CN109637540B - Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment - Google Patents

Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment Download PDF

Info

Publication number
CN109637540B
CN109637540B CN201910153246.5A CN201910153246A CN109637540B CN 109637540 B CN109637540 B CN 109637540B CN 201910153246 A CN201910153246 A CN 201910153246A CN 109637540 B CN109637540 B CN 109637540B
Authority
CN
China
Prior art keywords
voice
frame loss
frame
test sample
bluetooth
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.)
Active
Application number
CN201910153246.5A
Other languages
Chinese (zh)
Other versions
CN109637540A (en
Inventor
郑林
张在东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201910153246.5A priority Critical patent/CN109637540B/en
Publication of CN109637540A publication Critical patent/CN109637540A/en
Application granted granted Critical
Publication of CN109637540B publication Critical patent/CN109637540B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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

Abstract

The embodiment of the invention discloses a Bluetooth evaluation method, a Bluetooth evaluation device, Bluetooth evaluation equipment and a Bluetooth evaluation medium for intelligent voice equipment. The method comprises the following steps: counting the maximum frame loss number and the maximum continuous frame loss number of a voice test sample received by the terminal through the Bluetooth from the intelligent voice equipment under the initial Bluetooth connection distance; controlling each voice test sample to drop frames according to different frame dropping numbers according to the maximum frame dropping number and the maximum continuous frame dropping number, and counting the frame dropping voice recognition precision; if the frame-missing speech recognition accuracy is not in accordance with the expectation, the above operation is repeatedly executed under the adjusted Bluetooth connection distance until the frame-missing speech recognition accuracy is in accordance with the expectation, and the final Bluetooth connection distance is taken as the maximum effective distance of the Bluetooth. The final effective distance of the Bluetooth is obtained through the scheme, so that the Bluetooth function is effectively evaluated, and accurate voice recognition of the intelligent voice equipment under the effective distance is guaranteed.

Description

Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment
Technical Field
The embodiment of the invention relates to the technical field of Internet, in particular to a Bluetooth evaluation method, a Bluetooth evaluation device, Bluetooth evaluation equipment and Bluetooth evaluation media for intelligent voice equipment.
Background
The smart voice device is usually connected with a terminal device such as a mobile phone or a computer through bluetooth, and can receive audio information played in the terminal device through bluetooth for playing. In addition, the intelligent voice equipment can also receive and recognize the voice signal of the user, and automatically make corresponding operation according to the recognition result.
In a speech recognition scenario, in consideration of product design aspects such as cost of the intelligent speech device, the intelligent speech device generally receives a speech signal and then sends the speech signal to a mobile phone connected with the intelligent speech device through bluetooth, the mobile phone uploads the speech signal to a server for speech recognition, and then the intelligent speech device performs corresponding operations according to a recognition result issued by the server, such as playing a next song, fast forwarding or closing. Therefore, the quality of the transmitted data in the bluetooth connection mode directly affects the accuracy of the voice recognition.
Disclosure of Invention
The embodiment of the invention provides a Bluetooth evaluation method, a Bluetooth evaluation device, Bluetooth evaluation equipment and a Bluetooth evaluation medium of intelligent voice equipment, which are used for evaluating the influence of the quality of Bluetooth transmission data on voice recognition so as to obtain the maximum transmission distance of Bluetooth under the condition of normal voice recognition.
In a first aspect, an embodiment of the present invention provides a bluetooth evaluation method for an intelligent voice device, where the method includes:
under the initial Bluetooth connection distance, counting the maximum frame loss number and the maximum continuous frame loss number of a received voice test sample in the process that the terminal receives a voice test sample set from intelligent voice equipment through Bluetooth;
controlling the voice test samples to drop frames according to different frame dropping numbers according to the maximum frame dropping number and the maximum continuous frame dropping number aiming at each voice test sample in the voice test sample set, and counting the frame dropping voice recognition precision of the voice test samples after frame dropping by the server;
if the frame-lost voice recognition precision is not in line with the expectation, the operations are repeatedly executed under the adjusted Bluetooth connection distance until the frame-lost voice recognition precision is in line with the expectation, and the final Bluetooth connection distance is used as the maximum effective distance of the Bluetooth of the intelligent voice equipment.
In a second aspect, an embodiment of the present invention provides a bluetooth evaluation apparatus for an intelligent speech device, where the apparatus includes:
the lost frame counting module is used for counting the maximum lost frame number and the maximum continuous lost frame number of the received voice test sample in the process that the terminal receives the voice test sample set from the intelligent voice equipment through the Bluetooth under the initial Bluetooth connection distance;
the voice recognition precision statistical module is used for controlling the voice test samples to drop frames according to different frame loss numbers according to the maximum frame loss number and the maximum continuous frame loss number aiming at each voice test sample in the voice test sample set, and counting the frame loss voice recognition precision of the voice test samples after frame loss by the server;
and the maximum effective distance determining module is used for repeating the operation under the adjusted Bluetooth connection distance if the frame loss voice recognition precision does not meet the expectation, until the frame loss voice recognition precision meets the expectation, and taking the final Bluetooth connection distance as the Bluetooth maximum effective distance of the intelligent voice equipment.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the bluetooth profiling method for intelligent speech devices according to any of the embodiments of the present invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a bluetooth evaluation method for any one of the intelligent speech devices in the embodiments of the present invention.
