CN110290280A - A kind of recognition methods of the SOT state of termination, device and storage medium - Google Patents
A kind of recognition methods of the SOT state of termination, device and storage medium Download PDFInfo
- Publication number
- CN110290280A CN110290280A CN201910453671.6A CN201910453671A CN110290280A CN 110290280 A CN110290280 A CN 110290280A CN 201910453671 A CN201910453671 A CN 201910453671A CN 110290280 A CN110290280 A CN 110290280A
- Authority
- CN
- China
- Prior art keywords
- audio data
- termination
- state
- audio
- frequency characteristics
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 239000003550 marker Substances 0.000 claims abstract description 28
- 238000000605 extraction Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims description 19
- 230000015654 memory Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 18
- 238000009432 framing Methods 0.000 description 32
- 238000012545 processing Methods 0.000 description 25
- 239000011159 matrix material Substances 0.000 description 21
- 238000010586 diagram Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 206010048669 Terminal state Diseases 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000001228 spectrum Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W8/00—Network data management
- H04W8/22—Processing or transfer of terminal data, e.g. status or physical capabilities
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the present application provides recognition methods, device and the storage medium of a kind of SOT state of termination, which comprises obtains the call request that calling terminal is sent to called terminal;It include the terminal iidentification of called terminal in call request;According to terminal iidentification, obtains called terminal and be directed to the audio data that call request is sent;Feature extraction is carried out to audio data and obtains audio frequency characteristics;Audio frequency characteristics are input to preset state recognition model, recognize the SOT state of termination of called terminal;Wherein, state recognition model is to be trained to obtain to default training pattern by the corresponding audio frequency characteristics sample of audio data sample and the corresponding SOT state of termination marker samples of audio data sample.In this way, by extracting audio frequency characteristics from the audio data of called terminal, the SOT state of termination that called terminal is determined using the audio frequency characteristics, without executing the process in the prior art that audio data is converted to text data, to solve the problems, such as that recognition accuracy in the prior art is lower.
Description
Technical field
This application involves fields of communication technology, are situated between more particularly to a kind of recognition methods of SOT state of termination, device and storage
Matter.
Background technique
With the fast development of the communication technology, mobile terminal has become the essential tool that people interact.
In view of usually there is the case where called terminal is not turned in outgoing call scene, at this point, calling terminal need to get it is called
The current SOT state of termination of terminal (such as off-mode, engaged condition, ring unanswered's state, shutdown status, absent-subscriber condition, rejection shape
State etc.) so that calling terminal can execute intelligent strategy according to the SOT state of termination, if the SOT state of termination is shutdown status,
Playback operation is then no longer executed, if the SOT state of termination is engaged condition, playback operation etc. is executed after preset time period, this
Sample can save system resource to avoid blindly redialing.
In the prior art, ASR (automatic speech recognition is generallyd use;Automatic Speech Recognition) skill
The audio data that called terminal returns is converted to text data, the identification of the SOT state of termination is then carried out according to text data by art.
But inventor has found in research above scheme, audio data is converted to text data, so that the sound in audio data
It adjusts, the information such as audio spacing are lost, and cause recognition accuracy lower.
Summary of the invention
In view of the above problems, the embodiment of the present application provides recognition methods, device and the storage medium of a kind of SOT state of termination, leads to
It crosses and extracts audio frequency characteristics from the audio data of called terminal, the SOT state of termination of called terminal, nothing are determined using the audio frequency characteristics
The process in the prior art that audio data is converted to text data need to be executed, so that it is accurate to solve identification in the prior art
The lower problem of rate.
According to the embodiment of the present application in a first aspect, providing a kind of recognition methods of SOT state of termination, which comprises
Obtain the call request that calling terminal is sent to called terminal;Including the called terminal in the call request
Terminal iidentification;
According to the terminal iidentification, obtains the called terminal and be directed to the audio data that the call request is sent;
Feature extraction is carried out to the audio data and obtains audio frequency characteristics;
The audio frequency characteristics are input to preset state recognition model, recognize the SOT state of termination of the called terminal;
Wherein, the state recognition model is by the corresponding audio frequency characteristics sample of audio data sample and the audio data sample
Corresponding SOT state of termination marker samples, are trained to obtain to default training pattern.
According to the second aspect of the embodiment of the present application, a kind of identification device of SOT state of termination is provided, described device includes:
Request module, the call request sent for obtaining calling terminal to called terminal;In the call request
Terminal iidentification including the called terminal;
Audio data obtains module, for obtaining the called terminal and asking for the calling according to the terminal iidentification
Seek the audio data of transmission;
Characteristic extracting module obtains audio frequency characteristics for carrying out feature extraction to the audio data;
State recognition module recognizes the quilt for the audio frequency characteristics to be input to preset state recognition model
It is the SOT state of termination of terminal;Wherein, the state recognition model be by the corresponding audio frequency characteristics sample of audio data sample with
And the corresponding SOT state of termination marker samples of the audio data sample, default training pattern is trained to obtain.
According to the third aspect of the embodiment of the present application, provide a kind of identification device of SOT state of termination, including processor and
Memory, wherein
The processor executes the computer program code that the memory is stored, to realize terminal described herein
The step of recognition methods of state.
According to the fourth aspect of the embodiment of the present application, a kind of computer readable storage medium is provided, it is described computer-readable
Computer program is stored on storage medium, the computer program realizes the SOT state of termination described herein when being executed by processor
Recognition methods the step of.
