
It is people；Then the corresponding sound characteristic sample of first contact person is obtained from the sound characteristic sample database that storage module 15 stores
This；The sound characteristic parameter for the caller that finally extraction module 12 is extracted sound characteristic sample corresponding with first contact person
It is compared.
Further, reminding module 14 is additionally operable to the comparison result according to comparing module 13, when the sound characteristic of caller
When parameter is identical as the sound characteristic sample of the first contact person, the prompt message that caller is the first contact person is sent out；Or it carries
Show that module 14 is additionally operable to, when the sound characteristic sample of the sound characteristic parameter of caller and the first contact person differs, issue
Electric person is the prompt message of stranger.
Or still optionally further, the reminding module 14 in the speech recognition equipment of the present embodiment is specifically used for according to comparison
The comparison result of module 13, when sound characteristic sample database includes sound characteristic sample identical with the sound characteristic parameter of caller
This when, extracts the information of corresponding second contact person of identical with sound characteristic parameter sound characteristic sample, such as second contacts
The name of people, or further include further the telephone number of the second contact person；And it is second contact person's to issue electric person
Prompt message；
Or reminding module 14 is additionally operable to the comparison result according to comparing module 13, when not including in sound characteristic sample database
When sound characteristic sample identical with the sound characteristic parameter of caller, the prompt message that caller is stranger is sent out.
Still optionally further, in the speech recognition equipment of the present embodiment judgment module 16 be specifically used for judge be in address list
It is no to include the telephone number of caller, if including, determine that incoming call is non-Stranger Calls, i.e., incoming call is the contact person's in address list
Incoming call；If otherwise not including, determine that incoming call is Stranger Calls.
The speech recognition equipment of the present embodiment realizes the realization mechanism of speech recognition by using above-mentioned module, with Fig. 2 institutes
Show that realization mechanism and the technique effect of embodiment of the method are identical, the record of above-mentioned embodiment illustrated in fig. 2 can be referred in detail,
This is repeated no more.
The present invention also provides a kind of mobile terminals, and above-mentioned Fig. 3 or embodiment illustrated in fig. 4 are provided on the mobile terminal
Speech recognition device, and the audio recognition method that above-mentioned Fig. 1 or embodiment illustrated in fig. 2 may be used realizes that voice is known
Not, the related of above-described embodiment can be referred in detail to record, details are not described herein.
One of ordinary skill in the art will appreciate that：Realize that all or part of step of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer read/write memory medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned includes：ROM, RAM, magnetic disc or
The various media that can store program code such as person's CD.
Finally it should be noted that：The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, it will be understood by those of ordinary skill in the art that：Its according to
So can with technical scheme described in the above embodiments is modified, either to which part or all technical features into
Row equivalent replacement；And these modifications or replacements, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (8)
1. a kind of audio recognition method, which is characterized in that the method includes：
Acquire the sound of caller；
Extract the sound characteristic parameter of the caller；
Judge whether the incoming call of the caller is Stranger Calls according to address list；
If it is determined that the incoming call is the incoming call of the first contact person in the address list, by the sound characteristic of the caller
Parameter is compared with the sound characteristic sample of the first contact person described in pre-stored sound characteristic sample database, if alternatively, really
The incoming call of the fixed caller is Stranger Calls, by the sound characteristic parameter and the institute in pre-stored sound characteristic sample database
There are sound feature samples to be compared, the sound characteristic sample includes the sound characteristic ginseng of the contact person in the address list
Number；
According to comparing result, the prompt message of the identity of the caller is sent out.
2. according to the method described in claim 1, it is characterized in that, when determining that the incoming call is first in the address list
When being the incoming call of people, described according to comparing result, the prompt message for sending out the identity of the caller includes：
When the sound characteristic parameter of the caller is identical as the sound characteristic sample of the first contact person, institute is sent out
State the prompt message that caller is first contact person；Otherwise when the sound characteristic parameter of the caller and described the
When the sound characteristic sample of one contact person differs, the prompt message that the caller is stranger is sent out.
3. according to the method described in claim 1, it is characterized in that, judging that the incoming call of the caller is according to the address list
No is Stranger Calls, is specifically included：
Judge whether include the telephone number of the caller in the address list, if including determining that the incoming call is non-strange
Incoming call, i.e., the described incoming call are the incoming call of the contact person in the address list；If otherwise not including, determine that the incoming call is strange next
Electricity.
4. according to the method described in claim 3, it is characterized in that, when determining that incoming call of the incoming call for caller is strange next
When electric, according to comparing result, the prompt message of the identity of the caller sent out, is specifically included：
When the sound characteristic sample database includes sound characteristic sample identical with the sound characteristic parameter of the caller
This when, extracts the information of corresponding second contact person of identical with the sound characteristic parameter sound characteristic sample；
Send out the prompt message that the caller is second contact person；
Or when not including sound identical with the sound characteristic parameter of the caller in the sound characteristic sample database
When feature samples, the prompt message that the caller is stranger is sent out.