According to the embodiment of the invention, under the initial Bluetooth connection distance, the voice test sample is controlled to drop frames according to different frame loss numbers according to the maximum frame loss number and the maximum continuous frame loss number, so that the voice recognition precision under different frame loss conditions is counted in real time, the initial Bluetooth connection distance is adjusted according to the comparison between the voice recognition precision and the expected condition until the voice recognition precision is in line with the expectation, the maximum effective distance of the Bluetooth is obtained by evaluation under the condition of considering the voice recognition precision, so that the intelligent voice equipment can be used in the range of the effective distance of the Bluetooth, and the voice recognition quality is ensured.
Drawings
Fig. 1 is a flowchart of a bluetooth evaluation method for an intelligent speech device according to a first embodiment of the present invention;
fig. 2 is a schematic diagram of interaction between a terminal and an intelligent voice device in the first embodiment of the present invention;
fig. 3 is a flowchart of a bluetooth evaluation method for an intelligent speech device according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a bluetooth evaluation device of an intelligent speech device in a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device in a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a bluetooth evaluation method for an intelligent speech device according to an embodiment of the present invention. The bluetooth evaluation method for the intelligent voice device provided by this embodiment may be applicable to a situation of testing the maximum effective distance of bluetooth on the premise of meeting the requirement of voice recognition accuracy, and the method may be specifically executed by a bluetooth evaluation device for the intelligent voice device, and the device may be implemented in a software and/or hardware manner, and the device may be integrated in an electronic device, and the electronic device may be a device for implementing bluetooth evaluation, such as a computer device. Referring to fig. 1, the bluetooth evaluation method of the present embodiment specifically includes:
s110, under the initial Bluetooth connection distance, counting the maximum frame loss number and the maximum continuous frame loss number of the received voice test sample in the process that the terminal receives the voice test sample set from the intelligent voice device through Bluetooth.
Wherein, the terminal can be for intelligent terminal that can carry out bluetooth communication such as smart mobile phone, panel computer, intelligent wearing equipment. The intelligent voice equipment can receive voice signals, is connected with the terminal through the Bluetooth and sends the received voice signals to the terminal through a Bluetooth mode. Specifically, fig. 2 is a schematic diagram of interaction between a terminal and an intelligent voice device in the first embodiment of the present invention. As shown in fig. 2, the intelligent voice device and the terminal are in communication connection through bluetooth, the relative distance between the intelligent voice device and the terminal is the bluetooth connection distance, and the bluetooth connection distance can affect the quality of bluetooth transmission signals, thereby affecting the voice recognition accuracy.
In the embodiment of the invention, the electronic equipment for testing is connected with the terminal, so that the frame loss condition of the voice signal of the voice test sample received by the terminal can be counted. In addition, the voice test sample can be controlled to drop frames at different positions according to the frame dropping condition, and the voice signal after frame dropping is sent to the server to perform voice recognition again, so that whether the voice recognition precision after frame dropping is in line with expectation is compared. According to different comparison results, the Bluetooth connection distance can be readjusted, and the test operation is further executed under the adjusted Bluetooth connection distance until the voice recognition precision is in accordance with expectation, so that the maximum effective distance of the Bluetooth connection is obtained.
Specifically, the initial bluetooth connection distance is set by a technician according to specific conditions, and in general, the communication distance range between personal communication products is 0-10m, so that any distance value in the range interval can be selected as the initial bluetooth connection distance. Under the initial Bluetooth connection distance, the intelligent voice device sends a voice test sample set to the terminal in a Bluetooth communication mode, the terminal receives the voice test sample set, and the electronic device counts the maximum frame loss number and the maximum continuous frame loss number of the voice test sample in the transmission process of the voice test sample set. Illustratively, the voice test sample set includes 50 voice test samples, and the 50 voice test samples can be sent 100 times, frame loss groups in each sending process form a set, and the maximum frame loss number in all the sets is the maximum frame loss number in the transmission process of the voice test samples. Similarly, the number of continuous frame losses in each transmission process can be counted, and the maximum number of frame losses is taken as the maximum number of continuous frame losses in the transmission process of the voice test sample.
Optionally, the frame loss probability corresponding to each frame loss quantity, that is, the ratio of the number of times that the frame loss quantity appears in the set to the total number of times that the voice test sample set is transmitted, may be obtained according to the frame loss quantity set, and exemplarily, 50 voice test samples are transmitted 100 times, where, if 2 frames are lost 5 times, the frame loss probability corresponding to 2 frame loss quantity is 5/100. At this time, counting the frame loss probability corresponding to each frame loss quantity, comparing each frame loss probability with the frame loss probability allowed by the pre-established speech recognition model, and counting the maximum frame loss quantity and the maximum continuous frame loss quantity under the condition that the frame loss probability is not greater than the allowed frame loss probability.
S120, controlling the voice test samples to drop frames according to different frame loss numbers according to the maximum frame loss number and the maximum continuous frame loss number aiming at each voice test sample in the voice test sample set, and counting the frame loss voice recognition precision of the voice test samples after frame loss by the server.