The embodiment of the present application includes the following advantages:
The call request that the embodiment of the present application is sent by obtaining calling terminal to called terminal;It is wrapped in the call request
Include the terminal iidentification of the called terminal;According to the terminal iidentification, obtains the called terminal and sent out for the call request
The audio data sent;Feature extraction is carried out to the audio data and obtains audio frequency characteristics;The audio frequency characteristics are input to default
State recognition model, recognize the SOT state of termination of the called terminal;Wherein, the state recognition model is by audio number
According to the corresponding audio frequency characteristics sample of sample and the corresponding SOT state of termination marker samples of the audio data sample, to default training
Model is trained to obtain.In this way, by extracting audio frequency characteristics from the audio data of called terminal, it is true using the audio frequency characteristics
The SOT state of termination for determining called terminal, without executing the process in the prior art that audio data is converted to text data, thus
It solves the problems, such as that recognition accuracy in the prior art is lower, and improves recognition efficiency.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of the recognition methods embodiment of SOT state of termination of the application;
Fig. 2 is a kind of step flow chart of the recognition methods alternative embodiment of SOT state of termination of the application;
Fig. 3 is a kind of step flow chart of the recognition methods alternative embodiment of SOT state of termination of the application;
Fig. 4 is a kind of step flow chart of the recognition methods alternative embodiment of SOT state of termination of the application;
Fig. 5 is a kind of structural block diagram of the identification device embodiment of SOT state of termination of the application;
Fig. 6 is a kind of structural block diagram of the identification device alternative embodiment of SOT state of termination of the application;
Fig. 7 is a kind of structural block diagram of the identification device alternative embodiment of SOT state of termination of the application;
Fig. 8 is a kind of structural block diagram of the identification device alternative embodiment of SOT state of termination of the application;
Fig. 9 is the hardware structural diagram of the identification device for the SOT state of termination that another embodiment of the application provides;
Figure 10 is the hardware structural diagram of the identification device for the SOT state of termination that another embodiment of the application provides.
Specific embodiment
In order to make the above objects, features, and advantages of the present application more apparent, with reference to the accompanying drawing and it is specific real
Applying mode, the present application will be further described in detail.
Referring to Fig.1, a kind of step flow chart of the recognition methods embodiment of SOT state of termination of the application, the side are shown
Method can be applied to calling terminal or server etc., wherein the server is connect with calling terminal and called terminal respectively;
It can specifically include following steps:
Step 101, the call request that calling terminal is sent to called terminal is obtained.
It in the embodiment of the present application, may include the terminal iidentification of called terminal in call request, wherein calling terminal
User passes through the Subscriber Number of calling terminal dialing called terminal, dials operation so as to basis and generates call request.
Calling terminal and called terminal in the embodiment of the present application can be respectively following any: smart phone, intelligence
Wrist-watch and tablet computer etc. have the terminal of call function, and above-mentioned example is merely illustrative, and the application is not construed as limiting this.
It should be noted that if the application obtains the SOT state of termination by server, then this step can be by server monitoring
Whether multiple terminals generate call request, in the case where monitoring the generation call request of some terminal, determine some terminal
Calling terminal as in the application, at this point, the call request that the available calling terminal of server is sent to called terminal.
Step 102, it according to terminal iidentification, obtains called terminal and is directed to the audio data that call request is sent.
Since called terminal is in the case where receiving the call request of calling terminal, if called terminal is not turned on,
It needs to make requests response to the call request of calling terminal, it can it generates and is directed to the corresponding audio data of the call request,
And audio data is sent to calling terminal, wherein if the SOT state of termination is obtained by server in the application, in the audio number
According to before being sent to calling terminal, this step can be got audio data, certainly, the application by server from called terminal
The audio data can also be obtained from calling terminal, above-mentioned example is only lifted after the audio data is sent to calling terminal
Example explanation, the application are not construed as limiting this.
Illustratively, which can be the access failure voice prompting data prerecorded, and the usual audio data can
With the access failure voice prompting data comprising 10 seconds to 40 seconds, which can be 8000Hz monophonic audio waveform, such as
The audio data include " you are good, and the phone that you dial temporarily is not turned on, and please dials again later ", " ask should not on-hook, what you dialed
Phone is busy now " etc..
Step 103, feature extraction is carried out to audio data and obtains audio frequency characteristics.
Wherein, which comprises at least one of the following: mel-frequency cepstrum coefficient feature, sonograph feature, chromatography
Figure feature.It is, of course, also possible to include other audio frequency characteristics, such as time domain acoustic feature, frequency domain acoustic feature, the application is to this
It is not construed as limiting.
It should be noted that due to generally including noise in audio data, and noise may result in useful audio number
According to annihilated, therefore, which can be denoised, so that the application can be carried out for the audio data after denoising
Feature extraction.
It in the embodiment of the present application, can be right in the case where the audio frequency characteristics include mel-frequency cepstrum coefficient feature
The audio data executes sub-frame processing and obtains audio framing, and to each audio framing calculating cycle power spectrum, by different filtering
Device is applied in Cyclical power spectrum and calculates the energy value of each filter, and calculates the corresponding logarithm of energy value, to each right
Numerical value carry out discrete cosine transform obtain multiple numerical value to be selected, from it is multiple wait select in numerical value extract specified quantity wait select
Numerical value obtains the framing mel-frequency cepstrum coefficient feature of the audio framing, by the framing mel-frequency cepstrum of all audio frequency framing
Coefficient characteristics constitute the mel-frequency cepstrum coefficient feature of the audio data, currently, mfcc (Mel frequency cepstral system can be used
Number;Mel Frequency Cepstrum Coefficient) the library function execution above process.Illustratively, the Meier got
Frequency cepstral coefficient feature can be the matrix of a n*m, wherein n can indicate point for the audio framing that audio data includes
Frame number, m indicate the corresponding characteristic dimension of framing mel-frequency cepstrum coefficient feature.It, can be to n*m in order to improve processing speed
Matrix simplified, in one possible implementation, the matrix of the n*m is subjected to matrix conversion and obtains the matrix of 1*m,
Detailed process includes: to carry out mean value calculation to the data in the i-th column to obtain the corresponding characteristic of the i-th column, and i is the square of n*m
Either rank in battle array.
In the case where the audio frequency characteristics include sonograph feature, equally sub-frame processing can be executed to the audio data and obtained
To audio framing, and Fourier transformation is carried out to each audio framing and obtains the corresponding sonograph of each audio framing, is based on sound
The feature extraction algorithm of spectrogram Energy distribution carries out feature extraction to the corresponding sonograph of each audio framing and obtains each audio
Multiple sound spectrum evaluations of estimate of framing, multiple sound spectrum evaluation of estimate is the framing sonograph feature of the audio framing, by the whole
The framing sonograph feature of audio framing constitutes the sonograph feature of the audio data.Illustratively, the sonograph feature got
It can be the matrix of a v*u, wherein v can indicate the framing serial number of the audio framing of audio data, and u indicates framing sound spectrum
The characteristic dimension of figure feature.Similarly, in order to improve processing speed, the matrix of the v*u can be subjected to matrix conversion and obtains 1*v
Matrix, detailed process includes: to carry out mean value calculation to the data in jth column and obtain jth arranging corresponding characteristic, and j is
Either rank in the matrix of v*u.
