CN109637540A - Bluetooth evaluating method, device, equipment and the medium of intelligent sound equipment - Google Patents
Bluetooth evaluating method, device, equipment and the medium of intelligent sound equipment Download PDFInfo
- Publication number
- CN109637540A CN109637540A CN201910153246.5A CN201910153246A CN109637540A CN 109637540 A CN109637540 A CN 109637540A CN 201910153246 A CN201910153246 A CN 201910153246A CN 109637540 A CN109637540 A CN 109637540A
- Authority
- CN
- China
- Prior art keywords
- frame losing
- frame
- precision
- testing sample
- tone testing
- 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 36
- 238000012360 testing method Methods 0.000 claims abstract description 177
- 238000005194 fractionation Methods 0.000 claims description 15
- 230000001965 increasing effect Effects 0.000 claims description 5
- 241001062009 Indigofera Species 0.000 claims description 2
- 238000004590 computer program Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 8
- 230000007423 decrease Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000005291 magnetic effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000013102 re-test Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- H04B5/72—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/20—Arrangements for detecting or preventing errors in the information received using signal quality detector
- H04L1/201—Frame classification, e.g. bad, good or erased
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The embodiment of the invention discloses bluetooth evaluating method, device, equipment and the media of a kind of intelligent sound equipment.This method comprises: statistics terminal is being received by bluetooth under initial Bluetooth connection distance, tone testing Sample Maximal frame losing number and maximum continuous frame losing number from intelligent sound equipment;Each tone testing sample is controlled by different frame losing number frame losings according to maximum frame losing number and maximum continuous frame losing number, counts frame losing precision of identifying speech;If frame losing precision of identifying speech does not meet expection, aforesaid operations are repeated under bluetooth connection after the adjustment distance, until frame losing precision of identifying speech meets expection, and regard final bluetooth connection distance as bluetooth maximum effective distance.Final bluetooth effective distance is obtained through the above scheme, to effectively test and assess to Bluetooth function, to guarantee that intelligent sound equipment realizes accurate speech recognition under effective distance.
Description
Technical field
The present embodiments relate to Internet technical field more particularly to a kind of bluetooth evaluation and test sides of intelligent sound equipment
Method, device, equipment and medium.
Background technique
Intelligent sound equipment usually passes through the terminal devices such as bluetooth and mobile phone or computer and connect, and can be received by bluetooth
The audio-frequency information played in terminal device plays out.In addition, intelligent sound equipment can also receive the voice signal of user
And identified, make corresponding operation automatically according to recognition result.
In the scene of speech recognition, the considerations of in terms of the product designs such as the cost of intelligent sound equipment, usually
Intelligent sound equipment sends it to by bluetooth the mobile phone being attached thereto after receiving voice signal, and mobile phone is uploaded to clothes again
Business device carries out speech recognition, then makes corresponding operation, example according to the recognition result that server issues by intelligent sound equipment
Such as play next song, F.F. or closing.Therefore, the quality that data are transmitted under bluetooth connection mode directly affects voice knowledge
Other accuracy rate.
Summary of the invention
The embodiment of the present invention provides bluetooth evaluating method, device, equipment and the medium of a kind of intelligent sound equipment, with evaluation and test
Influence of the bluetooth data transmission quality to speech recognition, to obtain in the case where voice normally identifies, the maximum of bluetooth is passed
Defeated distance.
In a first aspect, the embodiment of the invention provides a kind of bluetooth evaluating methods of intelligent sound equipment, this method comprises:
Under initial Bluetooth connection distance, counts the terminal and the voice from intelligent sound equipment is being received by bluetooth
During test sample collection, the maximum frame losing number of the tone testing sample received and maximum continuous frame losing number;
For each tone testing sample in the tone testing sample set, continuously lost according to maximum frame losing number and maximum
Frame number controls tone testing sample and presses different frame losing number frame losings, and statistical server losing to the tone testing sample after frame losing
Frame precision of identifying speech;
If the frame losing precision of identifying speech does not meet expection, repeated under bluetooth connection distance after the adjustment
Aforesaid operations until the frame losing precision of identifying speech meets expection, and regard final bluetooth connection distance as intelligent sound
The bluetooth maximum effective distance of equipment.
Second aspect, the embodiment of the invention provides a kind of bluetooth evaluating apparatus of intelligent sound equipment, which includes:
Frame losing number statistical module, for initial Bluetooth connection distance under, count the terminal by bluetooth reception come
During the tone testing sample set of intelligent sound equipment, the maximum frame losing number and maximum of the tone testing sample received
Continuous frame losing number;
Precision of identifying speech statistical module, each tone testing sample for being directed in the tone testing sample set,
Different frame losing number frame losings, and statistical server are pressed according to maximum frame losing number and maximum continuous frame losing number control tone testing sample
To the frame losing precision of identifying speech of the tone testing sample after frame losing;
Maximum effective distance determining module is adjusting if not meeting expection for the frame losing precision of identifying speech
Aforesaid operations are repeated under bluetooth connection distance afterwards, until the frame losing precision of identifying speech meets expection, and will be final
Bluetooth maximum effective distance of the bluetooth connection distance as intelligent sound equipment.
The third aspect, the embodiment of the invention also provides a kind of electronic equipment, which includes:
One or more processors;
Memory, for storing one or more programs, when one or more of programs are by one or more of places
It manages device to execute, so that one or more of processors realize the bluetooth of any intelligent sound equipment in the embodiment of the present invention
Evaluating method.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the bluetooth evaluation and test side of any intelligent sound equipment in the embodiment of the present invention when program is executed by processor
Method.
The embodiment of the present invention is under initial Bluetooth connection distance, by according to maximum frame losing number and maximum continuous frame losing numerical control
Tone testing sample processed is according to different frame losing number frame losings, thus speech recognition essence of the real-time statistics under different frame loss conditions
Degree, further according to the comparison of precision of identifying speech and expected situation, adjustment initial Bluetooth connects distance, until speech recognition essence
Degree meets expection, to obtain bluetooth maximum effective distance, in the case where considering precision of identifying speech, evaluation and test obtains bluetooth
Maximum effective distance guarantees speech recognition to guarantee that intelligent sound equipment can use in the range of bluetooth effective distance
Quality.