Specifically, for each voice test sample, according to the maximum frame loss number and the maximum continuous frame loss number, the voice test sample is controlled to lose frames according to different frame loss numbers, because the recognition condition of the server to the voice test sample after frame loss can change, therefore, under different frame loss modes and frame loss numbers, the server can evaluate the frame loss voice recognition precision of the voice test sample after frame loss, the influence on the voice recognition effect under the condition of the current Bluetooth connection distance can be evaluated, and if the current Bluetooth connection distance is increased, the corresponding frame loss voice recognition precision can not meet the requirement, and then the current Bluetooth connection distance can be used as the maximum effective distance of Bluetooth. For example, the voice test sample after the frame loss can be input into a voice recognition model of the server, the output of the model is used as the frame loss voice recognition accuracy, and the server can send the output of the model to the electronic device for statistics.
Optionally, for each voice test sample in the voice test sample set, controlling the voice test sample to drop frames according to the maximum frame loss number and the maximum continuous frame loss number, and counting the frame loss voice recognition accuracy of the voice test sample after frame loss by the server, specifically including:
determining the continuous frame loss number and the discontinuous frame loss number of the voice test sample at different positions according to the maximum frame loss number and the maximum continuous frame loss number aiming at each voice test sample in the voice test sample set, and controlling the voice test sample to drop frames at different positions according to the continuous frame loss number and the discontinuous frame loss number respectively;
and respectively counting the speech recognition precision with the minimum precision value in the speech recognition precision of the speech test samples after continuous frame loss and discontinuous frame loss by the server, and taking the speech recognition precision as the frame loss speech recognition precision.
In order to realize comprehensive and accurate evaluation, the speech recognition accuracy of the test server on the speech signal after frame loss needs to be tested under different frame loss conditions, and in the bluetooth transmission process, the situations of continuous frame loss and discontinuous frame loss generally exist, so that the frame loss of the speech test sample needs to be controlled according to different conditions, and then the comprehensive and accurate evaluation is realized.
Illustratively, the voice test sample is controlled to continuously drop frames, that is, at a plurality of different positions of the voice test sample, the voice test sample is controlled to continuously drop a certain number of frames. In the embodiment of the invention, the maximum frame loss number counted in advance can be used as the maximum continuous frame loss number, and the voice test sample is controlled to drop frames at different positions according to the maximum continuous frame loss number. And controlling the voice test sample to perform discontinuous frame loss, namely after determining different frame loss positions and frame loss numbers, controlling to respectively lose a certain number of frame numbers at different positions, wherein the total frame loss number does not exceed the maximum frame loss number counted in advance, and the continuous frame loss number at each position does not exceed the maximum continuous frame loss number counted in advance. For example, the maximum frame loss is 10, and the maximum consecutive frame loss is 4, then the discontinuous frame loss may be achieved by respectively dropping consecutive 3 frames, consecutive 2 frames, and consecutive 1 frames at three different positions of the voice test sample, and the total frame loss does not exceed the maximum frame loss, and the consecutive frame loss does not exceed the maximum consecutive frame loss.
S130, if the frame loss voice recognition accuracy is not in line with the expectation, the operation is repeatedly executed under the adjusted Bluetooth connection distance until the frame loss voice recognition accuracy is in line with the expectation, and the final Bluetooth connection distance is used as the maximum effective Bluetooth distance of the intelligent voice equipment.
The expectation may be an evaluation criterion determined according to a minimum value of the speech recognition accuracy, for example, an accuracy interval corresponding to a certain value floating up and down on the basis of the minimum value. Specifically, if the frame loss speech recognition accuracy exceeds the expectation, it indicates that the current bluetooth connection distance is not far enough, and the bluetooth connection distance needs to be increased; if the frame loss speech recognition accuracy is lower than expected, the speech recognition accuracy after frame loss cannot meet the actual requirement, and the current Bluetooth connection distance is too far, so that the Bluetooth connection distance needs to be reduced. After increasing or decreasing the connection distance of the Bluetooth, repeatedly executing the statistical operation of the maximum frame loss number and the maximum continuous frame loss number, controlling the voice test sample to lose frames according to different frame loss numbers, and finally comparing the frame loss voice recognition precision of the voice test sample after frame loss by the statistical server with the expectation. In the repeated operation process, when the frame loss voice recognition precision is guided to meet the expectation, the maximum effective distance of the Bluetooth is determined.
For example, if the frame loss speech recognition accuracy is greater than the maximum value of the accuracy interval, it indicates that the current bluetooth connection distance is not far enough, and the bluetooth connection distance needs to be increased; and if the frame loss speech recognition precision is smaller than the minimum value of the interval, reducing the distance of the Bluetooth connection and carrying out the test again. And through adjusting the connection distance of the Bluetooth, the frame-missing voice recognition precision falls into the interval again, and when the frame-missing voice recognition precision cannot fall into the interval again after the frame-missing voice recognition precision is adjusted again, the current connection distance of the Bluetooth is the maximum effective distance of the Bluetooth, and accurate voice recognition can be realized in a range allowed by requirements by using intelligent voice equipment within the distance.