In the case where the audio frequency characteristics include chromatogram feature, equally sub-frame processing can be executed to the audio data and obtained
To audio framing, and Fourier transformation is carried out to each audio framing and obtains the corresponding chromatogram of each audio framing, based on pre-
If chromatographic characteristics extraction algorithm, feature extraction is carried out to the corresponding chromatogram of each audio framing and obtains the more of each audio framing
A chromatographic evaluation value, multiple chromatographic evaluation value is the framing chromatogram feature of the audio framing, by all audio frequency framing
Framing chromatogram feature constitute the chromatogram feature of the audio data.Illustratively, the chromatogram feature got can be one
The matrix of a b*d, wherein b can indicate the framing serial number of the audio framing of audio data, and d indicates framing chromatogram feature
Characteristic dimension.Similarly, in order to improve processing speed, the matrix of the b*d can be subjected to matrix conversion and obtains the matrix of 1*d,
Detailed process includes: to carry out mean value calculation to the data in h column to obtain the corresponding characteristic of h column, and h is the square of b*d
Either rank in battle array.The detailed process of above-mentioned acquisition audio frequency characteristics can refer to the prior art, repeat no more.
It should be noted that if the audio frequency characteristics include following at least two: mel-frequency cepstrum coefficient feature, sonograph
Feature, chromatogram feature, it is contemplated that the corresponding matrix size of at least two audio frequency characteristics may be different, therefore, it is impossible to will at least
Two kinds of audio frequency characteristics merge into an eigenmatrix, and in order to solve this problem, the application can be by least two audio frequency characteristics point
Not carry out matrix conversion obtain corresponding row matrix, and merge the row matrix of at least two audio frequency characteristics to obtain target line
Matrix, in this way, the audio frequency characteristics in the application are the target row matrix.Certainly, the application can not also be at least two sounds
Frequency feature carries out matrix conversion, so that the audio frequency characteristics in the application are that at least two audio frequency characteristics are corresponding
Eigenmatrix.
Step 104, audio frequency characteristics are input to preset state recognition model, recognize the SOT state of termination of called terminal.
In the embodiment of the present application, state recognition model be by the corresponding audio frequency characteristics sample of audio data sample and
The corresponding SOT state of termination marker samples of audio data sample, are trained to obtain to default training pattern, the default training pattern
Can for RNN (Recognition with Recurrent Neural Network, Recurrent Neural Network), CNN (convolutional neural networks,
Convolutional Neural Networks), support vector machines etc., the application is not construed as limiting this.
Wherein, if the SOT state of termination marker samples that the state recognition model includes include off-mode, engaged condition, nobody
State, shutdown status, absent-subscriber condition, rejection state etc. are answered, then the SOT state of termination in this step is terminal described above
Some in status indication sample, above-mentioned example is merely illustrative, and the application is not construed as limiting this.
It should be noted that the above-mentioned identification process for carrying out the SOT state of termination according to audio data, the usual file of audio data
Larger, calculating is complex, accordingly, it is possible to there is a problem of that processing speed is slower, the application passes through pressure test and finds: using
Multithreading carries out the identification of the SOT state of termination, entire throughput can be improved, and improve processing capacity, furthermore it is also possible to
By increasing group scheme, so that executing the identification process of the SOT state of termination jointly by multiple servers in cluster.
In addition, the application can externally provide service by the RestFull interface mode that web service container is issued
To detect the call request of calling terminal transmission, and after detecting the call request that calling terminal is sent, asked according to calling
The audio protocols data for obtaining called terminal are sought, since the audio protocols data are usually protocol data, it is therefore desirable to the sound
Frequency protocol data carries out the audio data after protocol analysis is parsed, and audio data is sent to audio processor, so that
Audio frequency characteristics can be obtained to audio data progress feature extraction by obtaining audio processor, then call Tensorflow engineering
It practises engine and executes trained state recognition model, obtain the SOT state of termination of the called terminal, finally by Web container publication
The SOT state of termination is sent to calling terminal by RestFull interface.Wherein, in order to improve recognition efficiency, can start in Web container
While, Tensorflow machine learning engine is loaded and initialized, a large amount of calculate is avoided and wastes, and reduce
The a large amount of waiting time, to improve recognition efficiency.
Using the above method, the call request that calling terminal is sent to called terminal is obtained;It include called in call request
The terminal iidentification of terminal;According to terminal iidentification, obtains called terminal and be directed to the audio data that call request is sent;To audio data
It carries out feature extraction and obtains audio frequency characteristics;Audio frequency characteristics are input to preset state recognition model, recognize called terminal
The SOT state of termination;Wherein, state recognition model is by the corresponding audio frequency characteristics sample of audio data sample and audio data sample
This corresponding SOT state of termination marker samples, is trained to obtain to default training pattern.In this way, passing through the audio from called terminal
Audio frequency characteristics are extracted in data, and the SOT state of termination of called terminal is determined using the audio frequency characteristics, it is in the prior art without executing
Audio data is converted to the process of text data, thus solve the problems, such as that recognition accuracy in the prior art is lower, and
Improve recognition efficiency.
Referring to Fig. 2, a kind of step flow chart of the recognition methods alternative embodiment of SOT state of termination of the application is shown, is walked
The audio frequency characteristics are input to preset state recognition model described in rapid 104, recognize the terminal shape of the called terminal
State may include steps of:
Step 1041, audio frequency characteristics are input to state recognition model, obtain audio frequency characteristics and corresponds to different terminals state mark
Remember the identification and evaluation value of sample.