Detailed description of the invention
Fig. 1 is the flow chart of the bluetooth evaluating method of one of embodiment of the present invention one intelligent sound equipment;
Fig. 2 is terminal and intelligent sound equipment interaction schematic diagram in the embodiment of the present invention one;
Fig. 3 is the flow chart of the bluetooth evaluating method of one of embodiment of the present invention two intelligent sound equipment;
Fig. 4 is the structural schematic diagram of the bluetooth evaluating apparatus of one of embodiment of the present invention three intelligent sound equipment;
Fig. 5 is the structural schematic diagram of one of the embodiment of the present invention four electronic equipment.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart of the bluetooth evaluating method of one of embodiment of the present invention one intelligent sound equipment.This implementation
The bluetooth evaluating method for the intelligent sound equipment that example provides is applicable to test under the premise of meeting precision of identifying speech requirement
The case where bluetooth maximum effective distance, this method can specifically be executed by the bluetooth evaluating apparatus of intelligent sound equipment, the dress
Setting can be realized by the mode of software and/or hardware, which can integrate in the electronic device, and the electronic equipment can be
The equipment that computer equipment etc. is evaluated and tested for realizing bluetooth.Referring to Fig. 1, the bluetooth evaluating method of the present embodiment is specifically included:
S110, it is connected under in initial Bluetooth, counts the terminal and receive by bluetooth from intelligent sound equipment
Tone testing sample set during, the maximum frame losing number of the tone testing sample received and maximum continuous frame losing number.
Wherein, terminal can carry out the intelligence of Bluetooth communication for smart phone, tablet computer, intelligent wearable device etc.
Terminal.Intelligent sound equipment can receive voice signal, and be connect by bluetooth with terminal, and the voice signal received is passed through
Bluetooth approach is sent to terminal.Specifically, Fig. 2 is terminal and the interaction signal of intelligent sound equipment in the embodiment of the present invention one
Figure.As shown in Fig. 2, intelligent sound equipment and terminal are communicatively coupled by bluetooth, intelligent sound equipment and terminal it is opposite
Distance as bluetooth connection distance, which will affect the quality of Bluetooth transmission signal, to influence speech recognition
Precision.
In embodiments of the present invention, the electronic equipment for being used to test is connect with the terminal, so as to count
The frame loss condition of the voice signal for the tone testing sample that terminal receives, further, the electronic equipment can also and voice
It identifies that server is wirelessly connected, and the voice signal received is sent to server and carries out speech recognition.Further, it is also possible to according to
The tone testing sample is controlled according to the frame loss condition and carries out frame losing in different location, and the voice signal after frame losing is sent
Speech recognition is carried out again to server, to compare whether the precision of identifying speech after frame losing meets expection.According to different
Comparison result can readjust bluetooth connection distance, and bluetooth connection after the adjustment further executes above-mentioned survey apart from lower
Examination operation, until precision of identifying speech, which meets, is expected, to obtain the maximum effective distance of bluetooth connection.
Specifically, the bluetooth connection distance that setting is initial, can be set, generally as the case may be by technical staff
Either one or two of in the case of, communication distance range between person-to-person communication product is 0-10m, therefore can choose in the range intervals
Distance value connects distance as initial Bluetooth.Under initial Bluetooth connection distance, intelligent sound equipment passes through Blue-tooth communication method
Tone testing sample set is sent to terminal, terminal receives the tone testing sample set, and electronic equipment statistics is surveyed in above-mentioned voice
Try the maximum frame losing number and maximum continuous frame losing number of the tone testing sample in sample set transmission process.Illustratively, voice is surveyed
This concentration of sample includes 50 tone testing samples, 50 tone testing samples can be sent 100 times, in each transmission process
Frame losing array gather at one, maximum frame losing number is that the maximum during tone testing sample delivery is lost in entire set
Frame number.Similar, the continuous frame losing quantity during sending every time can be counted, using maximum frame losing quantity as language
The continuous frame losing quantity of maximum in sound test sample transmission process.
Optionally, it can be closed to obtain the corresponding missed frame probabilities of each frame losing quantity according to frame losing manifold, i.e. the frame losing quantity exists
The number and tone testing sample set that occur in set send the ratio of total degree, illustratively, by 50 tone testing samples
It sends 100 times, wherein the case where occurring 5 times and lose 2 frame, then it is 5/100 that frame losing quantity, which is 2 corresponding missed frame probabilities,.At this point,
The corresponding missed frame probabilities of each frame losing quantity are counted, and allow by each missed frame probabilities and for the speech recognition modeling pre-established
Missed frame probabilities are compared, and in the case where missed frame probabilities are not more than the missed frame probabilities of the permission, count maximum frame losing number and most
Big continuous frame losing number.
S120, for each tone testing sample in the tone testing sample set, according to maximum frame losing number and maximum
Continuous frame losing number control tone testing sample presses different frame losing number frame losings, and statistical server is to the tone testing sample after frame losing
This frame losing precision of identifying speech.
Specifically, according to maximum frame losing number and maximum continuous frame losing number, control voice is surveyed for each tone testing sample
Sample sheet presses different frame losing number frame losings, since identification situation of the server to the tone testing sample after frame losing can become
Change, therefore, by counting under different frame losing modes and frame losing quantity, server is lost to the tone testing sample after frame losing
Frame precision of identifying speech, can evaluate and test out the influence to speech recognition effect in the case where current Bluetooth connects distance condition, and if
After increasing current Bluetooth connection distance, corresponding frame losing precision of identifying speech can no longer meet demand, then current Bluetooth connects
Distance can be used as bluetooth maximum effective distance.Illustratively, the tone testing sample after frame losing can be input to server
Speech recognition modeling, as frame losing precision of identifying speech, the output of model can be sent to electricity by server for the output of model
Sub- equipment is counted.