In a specific embodiment, optionally, if the frame loss speech recognition accuracy does not meet the expectation, adjusting the initial bluetooth connection distance, and repeatedly performing the above operations until the frame loss speech recognition accuracy meets the expectation, and taking the final bluetooth connection distance as the maximum effective bluetooth distance of the intelligent speech device specifically includes:
calculating a degradation value of the frame loss speech recognition precision compared with the original speech recognition precision under the condition of no frame loss, and comparing the degradation value with a preset loss expectation;
if the descending value is larger than the loss expectation, reducing the initial Bluetooth connection distance according to a set step length, and repeatedly executing the operation until the descending value is smaller than the loss expectation, and taking the corresponding Bluetooth connection distance before the current reduction operation as the maximum effective Bluetooth distance of the intelligent voice equipment; or
And if the descending value is smaller than the expected loss, increasing the initial Bluetooth connection distance according to a set step length, and repeatedly executing the operation until the descending value is larger than the expected loss, and taking the corresponding Bluetooth connection distance before the current increasing operation as the maximum effective Bluetooth distance of the intelligent voice equipment.
Specifically, under the condition of no frame loss, the voice signal is normally recognized, the original voice recognition precision is the largest at the moment, and under the condition of frame loss, the frame loss voice recognition precision is reduced compared with the original voice recognition precision, so that the maximum effective distance of the Bluetooth is determined according to the comparison result and in the repeated testing process after the Bluetooth connection distance is adjusted by calculating the voice recognition precision reduction value and comparing the reduction value with the preset loss expectation.
The preset loss expectation can be set by a technician according to specific conditions and can be a specific numerical value, that is, compared with the original speech recognition accuracy, the frame loss speech recognition accuracy can only be reduced at most, and the actual requirements cannot be met at most. Therefore, if the drop value is smaller than the expected loss value, the frame loss speech recognition precision is still the reduced control, and the test is repeated after the Bluetooth connection distance needs to be increased; if the drop value is larger than the expected loss value, the frame loss speech recognition precision cannot meet the actual requirement, and the current Bluetooth connection distance is too large and needs to be further reduced. It should also be noted that the bluetooth connection distance may be increased or decreased step by step according to a preset step size. And when the step length is increased or decreased, the corresponding decrease value is larger or smaller than the expected loss, which indicates that the corresponding Bluetooth connection distance before the operation of increasing or decreasing is the maximum effective distance of the Bluetooth.
The technical scheme of the embodiment is that the maximum frame loss number and the maximum continuous frame loss number of the voice test sample are counted under the initial Bluetooth connection distance, so as to adaptively control the voice test sample to drop frames according to different frame loss numbers according to the maximum frame loss number and the maximum continuous frame loss number, and by counting the frame loss speech recognition accuracy of the server on the speech test sample under the frame loss condition, thereby obtaining the speech recognition condition under the current Bluetooth connection distance in real time, adaptively adjusting the Bluetooth connection distance by comparing the frame loss speech recognition precision with the expectation, guiding the frame loss speech recognition precision to accord with the expectation, and then the final maximum effective distance of the Bluetooth is obtained through evaluation, the maximum effective distance of the Bluetooth of the intelligent voice equipment is effectively and accurately tested, and the requirement on the voice signal identification accuracy is met on the basis of ensuring the effective transmission of the voice signal.
Example two
Fig. 3 is a flowchart of a bluetooth evaluation method for an intelligent speech device according to a second embodiment of the present invention. The present embodiment is optimized based on the above embodiments, and details not described in detail in the present embodiment are described in the above embodiments. Referring to fig. 3, the bluetooth evaluation method provided in this embodiment includes:
s210, under the initial Bluetooth connection distance, counting the maximum frame loss number and the maximum continuous frame loss number of the received voice test sample in the process that the terminal receives the voice test sample set from the intelligent voice device through Bluetooth.
S220, controlling each voice test sample in the voice test sample set from a first frame to an m-th frameiFrame start, successive frame loss miAnd counting the speech recognition precision of the speech test sample after frame loss by the server to obtain a first speech recognition precision set, wherein m isiIs the maximum number of lost frames.
Specifically, each voice test sample in the voice test sample set is subjected to continuous frame loss, and the continuous frame loss m is started from the first frame of the voice test sampleiFrame, obtaining frame loss speech recognition accuracy, and obtaining frame loss speech recognition accuracyBeginning the second frame of the speech test sample, continuously dropping miFrame, obtaining frame loss speech recognition accuracy, and so on, until m is from lastiFrame start, consecutive lost miAnd framing to obtain frame loss voice recognition precision, wherein all the frame loss voice recognition precision form a first voice recognition precision set.
S230, mixing miSplitting into niAnd less than niE split combinations are obtained, such that in each split combination, n isiAnd the sum of said at least one natural number and miAre equal to each other, wherein niFor the maximum continuous frame loss number, and niAnd at least one natural number is referred to as a split element in the combination.
Specifically, the maximum number of lost frames miSplitting into the corresponding maximum continuous frame loss number niAnd less than niSo as to perform a discontinuous frame loss test according to the split frame loss number.
S240, in each combination eiThen, frame dropping is controlled according to the following mode, and the speech recognition precision of the server to the speech test samples after frame dropping under each combination is counted to obtain a second speech recognition precision set: for each speech test sample of the set of speech test samples, combining eiAnd taking each split element as the frame number of discontinuous frame loss, and controlling the frame loss under all position combinations of each voice test sample according to the frame number.
Specifically, each voice test sample in the voice test sample set is subjected to discontinuous frame loss, frame loss position combinations in each voice test sample are determined according to split elements in various split combinations, and frame loss is carried out according to the split elements at each position.