In the application implementation, which is the terminal shape for including in the state recognition model
State.In one possible implementation, softmax network layer can be set in the state recognition model, to pass through
The corresponding output end value of different terminals status indication sample is mapped to (0,1) section by softmax network layer, to obtain the quilt
The probability value for making terminal belong to different terminals status indication sample, above-mentioned example are merely illustrative, and the application does not limit this
It is fixed.
Step 1042, the SOT state of termination is obtained from SOT state of termination marker samples according to identification and evaluation value.
If the identification and evaluation value is the probability value that called terminal belongs to different terminals status indication sample, can determine most
The corresponding SOT state of termination marker samples of identification and evaluation value are the SOT state of termination greatly.
Referring to Fig. 3, a kind of step flow chart of the recognition methods alternative embodiment of SOT state of termination of the application is shown,
The audio frequency characteristics are input to preset state recognition model described in step 104, recognize the terminal of the called terminal
Before state, it can also include the following steps:
Step 105, audio data sample and the corresponding SOT state of termination marker samples of audio data sample are obtained.
In one possible implementation, the audio data sample can be marked by handmarking's mode
To corresponding SOT state of termination marker samples, in alternatively possible implementation, due to the sample number of the audio data sample
It measures more, in order to reduce handmarking's amount, and improves signature velocity, the application can also be converted to the audio data sample
Text data sample, thus by being identified to obtain corresponding SOT state of termination marker samples to text data sample, it is contemplated that
There may be part text data samples to fail to be marked, at this time, it may be necessary to using handmarking's mode to the part textual data
It is marked according to sample.Illustratively, 100,000 audio data samples can be usually chosen to be trained.
In addition, getting audio data sample and audio data sample described above for the ease of data management
In the case where corresponding SOT state of termination marker samples, format can be arranged according to default file title in each audio data sample
It is stored in file directory, illustratively, it may include: the corresponding sample of audio data sample which, which is arranged format,
The status indication of mark and the corresponding SOT state of termination marker samples of audio data sample mark, if different terminals state mark
Remember that sample includes off-mode, engaged condition, ring unanswered's state, shutdown status, absent-subscriber condition, rejection state, then pass is set
The corresponding status indication of machine state is identified as " 1 ", and the corresponding status indication of engaged condition is identified as " 2 ", ring unanswered's state pair
The status indication answered is identified as " 3 ", and the corresponding status indication of shutdown status is identified as " 4 ", the corresponding status indication of absent-subscriber condition
Be identified as " 5 ", the corresponding status indication of rejection state is identified as " 6 ", in this way, based on different terminals status indication sample from it is different
Corresponding relationship between status indication mark, if the file name of some audio data sample is
" S201811043132343590231_4.wav ", then " S201811043132343590231 " indicates some audio data sample
This sample identification, " 4 " indicate that the corresponding SOT state of termination marker samples of some audio data sample are shutdown status, " wav "
Indicate audio file formats.
Step 106, feature extraction is carried out to each audio data sample respectively, it is corresponding obtains each audio data sample
Audio frequency characteristics sample.
In the embodiment of the present application, which equally may include following at least one: mel-frequency cepstrum
Coefficient characteristics, sonograph feature, chromatogram feature.Wherein, the type phase of the type of the audio frequency characteristics sample and the audio frequency characteristics
Together, for example, if the audio frequency characteristics sample is mel-frequency cepstrum coefficient feature, the audio frequency characteristics got in step 103
The as mel-frequency cepstrum coefficient feature of the audio data, for another example, if the audio frequency characteristics sample is mel-frequency cepstrum coefficient
Feature harmony chromatogram characteristic, the then audio frequency characteristics got in step 103 are the mel-frequency cepstrum system of the audio data
The acquisition process of number feature and sonograph feature, the audio frequency characteristics sample can refer to step 103, repeat no more.
Step 107, pass through the corresponding audio frequency characteristics sample of audio data sample and the corresponding terminal of audio data sample
Status indication sample is trained default training pattern to obtain state recognition model.
In the embodiment of the present application, quasi- by the identification for the state recognition model being trained to default training pattern
True rate is up to 95% or more.
As it can be seen that by step 105 to the available state recognition model of step 107, so that the application can use the shape
State identification model carries out the identification of the SOT state of termination to audio data.
Referring to Fig. 4, a kind of step flow chart of the recognition methods alternative embodiment of SOT state of termination of the application is shown, is examined
Consider the fast development with terminal, in fact it could happen that new terminal state and the state recognition model have the wrong feelings of identification
Condition, therefore, it is necessary to be updated to the state recognition model according to predetermined period, so that the state recognition model is constantly complete
It is kind.
Audio frequency characteristics are input to preset state recognition model described in step 104, recognize the end of called terminal
After the state of end, it can also include the following steps:
Step 108, audio data to be verified is obtained from history audio data according to predetermined period.
Wherein, which can be to pass through the state recognition model to carry out the data after SOT state of termination identification.
Since the data bulk of the history audio data is larger, if being verified to whole history audio datas, take considerable time,
Therefore, the application the audio data to be verified can be obtained from history audio data in one possible implementation can
To obtain the audio data to be verified at random from history audio data, in alternatively possible implementation, according to history
The identification and evaluation value of the corresponding target terminal state of audio data, obtains the audio data to be verified, which is
The SOT state of termination determined by state recognition model, specifically, in the knowledge of the corresponding target terminal state of the history audio data
In the case that other evaluation of estimate is outside default evaluation of estimate range, determine that the history audio data is the audio data to be verified, it is above-mentioned
Example is merely illustrative, and the application is not construed as limiting this.
Step 109, the corresponding handmarking's SOT state of termination of audio data to be verified is obtained.
In this step, since the corresponding target terminal state of audio data to be verified may be inaccurate, it is therefore desirable to adopt
Manually mark mode obtains the corresponding handmarking's SOT state of termination of the audio data to be verified.
Step 110, according to audio data to be verified and handmarking's SOT state of termination, state recognition model is updated.