5. a kind of speech recognition equipment, which is characterized in that described device includes：
Acquisition module, the sound for acquiring caller；
Extraction module, the sound characteristic parameter for extracting the caller；
Judgment module, for judging whether the incoming call of the caller is Stranger Calls according to address list；
Comparing module is used for if it is determined that the incoming call is the incoming call of the first contact person in the address list, by the caller
The sound characteristic parameter and the sound characteristic sample of the first contact person described in pre-stored sound characteristic sample database carry out
It compares, or, however, it is determined that the incoming call of the caller is Stranger Calls, and the sound characteristic parameter is special with pre-stored sound
All sound characteristic samples in sign sample database are compared, and the sound characteristic sample includes the contact in the address list
The sound characteristic parameter of people；
Reminding module, for according to comparing result, sending out the prompt message of the identity of the caller；
Storage module, for storing the sound characteristic sample database, the sound characteristic sample database includes the contact in address list
The sound characteristic parameter of people.
6. device according to claim 5, which is characterized in that when determine it is described incoming call be the address list in first
When being the incoming call of people, the reminding module is additionally operable to contact with described first when the sound characteristic parameter of the caller
When the sound characteristic sample of people is identical, the prompt message that the caller is first contact person is sent out；Or it is additionally operable to work as
When the sound characteristic parameter of the caller is differed with the sound characteristic sample of first contact person, send out described next
Electric person is the prompt message of stranger.
7. device according to claim 5, which is characterized in that the reminding module is specifically used for working as the sound characteristic
When sample database includes sound characteristic sample identical with the sound characteristic parameter of the caller, extraction and the sound
The information of corresponding second contact person of the identical sound characteristic sample of characteristic parameter；It is described second to send out the caller
The prompt message of contact person；
Or the reminding module, it is additionally operable in the sound characteristic sample database not include the sound with the caller
When the identical sound characteristic sample of characteristic parameter, the prompt message that the caller is stranger is sent out.
8. a kind of mobile terminal, which is characterized in that be provided with any languages of claim 5-7 as above on the mobile terminal
Sound identification device.
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 CN104954532A (en) | 2015-09-30 |
| CN104954532B true 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) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105376143B (en) * | 2015-12-03 | 2019-05-07 | 小天才科技有限公司 | A kind of method and device identifying identity of the sender |
| 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 |
| 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 |
| 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 |
| CN109920450B (en) * | 2017-12-13 | 2024-08-06 | 北京回龙观医院 | Information processing apparatus and information processing method |
Citations (3)
| 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 |
| 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 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9300790B2 (en) * | 2005-06-24 | 2016-03-29 | Securus Technologies, Inc. | Multi-party conversation analyzer and logger |
| CN100563608C (en) * | 2008-05-21 | 2009-12-02 | 清华大学深圳研究生院 | The electric cochlea Chinese fixed electric stimulation amplitude changing pattern in-vitro voice processing unit |
| CN101944359B (en) * | 2010-07-23 | 2012-04-25 | 杭州网豆数字技术有限公司 | Voice recognition method for 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 |
-
2015
- 2015-06-19 CN CN201510346867.7A patent/CN104954532B/en not_active Expired - Fee Related
Patent Citations (3)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104954532A (en) | 2015-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104954532B (en) | The method and device and mobile terminal of speech recognition | |
| CN103888581B (en) | A kind of communication terminal and its method for recording call-information | |
| US20120159617A1 (en) | Headset, method for controlling usage of headset, and terminal | |
| CN104159229B (en) | Incoming call processing method and device | |
| US7920680B2 (en) | VoIP caller authentication by voice signature continuity | |
| US20030074201A1 (en) | Continuous authentication of the identity of a speaker | |
| CN103139404A (en) | System and method for generating interactive voice response display menu based on voice recognition | |
| WO2015192450A1 (en) | Identity identification method and apparatus and communication terminal | |
| CN103731832A (en) | System and method for preventing phone and short message frauds | |
| CN110072006A (en) | The answer method and intelligent terminal of intelligent terminal | |
| CN105263126B (en) | Short-message verification method, apparatus and system | |
| CN104023110A (en) | Voiceprint recognition-based caller management method and mobile terminal | |
| CN103856624A (en) | Identity recognition method and mobile terminals | |
| CN110536029B (en) | Interaction method, network side equipment, terminal equipment, storage medium and system | |
| CN108391020A (en) | A kind of call control method, device, equipment and storage medium | |
| CN106850931A (en) | The method and mobile intelligent terminal of Barassment preventing telephone | |
| CN104183238A (en) | Old people voiceprint recognition method based on questioning and answering | |
| CN106714178A (en) | Abnormal call judgment method and device | |
| WO2021051504A1 (en) | Method for identifying abnormal call party, device, computer apparatus, and storage medium | |
| CN104348621A (en) | Authentication system based on voiceprint recognition and method thereof | |
| CN107360313A (en) | For identifying anti-the swindle communication system and method for Stranger Calls | |
| CN110062097A (en) | Harassing call processing method, device, mobile terminal and storage medium | |
| CN103546613A (en) | Contact person recording method, contact person recording device and mobile terminal | |
| CN105991809A (en) | Method and device for storing temporary contact | |
| CN104869264A (en) | Method of monitoring swindle telephone and joining telephone conference and device of monitoring swindle telephone and joining telephone conference |
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 |