Optionally, for each tone testing sample in the tone testing sample set, according to maximum frame losing number and most
Big continuous frame losing number control tone testing sample presses different frame losing number frame losings, and statistical server is to the tone testing after frame losing
The frame losing precision of identifying speech of sample, specifically includes:
For each tone testing sample in the tone testing sample set, continuously lost according to maximum frame losing number and maximum
Frame number determines that tone testing sample in the continuous frame losing number and discontinuous frame losing number of different location, and controls tone testing sample point
The continuous frame losing number and discontinuous frame losing number frame losing are not pressed in the different location;
Statistical server is in the precision of identifying speech of the tone testing sample after continuous frame losing and discontinuous frame losing respectively
The smallest precision of identifying speech of accuracy value, as the frame losing precision of identifying speech.
It is accurately evaluated and tested comprehensively to realize, the testing service device under different frame losing situations is needed to believe the voice after frame losing
Number precision of identifying speech, and during Bluetooth transmission, it will usually the situation including continuous frame losing and discontinuous frame losing, because
This, needs to control the frame losing of tone testing sample for different situations, then realizes and accurately evaluates and tests comprehensively.
Illustratively, control tone testing sample carries out continuous frame losing, i.e., in multiple and different positions of tone testing sample
Place, controls it and continuously loses a certain number of frame numbers.In embodiments of the present invention, the maximum frame losing number counted in advance can be made
For maximum continuous frame losing number, frame losing is carried out at different locations according to the continuous frame losing number control tone testing sample of the maximum.Control
Tone testing sample processed carries out discontinuous frame losing, that is, after determining different frame losing position and frame losing quantity, controls in different positions
It sets and loses a certain number of frame numbers respectively, but total frame losing number is no more than the maximum frame losing number counted in advance, and in each position
The continuous frame losing number at place is no more than the continuous frame losing number of maximum that statistics in advance obtains.For example, maximum frame losing number is 10, it is maximum continuous
Frame losing number is 4, then discontinuous frame losing can lose continuous 3 frame, continuous respectively for three different locations in tone testing sample
2 frames and 1 frame, meet total frame losing number without departing from the maximum frame losing number, continuous frame losing number is without departing from the continuous frame losing of maximum
Number.
If S130, the frame losing precision of identifying speech do not meet expection, bluetooth connection after the adjustment is apart from lower heavy
Aforesaid operations are executed again, until the frame losing precision of identifying speech meets expection, and regard final bluetooth connection distance as intelligence
The bluetooth maximum effective distance of energy speech ciphering equipment.
Wherein, the expection can be the evaluating standard determined according to the minimum of precision of identifying speech, such as in the pole
Corresponding precision interval after the certain numerical value that floats up and down on the basis of small value.Specifically, if frame losing precision of identifying speech exceeds
It is expected that then illustrating that current bluetooth connection distance is remote not enough, need to increase bluetooth connection distance;If frame losing speech recognition essence
For degree lower than expection, then the precision of identifying speech after illustrating frame losing can no longer meet current demand, current bluetooth connection distance
It is too far, need to reduce bluetooth connection distance.After increaseing or decreasing bluetooth connection distance, repeat to maximum frame losing number and most
The statistical operation of big continuous frame losing number, and tone testing sample is controlled by different frame losing number frame losings, statistical server is to frame losing
The frame losing precision of identifying speech of tone testing sample afterwards, finally again compared with expected.In above-mentioned repeatable operation process, refer to
When leading frame losing precision of identifying speech and meeting expected, it is determined that go out bluetooth maximum effective distance.
For example, illustrating current bluetooth connection if frame losing precision of identifying speech is bigger than the maximum value of the precision interval
Distance is remote not enough, needs to increase bluetooth connection distance;And if frame losing precision of identifying speech is also smaller than the minimum value in the section,
It then needs to reduce bluetooth connection distance and re-starts test.And it is adjusted bluetooth connection distance, so that frame losing speech recognition essence
When spending and fallen in the section again, and can not all fall on again in the section after adjusting again in every case, then illustrate current indigo plant
Tooth connection distance be bluetooth maximum effective distance, this apart from it is interior using intelligent sound equipment can demand allow model
Enclose interior realization accurately speech recognition.
In a kind of specific embodiment, optionally, if the frame losing precision of identifying speech does not meet expection, adjust
The whole initial Bluetooth connects distance, and repeats aforesaid operations, until the frame losing precision of identifying speech meets expection, and
Bluetooth maximum effective distance by final bluetooth connection distance as intelligent sound equipment, specifically includes:
Drop-out value of the frame losing precision of identifying speech compared with the raw tone accuracy of identification under non-frame loss condition is calculated,
And the drop-out value and preset loss expectancy;
If the drop-out value is greater than the loss expectancy, according to setting step-length reduce initial Bluetooth connection away from
From, and aforesaid operations are repeated, it is corresponding before currently reducing operation when the drop-out value is less than the loss expectancy
Bluetooth maximum effective distance of the bluetooth connection distance as intelligent sound equipment;Or
If the drop-out value is less than the loss expectancy, according to setting step-length increase initial Bluetooth connection away from
From, and aforesaid operations are repeated, it is corresponding before currently increasing operation when the drop-out value is greater than the loss expectancy
Bluetooth maximum effective distance of the bluetooth connection distance as intelligent sound equipment.
Specifically, voice signal is normally identified in the case where non-frame losing, raw tone accuracy of identification at this time is most
Greatly, in the case where frame losing, frame losing precision of identifying speech can decline compared to raw tone accuracy of identification, therefore, pass through calculating
Precision of identifying speech drop-out value, and the drop-out value is compared with preset loss expectancy, thus according to comparison result, and
In test process repeatedly after adjusting bluetooth connection distance, bluetooth maximum effective distance is determined.
Wherein, the preset loss expectancy can be set as the case may be by technical staff, can be one specifically
Numerical value, namely compared with raw tone accuracy of identification, frame losing precision of identifying speech can only at most decline it is so more, then it is more then without
Method meets current demand.Therefore, if drop-out value is less than loss expectancy, illustrating frame losing precision of identifying speech, there are also the controls of decline
Part needs to increase retest again after bluetooth connection distance;If drop-out value is greater than loss expectancy, illustrate that frame losing voice is known
Other precision can no longer meet current demand, and current Bluetooth connection needs to further decrease apart from excessive.There is also the need to illustrate
, increaseing or decreasing bluetooth connection distance can gradually carry out according to preset step-length.And works as and increased or decrease a step-length
Afterwards, corresponding drop-out value is more than or less than loss expectancy, then explanation increaseds or decreases corresponding bluetooth connection distance before operation
As bluetooth maximum effective distance.