In the embodiment of the present application, if handmarking's SOT state of termination of the audio data to be verified and the target terminal state
Difference, then using the audio data to be verified as audio data to be trained, if handmarking's terminal of the audio data to be verified
State is identical as the target terminal state, then further without being carried out by the audio data to be verified to the state recognition model
Training, therefore, which can be filtered out, in this way, by the audio data to be trained and can be somebody's turn to do wait train
The corresponding handmarking's SOT state of termination of audio data is input to the state recognition model, to carry out the state recognition model into one
Step ground training, to achieve the purpose that enhance model.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method
It closes, but those skilled in the art should understand that, the embodiment of the present application is not limited by the described action sequence, because according to
According to the embodiment of the present application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and related movement not necessarily the application is implemented
Necessary to example.
Using the above method, the call request that calling terminal is sent to called terminal is obtained;It include called in call request
The terminal iidentification of terminal;According to terminal iidentification, obtains called terminal and be directed to the audio data that call request is sent;To audio data
It carries out feature extraction and obtains audio frequency characteristics;Audio frequency characteristics are input to preset state recognition model, recognize called terminal
The SOT state of termination;Wherein, state recognition model is by the corresponding audio frequency characteristics sample of audio data sample and audio data sample
This corresponding SOT state of termination marker samples, is trained to obtain to default training pattern.In this way, passing through the audio from called terminal
Audio frequency characteristics are extracted in data, and the SOT state of termination of called terminal is determined using the audio frequency characteristics, it is in the prior art without executing
Audio data is converted to the process of text data, thus solve the problems, such as that recognition accuracy in the prior art is lower, and
Improve recognition efficiency.
Referring to Fig. 5, a kind of structural block diagram of 50 embodiment of identification device of SOT state of termination of the application is shown, specifically may be used
To include following module:
Request module 501, the call request sent for obtaining calling terminal to called terminal;The call request
In include the called terminal terminal iidentification;
Audio data obtains module 502, for obtaining the called terminal for the calling according to the terminal iidentification
Request the audio data sent;
Characteristic extracting module 503 obtains audio frequency characteristics for carrying out feature extraction to the audio data;
State recognition module 504 recognizes described for the audio frequency characteristics to be input to preset state recognition model
The SOT state of termination of called terminal;Wherein, the state recognition model is by the corresponding audio frequency characteristics sample of audio data sample
And the corresponding SOT state of termination marker samples of the audio data sample, default training pattern is trained to obtain.
Referring to Fig. 6, in the alternative embodiment of the application, described device 50 further includes following module:
Data sample obtains module 505, corresponding for obtaining the audio data sample and the audio data sample
SOT state of termination marker samples;
Feature samples obtain module 506, for carrying out feature extraction to each audio data sample respectively, obtain every
The corresponding audio frequency characteristics sample of a audio data sample;
Model training module 507, for passing through the corresponding audio frequency characteristics sample of the audio data sample and the sound
The corresponding SOT state of termination marker samples of frequency data sample are trained the default training pattern to obtain the state recognition mould
Type.
In the alternative embodiment of the application, the audio frequency characteristics are comprised at least one of the following: mel-frequency cepstrum
Coefficient characteristics, sonograph feature, chromatogram feature.
Referring to Fig. 7, in the alternative embodiment of the application, described device 50 further includes following module:
Data acquisition module 508 to be verified, for obtaining audio to be verified from history audio data according to predetermined period
Data;
State acquisition module 509, for obtaining the corresponding handmarking's SOT state of termination of the audio data to be verified;
Model modification module 510, for updating according to the audio data to be verified and handmarking's SOT state of termination
The state recognition model.
Referring to Fig. 8, in the alternative embodiment of the application, the state recognition module 504, comprising:
Evaluation of estimate acquisition submodule 5041 obtains institute for the audio frequency characteristics to be input to the state recognition model
State the identification and evaluation value that audio frequency characteristics correspond to different terminals status indication sample;
State acquisition submodule 5042, for being obtained from the SOT state of termination marker samples according to the identification and evaluation value
The SOT state of termination.
Using above-mentioned apparatus, the call request that calling terminal is sent to called terminal is obtained;It include called in call request
The terminal iidentification of terminal;According to terminal iidentification, obtains called terminal and be directed to the audio data that call request is sent;To audio data
It carries out feature extraction and obtains audio frequency characteristics;Audio frequency characteristics are input to preset state recognition model, recognize called terminal
The SOT state of termination;Wherein, state recognition model is by the corresponding audio frequency characteristics sample of audio data sample and audio data sample
This corresponding SOT state of termination marker samples, is trained to obtain to default training pattern.In this way, passing through the audio from called terminal
Audio frequency characteristics are extracted in data, and the SOT state of termination of called terminal is determined using the audio frequency characteristics, it is in the prior art without executing
Audio data is converted to the process of text data, thus solve the problems, such as that recognition accuracy in the prior art is lower, and
Improve recognition efficiency.
The embodiment of the present application also provides a kind of non-volatile readable storage medium, be stored in the storage medium one or
Multiple modules (programs) when the one or more module is used in terminal device, can make the terminal device execute
The instruction (instructions) of various method steps in the embodiment of the present application.
Fig. 9 is the hardware structural diagram of the identification device for the SOT state of termination that one embodiment of the application provides.Such as Fig. 9 institute
Show, the identification device of the SOT state of termination may include input equipment 90, processor 91, output equipment 92, memory 93 and at least
One communication bus 94.Communication bus 94 is for realizing the communication connection between element.Memory 93 may be deposited comprising high-speed RAM
Reservoir, it is also possible to further include non-volatile memories NVM, a for example, at least magnetic disk storage can store in memory 93 each
Kind program, for completing various processing functions and realizing the method and step of the present embodiment.
Optionally, above-mentioned processor 91 can be for example central processing unit (Central Processing Unit, abbreviation
CPU), application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable
Logical device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are real
Existing, which is coupled to above-mentioned input equipment 90 and output equipment 92 by wired or wireless connection.