Illustratively, when the maximum frame loss is 10 and the maximum continuous frame loss is 5, one of the splitting modes may be continuous 5 frame loss, continuous 2 frame loss and continuous 3 frame loss. In this case, if the value of L is 10, the frame loss positions may be set to 5 frames continuously lost from the first frame, 2 frames continuously lost from the fourth frame, and 3 frames continuously lost from the fourteenth frame. Of course, the splitting manner may be 5 frames, 4 frames and 1 frame, or 5 frames, 3 frames and 2 frames. Correspondingly, on the premise that L is 10 frames, frame loss schemes under various different position combinations can be determined. And because the speech recognition result of the kth frame is only related to the speech test sample of the previous L frame, if the interval of the two frame loss positions is greater than L, the two frame loss positions cannot generate correlation influence on the speech recognition, so that the effect of two discontinuous frame loss evaluations cannot be achieved, therefore, the interval of the adjacent frame loss positions needs to be set to be not greater than the L frame, and the L can be obtained according to a model rule, namely, the speech recognition result of the kth frame is only related to the speech test sample of the previous L frame according to the statistics of a pre-obtained speech recognition model.
And S250, determining the speech recognition precision with the minimum precision value in the first speech recognition precision set and the second speech recognition precision set as the frame loss speech recognition precision.
Specifically, due to the fact that frame loss is carried out continuously and frame loss is carried out discontinuously, the speech recognition precision after frame loss is reduced compared with the original speech recognition precision, and in order to test the maximum effective distance of the Bluetooth, the speech recognition precision with the minimum speech recognition precision in the first speech recognition precision set and the second speech recognition precision set is selected as the frame loss speech recognition precision to be evaluated.
And S260, if the frame loss voice recognition precision does not meet the expectation, repeating the operation under the adjusted Bluetooth connection distance until the frame loss voice recognition precision meets the expectation, and taking the final Bluetooth connection distance as the maximum effective distance of the Bluetooth of the intelligent voice equipment.
According to the technical scheme of the embodiment, the continuous frame loss number and the non-continuous frame loss number are set, different positions of the non-continuous frame loss are set, each voice test sample is controlled to perform continuous frame loss and non-continuous frame loss, the voice recognition precision under the frame loss condition is obtained, and the test process is comprehensive and accurate. And finally, adjusting the initial Bluetooth connection distance according to the voice recognition precision and the expected comparative adaptability to obtain the final maximum effective distance of the Bluetooth, so that the intelligent voice equipment can realize normal voice signal transmission at the maximum effective distance of the Bluetooth.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a bluetooth evaluation device of an intelligent speech device according to a third embodiment of the present invention. The device is suitable for testing the maximum effective distance of the Bluetooth on the premise of meeting the requirement of voice recognition precision, can be realized by software and/or hardware, and can be specifically integrated in electronic equipment, and the electronic equipment can be equipment for realizing Bluetooth evaluation, such as computer equipment. Referring to fig. 4, the apparatus specifically includes:
a lost frame counting module 410, configured to count a maximum lost frame number and a maximum continuous lost frame number of a received voice test sample in a process that the terminal receives a voice test sample set from an intelligent voice device through bluetooth at an initial bluetooth connection distance;
a voice recognition accuracy statistic module 420, configured to control, for each voice test sample in the voice test sample set, frame loss of the voice test sample according to the maximum frame loss number and the maximum continuous frame loss number, and to count frame loss voice recognition accuracy of the voice test sample after frame loss by the server;
a maximum effective distance determining module 430, configured to, if the frame loss speech recognition accuracy does not meet the expectation, repeat the above operations at the adjusted bluetooth connection distance until the frame loss speech recognition accuracy meets the expectation, and use the final bluetooth connection distance as the bluetooth maximum effective distance of the intelligent speech device.
Optionally, the speech recognition accuracy statistics module 420 specifically includes:
the frame loss control unit is used for determining the continuous frame loss number and the discontinuous frame loss number of the voice test sample at different positions according to the maximum frame loss number and the maximum continuous frame loss number aiming at each voice test sample in the voice test sample set, and controlling the voice test sample to lose frames at different positions according to the continuous frame loss number and the discontinuous frame loss number respectively;
and the voice recognition precision determining unit is used for respectively counting the voice recognition precision with the minimum precision value in the voice recognition precision of the voice test samples after continuous frame loss and discontinuous frame loss by the server as the frame loss voice recognition precision.
Optionally, the speech recognition accuracy statistics module 420 specifically includes:
a first obtaining unit for controlling each voice test sample in the voice test sample set from a first frame to a m-th fromiFrame start, successive frame loss miAnd counting the speech recognition precision of the speech test sample after frame loss by the server to obtain a first speech recognition precision set, wherein m isiThe maximum frame loss number is the maximum frame loss number;
a splitting unit for splitting miSplitting into niAnd less than niE split combinations are obtained, such that in each split combination, n isiAnd the sum of said at least one natural number and miIs equal, wherein n isiAnd at least one natural number called a splitting element in the composition, where niThe maximum continuous frame loss number is set;
a second obtaining unit for obtaining each combination eiThen, frame dropping is controlled according to the following mode, and the speech recognition precision of the server to the speech test samples after frame dropping under each combination is counted to obtain a second speech recognition precision set: for each speech test sample of the set of speech test samples, combining eiTaking each split element as the frame number of discontinuous frame loss, and controlling frame loss under all position combinations of each voice test sample according to the frame number;
and the voice recognition precision acquisition unit is used for determining the voice recognition precision with the minimum precision value in the first voice recognition precision set and the second voice recognition precision set as the frame loss voice recognition precision.