The technical solution of the present embodiment, by the maximum frame losing for counting tone testing sample under initial Bluetooth connection distance
Several and maximum continuous frame losing number, to adaptively control tone testing sample according to maximum frame losing number and maximum continuous frame losing number
Frame losing is carried out according to different frame losing numbers, and the frame losing voice of tone testing sample is known by server under statistics frame loss condition
Other precision, so that obtaining current Bluetooth in real time connects speech recognition situation under, and by frame losing precision of identifying speech with
Expected comparison adaptively adjusts bluetooth connection distance, when frame losing precision of identifying speech being instructed to meet expected, and then tests and assesses
To final bluetooth maximum effective distance, the bluetooth maximum effective distance for efficiently and accurately testing out intelligent sound equipment is realized,
On the basis of guaranteeing that voice signal effectively transmits, meet the requirement to voice signal recognition accuracy.
Embodiment two
Fig. 3 is the flow chart of the bluetooth evaluating method of one of embodiment of the present invention two intelligent sound equipment.This implementation
Example is optimized on the basis of the above embodiments, and the details not being described in detail in the present embodiment is detailed in above-described embodiment.
Referring to Fig. 3, bluetooth evaluating method provided in this embodiment includes:
S210, it is connected under in initial Bluetooth, counts the terminal and receive by bluetooth from intelligent sound equipment
Tone testing sample set during, the maximum frame losing number of the tone testing sample received and maximum continuous frame losing number.
S220, for each tone testing sample in the tone testing sample set, control is respectively from first frame to falling
Several miFrame starts, continuous frame losing mi, and statistical server obtains the precision of identifying speech of the tone testing sample after frame losing
First precision of identifying speech collection, wherein miFor the maximum frame losing number.
Specifically, carrying out continuous frame losing to each tone testing sample in tone testing sample set, surveyed first from voice
The first frame of sample sheet starts, and continuously loses miFrame obtains frame losing precision of identifying speech, then opens from the second frame of tone testing sample
Begin, continuously loses miFrame obtains frame losing precision of identifying speech, and so on, until from inverse miFrame starts, and continuously loses miFrame obtains
To frame losing precision of identifying speech, all frame losing precision of identifying speech form the first precision of identifying speech collection.
S230, by miIt is split as niBe less than niAt least one natural number, obtain e kind split combination so that being torn open at every kind
In subassembly, niWith at least one natural number and and miIt is equal, wherein niFor the maximum continuous frame losing number, and by ni
It is referred to as the fractionation element in combining at least one natural number.
Specifically, by maximum frame losing number miIt is split, is split as corresponding maximum continuous frame losing number niBe less than niExtremely
The combination of a few natural number, to carry out the test of discontinuous frame losing according to the frame losing number after fractionation.
S240, each combine eiUnder, frame losing is controlled as follows, and statistical server is to frame losing under each combination
The precision of identifying speech of tone testing sample afterwards obtains the second precision of identifying speech collection: being directed to the tone testing sample set
In each tone testing sample, e will be combinediFrame number of each fractionation element as discontinuous frame losing, according to the frame number every
Frame losing is controlled under all position groupings of a tone testing sample.
Specifically, carrying out discontinuous frame losing to each tone testing sample in tone testing sample set, torn open according to various
Fractionation element in subassembly determines the frame losing position grouping in each tone testing sample, and first according to splitting in each position
Element carries out frame losing, and optionally, the interval of the adjacent frame losing position of any two is not more than L frame, wherein L is after influencing L frame close to one
The maximum frame number of the speech recognition result of frame.
Illustratively, when maximum frame losing number is 10, maximum continuous frame losing number is 5, then one of fractionation mode can be
5 frames are continuously lost, 2 frames are continuously lost and continuously lose 3 frames.If in the case, the value of L is 10, then it is that frame losing position, which can be set,
One frame starts continuously to lose 5 frames, continuously loses 2 frames since the 4th frame, continuously loses 3 frames since the 14th frame.Certainly, mode is split
It may be 5 frames, 4 frames and 1 frame or 5 frames, 3 frames and 2 frames etc..Correspondingly, can be determined more under the premise of L is 10 frame
Frame losing scheme under kind different location combination.And since the speech recognition result of kth frame only has with the tone testing sample of preceding L frame
It closes, so if the interval of frame losing position is greater than L twice, then frame losing twice cannot generate association to speech recognition and influence, thus
It cannot achieve the effect that discontinuous frame losing evaluation and test twice, it is therefore desirable to the interval of adjacent frame losing position be set no more than L frame, L can
To be obtained according to model rule, i.e., according to the speech recognition modeling that is previously obtained count the speech recognition result of kth frame only with
Preceding L frame tone testing sample is related.
S250, the determining the smallest language of accuracy value is concentrated in the first precision of identifying speech collection and the second precision of identifying speech
Sound accuracy of identification, as the frame losing precision of identifying speech.
Specifically, the precision of identifying speech after frame losing is compared and original language due to passing through continuous frame losing and discontinuous frame losing
Sound accuracy of identification can decline, and in order to test out bluetooth maximum effective distance, then select the first precision of identifying speech collection and the second language
Sound accuracy of identification concentrates the smallest precision of identifying speech to test and assess as frame losing precision of identifying speech.
If S260, the frame losing precision of identifying speech do not meet expection, bluetooth connection after the adjustment is apart from lower heavy
Aforesaid operations are executed again, until the frame losing precision of identifying speech meets expection, and regard final bluetooth connection distance as intelligence
The bluetooth maximum effective distance of energy speech ciphering equipment.