Optionally, above-mentioned input equipment 90 may include a variety of input equipments, such as may include user oriented user
At least one of interface, device oriented equipment interface, the programmable interface of software, camera, sensor.Optionally, the face
It can be wireline interface for carrying out data transmission between equipment and equipment to the equipment interface of equipment, can also be for setting
Standby hardware insertion interface (such as USB interface, serial ports etc.) carried out data transmission between equipment;Optionally, the user oriented
User interface for example can be user oriented control button, for receive voice input voice-input device and user
Receive the touch awareness apparatus (such as touch screen, Trackpad with touch sensing function etc.) of user's touch input;Optionally,
The programmable interface of above-mentioned software for example can be the entrance for editing or modifying program for user, such as the input pin of chip
Interface or input interface etc.;Optionally, above-mentioned transceiver can be rf chip with communication function, at base band
Manage chip and dual-mode antenna etc..The audio input device such as microphone can receive voice data.Output equipment 92 may include
The output equipments such as display, sound equipment.
In the present embodiment, the processor of the identification device of the SOT state of termination includes filling for executing the identification of the SOT state of termination
The function of each module in setting, concrete function and technical effect are referring to above-described embodiment, and details are not described herein again.
Figure 10 is the hardware structural diagram of the identification device for the SOT state of termination that another embodiment of the application provides.Figure 10 is
To a specific embodiment of Fig. 9 during realization.As shown in Figure 10, the identification device packet of the SOT state of termination of the present embodiment
Include processor 101 and memory 102.
Processor 101 executes the computer program code that memory 102 is stored, and realizes Fig. 1 to Fig. 4 in above-described embodiment
The SOT state of termination recognition methods.
Memory 102 is configured as storing various types of data to support the operation in the recognition methods of the SOT state of termination.
The example of these data includes the instruction of any application or method for operating on the identification device of the SOT state of termination, example
Such as message, picture, video etc..Memory 102 may include random access memory (random access memory, abbreviation
RAM), it is also possible to further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Optionally, processor 101 is arranged in processing component 100.The identification device of the SOT state of termination can also include: logical
Believe component 103, power supply module 104, multimedia component 105, audio component 106, input/output interface 107 and/or sensor group
Part 108.Component that the identification device of the SOT state of termination is specifically included etc. is set according to actual demand, and the present embodiment does not limit this
It is fixed.
The integrated operation of the identification device of the usual controlling terminal state of processing component 100.Processing component 100 may include one
A or multiple processors 101 execute instruction, to complete all or part of the steps of above-mentioned Fig. 1 to Fig. 4 method.In addition, processing
Component 100 may include one or more modules, convenient for the interaction between processing component 100 and other assemblies.For example, processing group
Part 100 may include multi-media module, to facilitate the interaction between multimedia component 105 and processing component 100.
Power supply module 104 provides electric power for the various assemblies of the identification device of the SOT state of termination.Power supply module 104 may include
Power-supply management system, one or more power supplys and other with the identification device for the SOT state of termination generate, manage, and distribute electric power phase
Associated component.
Multimedia component 105 includes the aobvious of one output interface of offer between the identification device and user of the SOT state of termination
Display screen.In some embodiments, display screen may include liquid crystal display (LCD) and touch panel (TP).If display screen packet
Touch panel is included, display screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one
Or multiple touch sensors are to sense the gesture on touch, slide, and touch panel.The touch sensor can be sensed not only
The boundary of a touch or slide action, but also detect duration and pressure associated with the touch or slide operation.
Audio component 106 is configured as output and/or input audio signal.For example, audio component 106 includes a Mike
Wind (MIC).The received audio signal can be further stored in memory 102 or send via communication component 103.One
In a little embodiments, audio component 106 further includes a loudspeaker, is used for output audio signal.
Input/output interface 107 provides interface, above-mentioned peripheral interface between processing component 100 and peripheral interface module
Module can be click wheel, button etc..These buttons may include, but are not limited to: volume button, start button and locking press button.
Sensor module 108 includes one or more sensors, provides each side for the identification device for the SOT state of termination
The status assessment in face.For example, sensor module 108 can detecte the state that opens/closes of the identification device of the SOT state of termination, group
The relative positioning of part, the existence or non-existence that user contacts with the identification device of the SOT state of termination.Sensor module 108 may include
Proximity sensor is configured to detect the presence of nearby objects without any physical contact.In some embodiments,
The sensor module 108 can also be including camera etc..
Communication component 103 is configured to facilitate wired or wireless way between the identification device of the SOT state of termination and other equipment
Communication.The identification device of the SOT state of termination can access the wireless network based on communication standard, such as WiFi, 2G or 3G or they
Combination.
From the foregoing, it will be observed that communication component 103, audio component 106 involved in Figure 10 embodiment and input/output connect
Mouth 107, sensor module 108 can be used as the implementation of the input equipment in Fig. 9 embodiment.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiments of the present application may be provided as method, apparatus or calculating
Machine program product.Therefore, the embodiment of the present application can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present application can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present application is referring to according to the method for the embodiment of the present application, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these
Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices
Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices
In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart
And/or in one or more blocks of the block diagram specify function the step of.
Although preferred embodiments of the embodiments of the present application have been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and all change and modification within the scope of the embodiments of the present application.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
Above the identification device of the recognition methods to a kind of SOT state of termination provided herein and a kind of SOT state of termination and
Storage medium is described in detail, and specific case used herein explains the principle and embodiment of the application
It states, the description of the example is only used to help understand the method for the present application and its core ideas;Meanwhile for this field
Those skilled in the art, according to the thought of the application, there will be changes in the specific implementation manner and application range, to sum up institute
It states, the contents of this specification should not be construed as limiting the present application.
Claims (12)
1. a kind of recognition methods of the SOT state of termination, which is characterized in that the described method includes:
Obtain the call request that calling terminal is sent to called terminal;It include the terminal of the called terminal in the call request
Mark;
According to the terminal iidentification, obtains the called terminal and be directed to the audio data that the call request is sent;
Feature extraction is carried out to the audio data and obtains audio frequency characteristics;
The audio frequency characteristics are input to preset state recognition model, recognize the SOT state of termination of the called terminal;Wherein,
The state recognition model is corresponding by the corresponding audio frequency characteristics sample of audio data sample and the audio data sample
SOT state of termination marker samples, default training pattern is trained to obtain.