Optionally, when aiming at each voice test sample in the voice test sample set, combining eiTaking each split element as the frame number of discontinuous frame loss, and testing each voice according to the frame numberWhen frame loss is controlled under all position combinations of the samples, the interval between any two adjacent frame loss positions is not more than L frames, wherein L is the maximum frame number of a voice recognition result of an adjacent frame after the L frames are influenced.
Optionally, the maximum effective distance determining module 430 includes:
the computing unit is used for computing a reduction value of the frame loss speech recognition precision compared with the original speech recognition precision under the condition of no frame loss and comparing the reduction value with a preset loss expectation;
a first distance adjusting unit, configured to reduce the initial bluetooth connection distance according to a set step length if the degradation value is greater than the loss expectation, and repeatedly perform the above operations until the degradation value is less than the loss expectation, and use a bluetooth connection distance corresponding to a current reduction operation as a bluetooth maximum effective distance of the intelligent voice device;
and the second distance adjusting unit is used for increasing the initial Bluetooth connection distance according to a set step length if the degradation value is smaller than the loss expectation, and repeatedly executing the operation until the degradation value is larger than the loss expectation, and taking the corresponding Bluetooth connection distance before the current increase operation as the maximum effective Bluetooth distance of the intelligent voice equipment.
The image processing apparatus according to the above embodiment is configured to execute the bluetooth evaluation method of the intelligent voice device according to any of the above embodiments, and the technical principle and the generated technical effect are similar, which are not described herein again.
Example four
Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary electronic device 512 that may be suitable for use in implementing embodiments of the present invention. The electronic device 512 shown in fig. 5 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present invention.
As shown in fig. 5, the electronic device 512 includes: one or more processors 516; the memory 528 is configured to store one or more programs, and when the one or more programs are executed by the one or more processors 516, the one or more processors 516 implement the bluetooth evaluation method for an intelligent speech device according to the embodiment of the present invention, including:
under the initial Bluetooth connection distance, counting the maximum frame loss number and the maximum continuous frame loss number of a received voice test sample in the process that the terminal receives a voice test sample set from intelligent voice equipment through Bluetooth;
controlling the voice test samples to drop frames according to different frame dropping numbers according to the maximum frame dropping number and the maximum continuous frame dropping number aiming at each voice test sample in the voice test sample set, and counting the frame dropping voice recognition precision of the voice test samples after frame dropping by equipment;
if the frame-lost voice recognition precision is not in line with the expectation, the operations are repeatedly executed under the adjusted Bluetooth connection distance until the frame-lost voice recognition precision is in line with the expectation, and the final Bluetooth connection distance is used as the maximum effective distance of the Bluetooth of the intelligent voice equipment.
In the form of a general purpose computing device. Components of the electronic device 512 may include, but are not limited to: one or more processors or processors 516, a system memory 528, and a bus 518 that couples the various system components including the system memory 528 and the processors 516.
Bus 518 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 512 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 512 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 528 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)530 and/or cache memory 532. The electronic device 512 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, the storage system 536 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 518 through one or more data media interfaces. Memory 528 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 560 having a set (at least one) of program modules 562, which may be stored, for example, in memory 528, such program modules 562 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. The program modules 562 generally execute the functions and/or methodologies of the described embodiments of the invention.
The electronic device 512 may also communicate with one or more external devices 516 (e.g., keyboard, pointing device, display 526, etc.), with one or more devices that enable a user to interact with the electronic device 512, and/or with any devices (e.g., network card, modem, etc.) that enable the electronic device 512 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 522. Also, the electronic device 512 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 520. As shown, the network adapter 520 communicates with the other modules of the electronic device 512 via the bus 518. It should be appreciated that although not shown in FIG. 5, other hardware and/or software modules may be used in conjunction with the electronic device 512, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processor 516 executes various functional applications and bluetooth evaluation of the intelligent speech device by running at least one of other programs stored in the system memory 528, for example, implementing a bluetooth evaluation method for the intelligent speech device provided by the embodiment of the present invention:
under the initial Bluetooth connection distance, counting the maximum frame loss number and the maximum continuous frame loss number of a received voice test sample in the process that the terminal receives a voice test sample set from intelligent voice equipment through Bluetooth;
controlling the voice test samples to drop frames according to different frame dropping numbers according to the maximum frame dropping number and the maximum continuous frame dropping number aiming at each voice test sample in the voice test sample set, and counting the frame dropping voice recognition precision of the voice test samples after frame dropping by the server;
if the frame-lost voice recognition precision is not in line with the expectation, the operations are repeatedly executed under the adjusted Bluetooth connection distance until the frame-lost voice recognition precision is in line with the expectation, and the final Bluetooth connection distance is used as the maximum effective distance of the Bluetooth of the intelligent voice equipment.