The technical solution of the present embodiment, by the way that continuous frame losing number and discontinuous frame losing number and discontinuous frame losing is arranged
Different location, and control each tone testing sample and carry out continuous frame losing and discontinuous frame losing, obtain the voice under frame loss condition
Accuracy of identification, test process are comprehensively accurate.It is finally further adaptively adjusted compared with expected according to precision of identifying speech just
Beginning bluetooth connection distance obtains final bluetooth maximum effective distance, makes intelligent sound equipment under bluetooth maximum effective distance
Realize normal transmitting voice signal.
Embodiment three
Fig. 4 is a kind of structural schematic diagram of the bluetooth evaluating apparatus for intelligent sound equipment that the embodiment of the present invention three provides.
The device is suitable for being applicable to the case where bluetooth maximum effective distance is tested under the premise of meeting precision of identifying speech requirement,
The device can be by software and or hardware realization, and can specifically integrate in the electronic device, and the electronic equipment can be calculating
The equipment that machine equipment etc. is evaluated and tested for realizing bluetooth.Referring to fig. 4, which specifically includes:
Frame losing number statistical module 410, for counting the terminal and being received by bluetooth under initial Bluetooth connection distance
During tone testing sample set from intelligent sound equipment, the maximum frame losing number of the tone testing sample received and most
Big continuous frame losing number;
Precision of identifying speech statistical module 420, for for each tone testing sample in the tone testing sample set
This, presses different frame losing number frame losings according to maximum frame losing number and maximum continuous frame losing number control tone testing sample, and count clothes
Frame losing precision of identifying speech of the business device to the tone testing sample after frame losing;
Maximum effective distance determining module 430 is being adjusted if not meeting expection for the frame losing precision of identifying speech
Aforesaid operations are repeated under bluetooth connection distance after whole, until the frame losing precision of identifying speech meets expection, and will most
Bluetooth maximum effective distance of the whole bluetooth connection distance as intelligent sound equipment.
Optionally, the precision of identifying speech statistical module 420, specifically includes:
Frame losing unit is controlled, for for each tone testing sample in the tone testing sample set, foundation to be maximum
Frame losing number and maximum continuous frame losing number determine tone testing sample in the continuous frame losing number and discontinuous frame losing number of different location, and
It controls tone testing sample and presses the continuous frame losing number and discontinuous frame losing number frame losing in the different location respectively;
Precision of identifying speech determination unit, for distinguishing statistical server to the voice after continuous frame losing and discontinuous frame losing
The smallest precision of identifying speech of accuracy value in the precision of identifying speech of test sample, as the frame losing precision of identifying speech.
Optionally, the precision of identifying speech statistical module 420, specifically includes:
First acquisition unit, for for each tone testing sample in the tone testing sample set, control difference
From first frame to inverse miFrame starts, continuous frame losing mi, and statistical server knows the voice of the tone testing sample after frame losing
Other precision obtains the first precision of identifying speech collection, wherein miFor the maximum frame losing number;
Split cells is used for miIt is split as niBe less than niAt least one natural number, obtain e kind split combination so that
In every kind of fractionation combination, niWith at least one natural number and and miIt is equal, wherein by niWith at least one natural number
Fractionation element referred to as in combination, wherein niFor the maximum continuous frame losing number;
Second acquisition unit, in each combination eiUnder, frame losing, and statistical server pair are controlled as follows
Each precision of identifying speech for combining the tone testing sample after lower frame losing, obtains the second precision of identifying speech collection: for institute's predicate
Each tone testing sample that sound test sample is concentrated, will combine eiFrame number of each fractionation element as discontinuous frame losing, root
Frame losing is controlled under all position groupings of each tone testing sample according to the frame number;
Precision of identifying speech acquiring unit, in the first precision of identifying speech collection and the second precision of identifying speech collection
The middle the smallest precision of identifying speech of determining accuracy value, as the frame losing precision of identifying speech.
Optionally, when each tone testing sample being directed in the tone testing sample set, e will be combinediEach fractionation
Frame number of the element as discontinuous frame losing controls frame losing under all position groupings of each tone testing sample according to the frame number
When, the interval of the adjacent frame losing position of any two is not more than L frame, wherein L is the speech recognition knot after influencing L frame close to a frame
The maximum frame number of fruit.
Optionally, the maximum effective distance determining module 430, comprising:
Computing unit, for calculating the raw tone accuracy of identification under the frame losing precision of identifying speech and non-frame loss condition
The drop-out value compared, and the drop-out value and preset loss expectancy;
First distance adjustment unit reduces institute according to setting step-length if the drop-out value is greater than the loss expectancy
Initial Bluetooth connection distance is stated, and repeats aforesaid operations, it, will be current when the drop-out value is less than the loss expectancy
Bluetooth maximum effective distance of the corresponding bluetooth connection distance as intelligent sound equipment before reducing operation;
Second distance adjustment unit increases if being less than the loss expectancy for the drop-out value according to setting step-length
Add the initial Bluetooth connection distance, and repeats aforesaid operations, it, will when the drop-out value is greater than the loss expectancy
Bluetooth maximum effective distance of the corresponding bluetooth connection distance as intelligent sound equipment before current increase operation.
Above-described embodiment described image processing unit is for executing intelligent sound equipment any described in above-described embodiment
The technical effect of bluetooth assessment method, technical principle and generation is similar, and which is not described herein again.
Example IV
Fig. 5 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention four provides.Fig. 5, which is shown, to be suitable for being used in fact
The block diagram of the example electronic device 512 of the existing embodiment of the present invention.The electronic equipment 512 that Fig. 5 is shown is only an example, no
The function and use scope for coping with the embodiment of the present invention bring any restrictions.
As shown in figure 5, electronic equipment 512 includes: one or more processors 516;Memory 528, for storing one
Or multiple programs, when one or more of programs are executed by one or more of processors 516, so that one or more
A processor 516 realizes the bluetooth evaluating method of intelligent sound equipment provided by the embodiment of the present invention, comprising:
Under initial Bluetooth connection distance, counts the terminal and the voice from intelligent sound equipment is being received by bluetooth
During test sample collection, the maximum frame losing number of the tone testing sample received and maximum continuous frame losing number;
For each tone testing sample in the tone testing sample set, continuously lost according to maximum frame losing number and maximum
Frame number controls tone testing sample and presses different frame losing number frame losings, and counts frame losing of the equipment to the tone testing sample after frame losing
Precision of identifying speech;
If the frame losing precision of identifying speech does not meet expection, repeated under bluetooth connection distance after the adjustment
Aforesaid operations until the frame losing precision of identifying speech meets expection, and regard final bluetooth connection distance as intelligent sound
The bluetooth maximum effective distance of equipment.
It is showed in the form of universal computing device.The component of electronic equipment 512 can include but is not limited to: one or more
A processor or processor 516, system storage 528 connect different system components (including system storage 528 and processing
Device 516) bus 518.
Bus 518 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Electronic equipment 512 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that electronic equipment 512 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 528 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 530 and/or cache memory 532.Electronic equipment 512 may further include it is other it is removable/no
Movably, volatile/non-volatile computer system storage medium.Only as an example, storage system 536 can be used for reading and writing
Immovable, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").It, can although being not shown in Fig. 5
To provide the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk "), and it is non-volatile to moving
Property CD (such as CD-ROM, DVD-ROM or other optical mediums) read and write CD drive.In these cases, each drive
Dynamic device can be connected by one or more data media interfaces with bus 518.Memory 528 may include at least one journey
Sequence product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform this hair
The function of bright each embodiment.
Program/utility 560 with one group of (at least one) program module 562, can store in such as memory
In 528, such program module 562 includes but is not limited to operating system, one or more application program, other program modules
And program data, it may include the realization of network environment in each of these examples or certain combination.Program module 562
Usually execute the function and/or method in embodiment described in the invention.
Electronic equipment 512 can also be with one or more external equipments 516 (such as keyboard, sensing equipment, display 526
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 512 communicate, and/or with make
Any equipment (such as network interface card, the modem that the electronic equipment 512 can be communicated with one or more of the other calculating equipment
Etc.) communication.This communication can be carried out by input/output (I/O) interface 522.Also, electronic equipment 512 can also lead to
Cross network adapter 520 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, example
Such as internet) communication.As shown, network adapter 520 is communicated by bus 518 with other modules of electronic equipment 512.It answers
When understanding, although being not shown in Fig. 5, other hardware and/or software module can be used in conjunction with electronic equipment 512, including not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Processor 516 by other programs in multiple programs for being stored in system storage 528 of operation at least one,
Thereby executing the evaluation and test of the bluetooth of various function application and intelligent sound equipment, such as realize one provided by the embodiment of the present invention
The bluetooth evaluating method of kind intelligent sound equipment:
Under initial Bluetooth connection distance, counts the terminal and the voice from intelligent sound equipment is being received by bluetooth
During test sample collection, the maximum frame losing number of the tone testing sample received and maximum continuous frame losing number;
For each tone testing sample in the tone testing sample set, continuously lost according to maximum frame losing number and maximum
Frame number controls tone testing sample and presses different frame losing number frame losings, and statistical server losing to the tone testing sample after frame losing
Frame precision of identifying speech;
If the frame losing precision of identifying speech does not meet expection, repeated under bluetooth connection distance after the adjustment
Aforesaid operations until the frame losing precision of identifying speech meets expection, and regard final bluetooth connection distance as intelligent sound
The bluetooth maximum effective distance of equipment.
Embodiment five
The embodiment of the present invention five additionally provides a kind of storage medium comprising computer executable instructions, and the computer can
It executes instruction when being executed by computer processor for executing a kind of bluetooth evaluating method of intelligent sound equipment:
Under initial Bluetooth connection distance, counts the terminal and the voice from intelligent sound equipment is being received by bluetooth
During test sample collection, the maximum frame losing number of the tone testing sample received and maximum continuous frame losing number;
For each tone testing sample in the tone testing sample set, continuously lost according to maximum frame losing number and maximum
Frame number controls tone testing sample and presses different frame losing number frame losings, and statistical server losing to the tone testing sample after frame losing
Frame precision of identifying speech;
If the frame losing precision of identifying speech does not meet expection, repeated under bluetooth connection distance after the adjustment
Aforesaid operations until the frame losing precision of identifying speech meets expection, and regard final bluetooth connection distance as intelligent sound
The bluetooth maximum effective distance of equipment.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of bluetooth evaluating method of intelligent sound equipment, the intelligent sound equipment is connect by bluetooth with terminal, special
Sign is, which comprises
Under initial Bluetooth connection distance, counts the terminal and the tone testing from intelligent sound equipment is being received by bluetooth
During sample set, the maximum frame losing number of the tone testing sample received and maximum continuous frame losing number;
For each tone testing sample in the tone testing sample set, according to maximum frame losing number and maximum continuous frame losing number
It controls tone testing sample and presses different frame losing number frame losings, and statistical server is to the frame losing language of the tone testing sample after frame losing
Sound accuracy of identification;
If the frame losing precision of identifying speech does not meet expection, repeated under bluetooth connection distance after the adjustment above-mentioned
Operation until the frame losing precision of identifying speech meets expection, and regard final bluetooth connection distance as intelligent sound equipment
Bluetooth maximum effective distance.
2. the method according to claim 1, wherein being surveyed for each voice in the tone testing sample set
Sample sheet presses different frame losing number frame losings according to maximum frame losing number and maximum continuous frame losing number control tone testing sample, and unites
Server is counted to the frame losing precision of identifying speech of the tone testing sample after frame losing, is specifically included:
For each tone testing sample in the tone testing sample set, according to maximum frame losing number and maximum continuous frame losing number
Determine that tone testing sample in the continuous frame losing number and discontinuous frame losing number of different location, and controls tone testing sample and exists respectively
The different location presses the continuous frame losing number and discontinuous frame losing number frame losing;
Statistical server is to precision in the precision of identifying speech of the tone testing sample after continuous frame losing and discontinuous frame losing respectively
It is worth the smallest precision of identifying speech, as the frame losing precision of identifying speech.