2. the method according to claim 1, wherein the audio frequency characteristics are input to preset state described
Identification model, before the SOT state of termination for recognizing the called terminal, further includes:
Obtain the audio data sample and the corresponding SOT state of termination marker samples of the audio data sample;
Feature extraction is carried out to each audio data sample respectively, obtains the corresponding audio of each audio data sample
Feature samples;
Pass through the corresponding audio frequency characteristics sample of the audio data sample and the corresponding SOT state of termination of the audio data sample
Marker samples are trained the default training pattern to obtain the state recognition model.
3. the method according to claim 1, wherein the audio frequency characteristics comprise at least one of the following: Meier frequency
Rate cepstrum coefficient feature, sonograph feature, chromatogram feature.
4. the method according to claim 1, wherein the audio frequency characteristics are input to preset state described
Identification model, after the SOT state of termination for recognizing the called terminal, further includes:
Audio data to be verified is obtained from history audio data according to predetermined period;
Obtain the corresponding handmarking's SOT state of termination of the audio data to be verified;
According to the audio data to be verified and handmarking's SOT state of termination, the state recognition model is updated.
5. the method according to claim 1, wherein described be input to preset state knowledge for the audio frequency characteristics
Other model, recognizes the SOT state of termination of the called terminal, comprising:
The audio frequency characteristics are input to the state recognition model, the audio frequency characteristics is obtained and corresponds to different terminals status indication
The identification and evaluation value of sample;
The SOT state of termination is obtained from the SOT state of termination marker samples according to the identification and evaluation value.
6. a kind of identification device of the SOT state of termination, which is characterized in that described device includes:
Request module, the call request sent for obtaining calling terminal to called terminal;Include in the call request
The terminal iidentification of the called terminal;
Audio data obtains module, for obtaining the called terminal and sending out for the call request according to the terminal iidentification
The audio data sent;
Characteristic extracting module obtains audio frequency characteristics for carrying out feature extraction to the audio data;
State recognition module recognizes the called end for the audio frequency characteristics to be input to preset state recognition model
The SOT state of termination at end;Wherein, the state recognition model is by the corresponding audio frequency characteristics sample of audio data sample and institute
The corresponding SOT state of termination marker samples of audio data sample are stated, default training pattern is trained to obtain.
7. device according to claim 6, which is characterized in that further include:
Data sample obtains module, for obtaining the audio data sample and the corresponding terminal of the audio data sample
Status indication sample;
Feature samples obtain module, for carrying out feature extraction to each audio data sample respectively, obtain each described
The corresponding audio frequency characteristics sample of audio data sample;
Model training module, for passing through the corresponding audio frequency characteristics sample of the audio data sample and the audio data sample
This corresponding SOT state of termination marker samples, is trained the default training pattern to obtain the state recognition model.
8. device according to claim 6, which is characterized in that the audio frequency characteristics comprise at least one of the following: Meier frequency
Rate cepstrum coefficient feature, sonograph feature, chromatogram feature.
9. device according to claim 6, which is characterized in that further include:
Data acquisition module to be verified, for obtaining audio data to be verified from history audio data according to predetermined period;
State acquisition module, for obtaining the corresponding handmarking's SOT state of termination of the audio data to be verified;
Model modification module, for updating the shape according to the audio data to be verified and handmarking's SOT state of termination
State identification model.
10. device according to claim 6, which is characterized in that the state recognition module, comprising:
It is special to obtain the audio for the audio frequency characteristics to be input to the state recognition model for evaluation of estimate acquisition submodule
Levy the identification and evaluation value of corresponding different terminals status indication sample;
State acquisition submodule, for obtaining the terminal from the SOT state of termination marker samples according to the identification and evaluation value
State.
11. a kind of identification device of the SOT state of termination, which is characterized in that described device includes processor and memory, wherein
The processor executes the computer program code that the memory is stored, to realize any one of claim 1 to 5 institute
The step of recognition methods for the SOT state of termination stated.
12. a kind of computer readable storage medium, which is characterized in that store computer journey on the computer readable storage medium
Sequence, the computer program realize the recognition methods of the SOT state of termination described in any one of claim 1 to 5 when being executed by processor
The step of.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910453671.6A CN110290280B (en) | 2019-05-28 | 2019-05-28 | Terminal state identification method and device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910453671.6A CN110290280B (en) | 2019-05-28 | 2019-05-28 | Terminal state identification method and device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110290280A true CN110290280A (en) | 2019-09-27 |
CN110290280B CN110290280B (en) | 2021-08-13 |
Family
ID=68002859
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910453671.6A Active CN110290280B (en) | 2019-05-28 | 2019-05-28 | Terminal state identification method and device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110290280B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110933235A (en) * | 2019-11-06 | 2020-03-27 | 杭州哲信信息技术有限公司 | Noise removing method in intelligent calling system based on machine learning |
CN111212193A (en) * | 2020-01-14 | 2020-05-29 | 中电智恒信息科技服务有限公司 | Method for identifying user on-hook state based on user color ring information |
CN111508527A (en) * | 2020-04-17 | 2020-08-07 | 北京帝派智能科技有限公司 | Telephone answering state detection method, device and server |