EXAMPLE five
The fifth embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the computer-executable instructions, when executed by a computer processor, are used to execute a bluetooth evaluation method for an intelligent voice device:
under the initial Bluetooth connection distance, counting the maximum frame loss number and the maximum continuous frame loss number of a received voice test sample in the process that the terminal receives a voice test sample set from intelligent voice equipment through Bluetooth;
controlling the voice test samples to drop frames according to different frame dropping numbers according to the maximum frame dropping number and the maximum continuous frame dropping number aiming at each voice test sample in the voice test sample set, and counting the frame dropping voice recognition precision of the voice test samples after frame dropping by the server;
if the frame-lost voice recognition precision is not in line with the expectation, the operations are repeatedly executed under the adjusted Bluetooth connection distance until the frame-lost voice recognition precision is in line with the expectation, and the final Bluetooth connection distance is used as the maximum effective distance of the Bluetooth of the intelligent voice equipment.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (10)

1. A Bluetooth evaluation method of intelligent voice equipment is provided, the intelligent voice equipment is connected with a terminal through Bluetooth, and the method is characterized by comprising the following steps:
under the initial Bluetooth connection distance, counting the maximum frame loss number and the maximum continuous frame loss number of a received voice test sample in the process that the terminal receives a voice test sample set from intelligent voice equipment through Bluetooth;
controlling the voice test samples to drop frames according to different frame dropping numbers according to the maximum frame dropping number and the maximum continuous frame dropping number aiming at each voice test sample in the voice test sample set, and counting the frame dropping voice recognition precision of the voice test samples after frame dropping by the server;
if the frame-lost voice recognition precision is not in line with the expectation, the operations are repeatedly executed under the adjusted Bluetooth connection distance until the frame-lost voice recognition precision is in line with the expectation, and the final Bluetooth connection distance is used as the maximum effective distance of the Bluetooth of the intelligent voice equipment.
2. The method of claim 1, wherein for each voice test sample in the voice test sample set, controlling the voice test sample to drop frames according to the maximum frame loss number and the maximum continuous frame loss number, and counting the frame loss voice recognition accuracy of the voice test sample after frame loss by the server, specifically comprises:
determining the continuous frame loss number and the discontinuous frame loss number of the voice test sample at different positions according to the maximum frame loss number and the maximum continuous frame loss number aiming at each voice test sample in the voice test sample set, and controlling the voice test sample to drop frames at different positions according to the continuous frame loss number and the discontinuous frame loss number respectively;
and respectively counting the speech recognition precision with the minimum precision value in the speech recognition precision of the speech test samples after continuous frame loss and discontinuous frame loss by the server, and taking the speech recognition precision as the frame loss speech recognition precision.
3. The method according to claim 1 or 2, wherein for each voice test sample in the voice test sample set, controlling the voice test sample to drop frames according to the maximum frame loss number and the maximum continuous frame loss number, and counting the frame loss voice recognition accuracy of the server on the voice test sample after frame loss, specifically comprises:
to is directed atEach voice test sample in the voice test sample set is controlled from a first frame to a m-th frameiFrame start, successive frame loss miAnd counting the speech recognition precision of the speech test sample after frame loss by the server to obtain a first speech recognition precision set, wherein m isiThe maximum frame loss number is the maximum frame loss number;
m is to beiSplitting into niAnd less than niE split combinations are obtained, such that in each split combination, n isiAnd the sum of said at least one natural number and miAre equal to each other, wherein niFor the maximum continuous frame loss number, and niAnd at least one natural number is called a split element in the combination;
in each combination eiThen, frame dropping is controlled according to the following mode, and the speech recognition precision of the server to the speech test samples after frame dropping under each combination is counted to obtain a second speech recognition precision set: for each speech test sample of the set of speech test samples, combining eiTaking each split element as the frame number of discontinuous frame loss, and controlling frame loss under all position combinations of each voice test sample according to the frame number;
and determining the speech recognition precision with the minimum precision value in the first speech recognition precision set and the second speech recognition precision set as the frame loss speech recognition precision.
4. The method of claim 3, wherein e is combined for each speech test sample in the set of speech test samplesiWhen frame loss is controlled under all position combinations of each voice test sample according to the frame number, the interval between any two adjacent frame loss positions is not more than L frames, wherein L is the maximum frame number influencing the voice recognition result of an adjacent frame after the L frames.
5. The method of claim 1, wherein if the frame-lost speech recognition accuracy is not satisfactory, the above operations are repeatedly performed at the adjusted bluetooth connection distance until the frame-lost speech recognition accuracy is satisfactory, and the final bluetooth connection distance is used as the maximum effective bluetooth distance of the intelligent speech device, and specifically comprises:
calculating a degradation value of the frame loss speech recognition precision compared with the original speech recognition precision under the condition of no frame loss, and comparing the degradation value with a preset loss expectation;
if the descending value is larger than the loss expectation, repeating the operation under the Bluetooth connection distance reduced according to the set step length until the descending value is smaller than the loss expectation, and taking the corresponding Bluetooth connection distance before the current reduction operation as the maximum effective Bluetooth distance of the intelligent voice equipment; or
And if the descending value is smaller than the expected loss, repeating the operation under the Bluetooth connection distance increased according to the set step length until the descending value is larger than the expected loss, and taking the corresponding Bluetooth connection distance before the current increasing operation as the maximum effective Bluetooth distance of the intelligent voice equipment.
6. A Bluetooth evaluating device of intelligent voice equipment is characterized by comprising:
the lost frame counting module is used for counting the maximum lost frame number and the maximum continuous lost frame number of the received voice test sample in the process that the terminal receives the voice test sample set from the intelligent voice equipment through the Bluetooth under the initial Bluetooth connection distance;
the voice recognition precision statistical module is used for controlling the voice test samples to drop frames according to different frame loss numbers according to the maximum frame loss number and the maximum continuous frame loss number aiming at each voice test sample in the voice test sample set, and counting the frame loss voice recognition precision of the voice test samples after frame loss by the server;
and the maximum effective distance determining module is used for repeating the operation under the adjusted Bluetooth connection distance if the frame loss voice recognition precision does not meet the expectation, until the frame loss voice recognition precision meets the expectation, and taking the final Bluetooth connection distance as the Bluetooth maximum effective distance of the intelligent voice equipment.
7. The apparatus according to claim 6, wherein the speech recognition accuracy statistic module specifically includes:
the frame loss control unit is used for determining the continuous frame loss number and the discontinuous frame loss number of the voice test sample at different positions according to the maximum frame loss number and the maximum continuous frame loss number aiming at each voice test sample in the voice test sample set, and controlling the voice test sample to lose frames at different positions according to the continuous frame loss number and the discontinuous frame loss number respectively;
and the voice recognition precision determining unit is used for respectively counting the voice recognition precision with the minimum precision value in the voice recognition precision of the voice test samples after continuous frame loss and discontinuous frame loss by the server as the frame loss voice recognition precision.
8. The apparatus according to claim 6 or 7, wherein the speech recognition accuracy statistic module specifically includes:
a first obtaining unit for controlling each voice test sample in the voice test sample set from a first frame to a m-th fromiFrame start, successive frame loss miAnd counting the speech recognition precision of the speech test sample after frame loss by the server to obtain a first speech recognition precision set, wherein m isiThe maximum frame loss number is the maximum frame loss number;
a splitting unit for splitting miSplitting into niAnd less than niE split combinations are obtained, such that in each split combination, n isiAnd the sum of said at least one natural number and miIs equal, wherein n isiAnd at least one natural number called a splitting element in the composition, where niThe maximum continuous frame loss number is set;
a second obtaining unit for obtaining each combination eiNext, frame loss is controlled as follows, and statistics server counts each combinationAnd obtaining a second speech recognition precision set according to the speech recognition precision of the speech test sample after frame dropping: for each speech test sample of the set of speech test samples, combining eiTaking each split element as the frame number of discontinuous frame loss, and controlling frame loss under all position combinations of each voice test sample according to the frame number;
and the voice recognition precision acquisition unit is used for determining the voice recognition precision with the minimum precision value in the first voice recognition precision set and the second voice recognition precision set as the frame loss voice recognition precision.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for bluetooth profiling of an intelligent speech device according to any of claims 1-5.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for bluetooth evaluation of an intelligent speech device according to any one of claims 1 to 5.
CN201910153246.5A 2019-02-28 2019-02-28 Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment Active CN109637540B (en)

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 CN109637540A (en) 2019-04-16
CN109637540B true 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)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003131683A (en) * 2001-10-22 2003-05-09 Sony Corp Device and method for voice recognition, and program and recording medium
JP5075664B2 (en) * 2008-02-15 2012-11-21 株式会社東芝 Spoken dialogue apparatus and support method
US10489515B2 (en) * 2015-05-08 2019-11-26 Electronics And Telecommunications Research Institute Method and apparatus for providing automatic speech translation service in face-to-face situation
US9980189B2 (en) * 2015-10-20 2018-05-22 Bragi GmbH Diversity bluetooth system and method
CN109243441B (en) * 2018-09-26 2023-01-20 广东小天才科技有限公司 Guiding method, guiding device, guiding terminal and storage medium for adjusting voice acquisition distance

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Also Published As

Publication number Publication date
CN109637540A (en) 2019-04-16

Similar Documents

Publication Publication Date Title
CN109767792B (en) Voice endpoint detection method, device, terminal and storage medium
CN104067341A (en) Voice activity detection in presence of background noise
CN110351595B (en) Buffer processing method, device, equipment and computer storage medium
CN109714636B (en) User identification method, device, equipment and medium
CN109359118B (en) Data writing method and device
CN109637540B (en) Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment
CN108073572B (en) Information processing method and device, simultaneous interpretation system
EP4102499A1 (en) Wakeup testing method and apparatus, electronic device and readable storage medium
US8868419B2 (en) Generalizing text content summary from speech content
CN111311392A (en) Wind control decision method, device, server and storage medium
CN106776039A (en) A kind of data processing method and device
CN113114540B (en) Method for setting bandwidth predictor and adjusting service and related device
US20190074029A1 (en) Voice data processing apparatus and voice data processing method for avoiding voice delay
WO2024051823A1 (en) Method for managing reception information and back-end device
CN112863545A (en) Performance test method and device, electronic equipment and computer readable storage medium
CN111311393A (en) Credit risk assessment method, device, server and storage medium
US11609925B2 (en) Systems and methods for automatically recommending content
CN113347497B (en) Target user identification method and device, electronic equipment and storage medium
CN114038465B (en) Voice processing method and device and electronic equipment
CN103561022A (en) Voice service access method, related device and voice service system
CN115312042A (en) Method, apparatus, device and storage medium for processing audio
CN113051400A (en) Method and device for determining annotation data, readable medium and electronic equipment
CN110995947B (en) Channel density detection method and device and computer equipment
CN114203204B (en) Tail point detection method, device, equipment and storage medium
CN111084985B (en) Parameter adjusting method and device of input equipment, terminal equipment and medium

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