3. method according to claim 1 or 2, which is characterized in that for each language in the tone testing sample set
Sound test sample presses different frame losing number frame losings according to maximum frame losing number and maximum continuous frame losing number control tone testing sample,
And statistical server specifically includes the frame losing precision of identifying speech of the tone testing sample after frame losing:
For each tone testing sample in the tone testing sample set, control respectively from first frame to inverse miFrame is opened
Begin, continuous frame losing mi, and statistical server obtains the knowledge of the first voice to the precision of identifying speech of the tone testing sample after frame losing
Other precision collection, wherein miFor the maximum frame losing number;
By miIt is split as niBe less than niAt least one natural number, obtain e kind and split combination so that in every kind of fractionations is combined,
niWith at least one natural number and and miIt is equal, wherein niFor the maximum continuous frame losing number, and by niAt least one
A natural number is referred to as the fractionation element in combining;
In each combination eiUnder, frame losing is controlled as follows, and statistical server surveys the voice after frame losing under each combination
The precision of identifying speech of sample sheet obtains the second precision of identifying speech collection: for each language in the tone testing sample set
Sound test sample will combine eiFrame number of each fractionation element as discontinuous frame losing, according to the frame number in each tone testing
Frame losing is controlled under all position groupings of sample;
It is concentrated in the first precision of identifying speech collection and the second precision of identifying speech and determines the smallest speech recognition essence of accuracy value
Degree, as the frame losing precision of identifying speech.
4. according to the method described in claim 3, it is characterized in that, when for each voice in the tone testing sample set
Test sample will combine eiFrame number of each fractionation element as discontinuous frame losing, according to the frame number in each tone testing sample
When controlling frame losing under this all position groupings, the interval of the adjacent frame losing position of any two is not more than L frame, wherein L is to influence
Close to the maximum frame number of the speech recognition result of a frame after L frame.
5. the method according to claim 1, wherein if the frame losing precision of identifying speech does not meet expection,
Aforesaid operations then are repeated under bluetooth connection distance after the adjustment, until the frame losing precision of identifying speech meets expection,
And the bluetooth maximum effective distance by final bluetooth connection distance as intelligent sound equipment, it specifically includes:
Drop-out value of the frame losing precision of identifying speech compared with the raw tone accuracy of identification under non-frame loss condition is calculated, and is compared
The drop-out value and preset loss expectancy;
If the drop-out value is greater than the loss expectancy, repeated under the bluetooth connection distance after reducing according to setting step-length
Aforesaid operations are executed, when the drop-out value is less than the loss expectancy, corresponding bluetooth connects before currently reducing operation
Connect bluetooth maximum effective distance of the distance as intelligent sound equipment;Or
If the drop-out value is less than the loss expectancy, repeated under according to the bluetooth connection distance after setting step-length increase
Aforesaid operations are executed, when the drop-out value is greater than the loss expectancy, corresponding bluetooth connects before currently increasing operation
Connect bluetooth maximum effective distance of the distance as intelligent sound equipment.
6. a kind of bluetooth evaluating apparatus of intelligent sound equipment, which is characterized in that described device includes:
Frame losing number statistical module, for counting the terminal and receiving by bluetooth from intelligence under initial Bluetooth connection distance
During the tone testing sample set of energy speech ciphering equipment, the maximum frame losing number and maximum of the tone testing sample received are continuous
Frame losing number;
Precision of identifying speech statistical module, for for each tone testing sample in the tone testing sample set, foundation
Maximum frame losing number and maximum continuous frame losing number control tone testing sample press different frame losing number frame losings, and statistical server is to losing
The frame losing precision of identifying speech of tone testing sample after frame;
Maximum effective distance determining module, if not meeting expection for the frame losing precision of identifying speech, after the adjustment
Aforesaid operations are repeated under bluetooth connection distance, until the frame losing precision of identifying speech meets expection, and by final indigo plant
Bluetooth maximum effective distance of the tooth connection distance as intelligent sound equipment.
7. device according to claim 6, which is characterized in that the precision of identifying speech statistical module specifically includes:
Frame losing unit is controlled, for for each tone testing sample in the tone testing sample set, the maximum frame losing of foundation
Several and maximum continuous frame losing number determines that tone testing sample in the continuous frame losing number and discontinuous frame losing number of different location, and controls
Tone testing sample presses the continuous frame losing number and discontinuous frame losing number frame losing in the different location respectively;
Precision of identifying speech determination unit, for distinguishing statistical server to the tone testing after continuous frame losing and discontinuous frame losing
The smallest precision of identifying speech of accuracy value in the precision of identifying speech of sample, as the frame losing precision of identifying speech.
8. device according to claim 6 or 7, which is characterized in that the precision of identifying speech statistical module, it is specific to wrap
It includes:
First acquisition unit, for for each tone testing sample in the tone testing sample set, control is respectively from the
One frame is to inverse miFrame starts, continuous frame losing mi, and statistical server is to the speech recognition essence of the tone testing sample after frame losing
Degree, obtains the first precision of identifying speech collection, wherein miFor the maximum frame losing number;
Split cells is used for miIt is split as niBe less than niAt least one natural number, obtain e kind split combination so that every
Kind is split in combination, niWith at least one natural number and and miIt is equal, wherein by niIt is referred to as at least one natural number
Fractionation element in combination, wherein niFor the maximum continuous frame losing number;
Second acquisition unit, in each combination eiUnder, frame losing is controlled as follows, and statistical server is to each group
The precision of identifying speech of tone testing sample after closing lower frame losing, obtains the second precision of identifying speech collection: surveying for the voice
Each tone testing sample of this concentration of sample, will combine eiFrame number of each fractionation element as discontinuous frame losing, according to this
Frame number controls frame losing under all position groupings of each tone testing sample;
Precision of identifying speech acquiring unit, it is true for being concentrated in the first precision of identifying speech collection and the second precision of identifying speech
The smallest precision of identifying speech of accuracy value is determined, as the frame losing precision of identifying speech.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
One or more processors;
Memory, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as a kind of bluetooth evaluating method of intelligent sound equipment as claimed in any one of claims 1 to 5.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
A kind of such as bluetooth evaluating method of intelligent sound equipment as claimed in any one of claims 1 to 5 is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910153246.5A CN109637540B (en) | 2019-02-28 | 2019-02-28 | Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910153246.5A CN109637540B (en) | 2019-02-28 | 2019-02-28 | Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109637540A true CN109637540A (en) | 2019-04-16 |
CN109637540B CN109637540B (en) | 2021-02-26 |
Family
ID=66066159
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910153246.5A Active CN109637540B (en) | 2019-02-28 | 2019-02-28 | Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109637540B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111883173A (en) * | 2020-03-20 | 2020-11-03 | 珠海市杰理科技股份有限公司 | Audio packet loss repairing method, device and system based on neural network |
CN113651199A (en) * | 2021-08-26 | 2021-11-16 | 江苏社家通信息科技有限公司 | Elevator control method for enabling mobile phone voice to pass ICCID code or IMEI |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1488134A (en) * | 2001-10-22 | 2004-04-07 | ���ṫ˾ | Device and method for voice recognition |
CN101510425A (en) * | 2008-02-15 | 2009-08-19 | 株式会社东芝 | Voice recognition apparatus and method for performing voice recognition |
WO2010100011A1 (en) * | 2009-03-04 | 2010-09-10 | Fujitsu Limited | Improvements to short-range wireless networks |
EP2649821A1 (en) * | 2010-12-06 | 2013-10-16 | Orange | Improved pairing of devices connected to a local area network |
US20160328391A1 (en) * | 2015-05-08 | 2016-11-10 | Electronics And Telecommunications Research Institute | Method and apparatus for providing automatic speech translation service in face-to-face situation |
US20180242212A1 (en) * | 2015-10-20 | 2018-08-23 | Bragi GmbH | Diversity Bluetooth System and Method |
CN109243441A (en) * | 2018-09-26 | 2019-01-18 | 广东小天才科技有限公司 | Adjust bootstrap technique, device, terminal and the storage medium of voice collecting distance |
-
2019
- 2019-02-28 CN CN201910153246.5A patent/CN109637540B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1488134A (en) * | 2001-10-22 | 2004-04-07 | ���ṫ˾ | Device and method for voice recognition |
CN101510425A (en) * | 2008-02-15 | 2009-08-19 | 株式会社东芝 | Voice recognition apparatus and method for performing voice recognition |
WO2010100011A1 (en) * | 2009-03-04 | 2010-09-10 | Fujitsu Limited | Improvements to short-range wireless networks |
EP2649821A1 (en) * | 2010-12-06 | 2013-10-16 | Orange | Improved pairing of devices connected to a local area network |
US20160328391A1 (en) * | 2015-05-08 | 2016-11-10 | Electronics And Telecommunications Research Institute | Method and apparatus for providing automatic speech translation service in face-to-face situation |
US20180242212A1 (en) * | 2015-10-20 | 2018-08-23 | Bragi GmbH | Diversity Bluetooth System and Method |
CN109243441A (en) * | 2018-09-26 | 2019-01-18 | 广东小天才科技有限公司 | Adjust bootstrap technique, device, terminal and the storage medium of voice collecting distance |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111883173A (en) * | 2020-03-20 | 2020-11-03 | 珠海市杰理科技股份有限公司 | Audio packet loss repairing method, device and system based on neural network |
WO2021184732A1 (en) * | 2020-03-20 | 2021-09-23 | 珠海市杰理科技股份有限公司 | Audio packet loss repairing method, device and system based on neural network |
CN111883173B (en) * | 2020-03-20 | 2023-09-12 | 珠海市杰理科技股份有限公司 | Audio packet loss repairing method, equipment and system based on neural network |
CN113651199A (en) * | 2021-08-26 | 2021-11-16 | 江苏社家通信息科技有限公司 | Elevator control method for enabling mobile phone voice to pass ICCID code or IMEI |
Also Published As
Publication number | Publication date |
---|---|
CN109637540B (en) | 2021-02-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10861480B2 (en) | Method and device for generating far-field speech data, computer device and computer readable storage medium | |
CN106164845B (en) | Dynamic audio frequency horizontal adjustment based on concern | |
CN109087669B (en) | Audio similarity detection method and device, storage medium and computer equipment | |
KR102444165B1 (en) | Apparatus and method for providing a meeting adaptively | |
CN1805008B (en) | Voice detection device, automatic image pickup device and voice detection method | |
CN109658352A (en) | Optimization method and device, electronic equipment and the storage medium of image information | |
CN111798852A (en) | Voice wake-up recognition performance test method, device and system and terminal equipment | |
CN110992963B (en) | Network communication method, device, computer equipment and storage medium | |
US20180190310A1 (en) | De-reverberation control method and apparatus for device equipped with microphone | |
CN108962231A (en) | A kind of method of speech classification, device, server and storage medium | |
CN111369976A (en) | Method and device for testing voice recognition equipment | |
CN107580155A (en) | Networking telephone quality determination method, device, computer equipment and storage medium | |
CN107103906A (en) | It is a kind of to wake up method, smart machine and medium that smart machine carries out speech recognition | |
US20190013020A1 (en) | Electronic device-awakening method and apparatus, device and computer-readable storage medium | |
EP4354343A1 (en) | Data processing method and device | |
CN106847305A (en) | A kind of method and device of the recording data for processing service calls | |
EP4033483B1 (en) | Method and apparatus for testing vehicle-mounted voice device, electronic device and storage medium | |
CN109637540A (en) | Bluetooth evaluating method, device, equipment and the medium of intelligent sound equipment | |
CN110310642A (en) | Method of speech processing, system, client, equipment and storage medium | |
CN113315979A (en) | Data processing method and device, electronic equipment and storage medium | |
US20190131948A1 (en) | Audio loudness control method and system based on signal analysis and deep learning | |
CN111081275B (en) | Terminal processing method and device based on sound analysis, storage medium and terminal | |
CN113591678B (en) | Classroom attention determination method, device, apparatus, storage medium, and program product | |
CN110475181A (en) | Equipment configuration method, device, equipment and storage medium | |
CN114338623A (en) | Audio processing method, device, equipment, medium and computer program product |
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 |