CN112735479A (en) * | 2021-03-31 | 2021-04-30 | 南方电网数字电网研究院有限公司 | Speech emotion recognition method and device, computer equipment and storage medium |
CN113889077A (en) * | 2021-09-22 | 2022-01-04 | 武汉普惠海洋光电技术有限公司 | Voice recognition method, voice recognition device, electronic equipment and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102404462A (en) * | 2010-09-08 | 2012-04-04 | 北京商路通信息技术有限公司 | Call progress analyzing method for phone dialing system and device |
US20140211669A1 (en) * | 2013-01-28 | 2014-07-31 | Pantech Co., Ltd. | Terminal to communicate data using voice command, and method and system thereof |
CN105895087A (en) * | 2016-03-24 | 2016-08-24 | 海信集团有限公司 | Voice recognition method and apparatus |
US20170068805A1 (en) * | 2015-09-08 | 2017-03-09 | Yahoo!, Inc. | Audio verification |
CN107330459A (en) * | 2017-06-28 | 2017-11-07 | 联想(北京)有限公司 | A kind of data processing method, device and electronic equipment |
CN108986789A (en) * | 2018-09-12 | 2018-12-11 | 携程旅游信息技术(上海)有限公司 | Audio recognition method, device, storage medium and electronic equipment |
CN109448719A (en) * | 2018-12-11 | 2019-03-08 | 网易(杭州)网络有限公司 | Establishment of Neural Model method and voice awakening method, device, medium and equipment |
CN109545213A (en) * | 2018-12-24 | 2019-03-29 | 珠海格力电器股份有限公司 | Apparatus control method, device, storage medium and air-conditioning |
CN109637537A (en) * | 2018-12-28 | 2019-04-16 | 北京声智科技有限公司 | A kind of method that automatic acquisition labeled data optimizes customized wake-up model |
CN109643549A (en) * | 2016-08-31 | 2019-04-16 | 三星电子株式会社 | Audio recognition method and device based on speaker identification |
CN109658939A (en) * | 2019-01-26 | 2019-04-19 | 北京灵伴即时智能科技有限公司 | A kind of telephonograph access failure reason recognition methods |
-
2019
- 2019-05-28 CN CN201910453671.6A patent/CN110290280B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102404462A (en) * | 2010-09-08 | 2012-04-04 | 北京商路通信息技术有限公司 | Call progress analyzing method for phone dialing system and device |
US20140211669A1 (en) * | 2013-01-28 | 2014-07-31 | Pantech Co., Ltd. | Terminal to communicate data using voice command, and method and system thereof |
US20170068805A1 (en) * | 2015-09-08 | 2017-03-09 | Yahoo!, Inc. | Audio verification |
CN105895087A (en) * | 2016-03-24 | 2016-08-24 | 海信集团有限公司 | Voice recognition method and apparatus |
CN109643549A (en) * | 2016-08-31 | 2019-04-16 | 三星电子株式会社 | Audio recognition method and device based on speaker identification |
CN107330459A (en) * | 2017-06-28 | 2017-11-07 | 联想(北京)有限公司 | A kind of data processing method, device and electronic equipment |
CN108986789A (en) * | 2018-09-12 | 2018-12-11 | 携程旅游信息技术(上海)有限公司 | Audio recognition method, device, storage medium and electronic equipment |
CN109448719A (en) * | 2018-12-11 | 2019-03-08 | 网易(杭州)网络有限公司 | Establishment of Neural Model method and voice awakening method, device, medium and equipment |
CN109545213A (en) * | 2018-12-24 | 2019-03-29 | 珠海格力电器股份有限公司 | Apparatus control method, device, storage medium and air-conditioning |
CN109637537A (en) * | 2018-12-28 | 2019-04-16 | 北京声智科技有限公司 | A kind of method that automatic acquisition labeled data optimizes customized wake-up model |
CN109658939A (en) * | 2019-01-26 | 2019-04-19 | 北京灵伴即时智能科技有限公司 | A kind of telephonograph access failure reason recognition methods |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110933235A (en) * | 2019-11-06 | 2020-03-27 | 杭州哲信信息技术有限公司 | Noise removing method in intelligent calling system based on machine learning |
CN110933235B (en) * | 2019-11-06 | 2021-07-27 | 杭州哲信信息技术有限公司 | Noise identification method in intelligent calling system based on machine learning |
CN111212193A (en) * | 2020-01-14 | 2020-05-29 | 中电智恒信息科技服务有限公司 | Method for identifying user on-hook state based on user color ring information |
CN111508527A (en) * | 2020-04-17 | 2020-08-07 | 北京帝派智能科技有限公司 | Telephone answering state detection method, device and server |
CN112735479A (en) * | 2021-03-31 | 2021-04-30 | 南方电网数字电网研究院有限公司 | Speech emotion recognition method and device, computer equipment and storage medium |
CN112735479B (en) * | 2021-03-31 | 2021-07-06 | 南方电网数字电网研究院有限公司 | Speech emotion recognition method and device, computer equipment and storage medium |
CN113889077A (en) * | 2021-09-22 | 2022-01-04 | 武汉普惠海洋光电技术有限公司 | Voice recognition method, voice recognition device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110290280B (en) | 2021-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110290280A (en) | A kind of recognition methods of the SOT state of termination, device and storage medium | |
CN111261144B (en) | Voice recognition method, device, terminal and storage medium | |
JP2019117623A (en) | Voice dialogue method, apparatus, device and storage medium | |
CN108877770A (en) | For testing the methods, devices and systems of intelligent sound equipment | |
CN107610695A (en) | Driver's voice wakes up the dynamic adjusting method of instruction word weight | |
CN104133851A (en) | Audio similarity detecting method, audio similarity detecting device and electronic equipment | |
CN105261366A (en) | Voice identification method, voice engine and terminal | |
CN106572272A (en) | IVR voice menu determination method and apparatus | |
CN108038231A (en) | log processing method, device, terminal device and storage medium | |
CN110299136A (en) | A kind of processing method and its system for speech recognition | |
CN106326211B (en) | Determination of distance method and apparatus between the keyword of alternate statement | |
CN104158885B (en) | A kind of method and system based on the loading application of positional information streaming | |
CN104361896B (en) | Voice quality assessment equipment, method and system | |
CN108168569A (en) | Air navigation aid, device, storage medium, mobile terminal and onboard system | |
CN109243426A (en) | A kind of automatization judgement voice false wake-up system and its judgment method | |
CN105242552B (en) | Bootstrap technique and device are installed | |
CN110277092A (en) | A kind of voice broadcast method, device, electronic equipment and readable storage medium storing program for executing | |
CN109961787A (en) | Determine the method and device of acquisition end time | |
CN104078045A (en) | Identifying method and electronic device | |
CN104317392A (en) | Information control method and electronic equipment | |
CN106357913A (en) | Method and device for prompting information | |
CN109558297A (en) | EMS memory management process and device | |
CN104063424B (en) | Web page picture shows method and demonstration device | |
CN109451506B (en) | LTE capacity expansion evaluation method and device, terminal and computer storage medium | |
CN110335626A (en) | Age recognition methods and device, storage medium based on audio |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |