CN111443329A - Sound source positioning method and device, computer storage medium and electronic equipment - Google Patents
Sound source positioning method and device, computer storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111443329A CN111443329A CN202010220486.5A CN202010220486A CN111443329A CN 111443329 A CN111443329 A CN 111443329A CN 202010220486 A CN202010220486 A CN 202010220486A CN 111443329 A CN111443329 A CN 111443329A
- Authority
- CN
- China
- Prior art keywords
- sound source
- measurement area
- current measurement
- area
- size
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/18—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using ultrasonic, sonic, or infrasonic waves
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The disclosure relates to the technical field of data processing, and provides a sound source positioning method, a sound source positioning device, a computer-readable storage medium for realizing the sound source positioning method and an electronic device. Wherein, the method comprises the following steps: for the current measurement area, determining the size of the current measurement area and the measurement precision corresponding to the current measurement area; performing mesh division on a current measurement area according to measurement accuracy to determine a plurality of assumed sound sources so as to determine a target sound source of the current measurement area among the plurality of assumed sound sources; dividing a next measurement area with a smaller size in the current test area according to the position of the target sound source in the current test area; and updating the next measurement area to the current measurement area so as to locate the target sound source of the next measurement area. According to the technical scheme, under the condition of ensuring the sound source positioning precision, the calculation amount is favorably reduced, and the sound source positioning efficiency is further improved.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a sound source positioning method, a sound source positioning apparatus, and a computer storage medium and an electronic device for implementing the sound source positioning method.
Background
Sound source localization technology has been widely used in the fields of sound source tracking, speech enhancement, etc. Sound localization in an area is generally achieved by using an array of microphones to collect sound signals in the area and further form beams.
In the related art, the sound source localization for a certain area may specifically include: the region is first divided into a plurality of assumed sound source points according to the positioning accuracy, and further, for each assumed sound source point, the following calculation is performed: calculating coordinates of a sound source point, calculating a relative position between the sound source point and each microphone in a microphone array, calculating weighting, time delay and summation after each microphone collects a sound source signal of the sound source point, and calculating a power spectrum of summed data.
However, in the sound source localization scheme in the related art, the amount of calculation is large, and the sound source localization efficiency needs to be improved.
It is to be noted that the information disclosed in the background section above is only used to enhance understanding of the background of the present disclosure.
Disclosure of Invention
An object of the present disclosure is to provide a sound source positioning method, a sound source positioning apparatus, a computer storage medium, and an electronic device, so that under the condition of ensuring positioning accuracy, the amount of calculation is reduced at least to a certain extent, which is beneficial to improving the sound source positioning efficiency.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present disclosure, there is provided a sound source localization method including:
for a current measurement area, determining the size of the current measurement area and determining the grid division size of the current measurement area; performing meshing on the current measurement area according to the meshing size to determine a plurality of assumed sound sources, and determining a target sound source of the current measurement area from the plurality of assumed sound sources; dividing a next measurement area with a smaller size in the current test area according to the position of the target sound source in the current test area; and updating the next measurement area to the current measurement area so as to locate the target sound source of the next measurement area.
In some embodiments of the present disclosure, based on the foregoing solution, determining the size of the current measurement area and determining the mesh division size of the current measurement area includes:
obtaining a first side length L and a second side length W of an inscribed rectangle of the current measurement region to obtain the size of the current measurement region, wherein L is larger than or equal to W, L and W are both positive numbers, obtaining a grid division size of L/n for the current measurement region in the first side direction, and obtaining a grid division size of W/n for the current measurement region in the second side direction, wherein n is a positive integer.
In some embodiments of the present disclosure, based on the foregoing scheme, determining a target sound source of the current measurement area among the plurality of assumed sound sources includes: calculating a power of each of the assumed sound sources based on an acoustic array composed of a plurality of acoustic sensors; and determining the assumed sound source with the maximum power as the target sound source of the current measuring area.
In some embodiments of the present disclosure, based on the foregoing solution, calculating the power of each of the assumed sound sources based on an acoustic array composed of a plurality of acoustic sensors includes: calculating a time delay between each acoustic sensor and a reference sensor for each assumed sound source, wherein the reference sensor is the acoustic sensor closest to the assumed sound source in the acoustic array; and carrying out signal time shift on each acoustic sensor according to the time delay, and carrying out weighted summation to obtain the power of the assumed sound source.
In some embodiments of the present disclosure, based on the foregoing solution, cutting out a next measurement area with a smaller size in the current test area according to the position of the target sound source in the current test area includes: and determining the side length of the next measurement area according to the grid division size by taking the position of the target sound source in the current test area as the center of the next measurement area, and cutting the next measurement area in the current test area.
In some embodiments of the present disclosure, based on the foregoing scheme, updating the next measurement area to the current measurement area to locate the target sound source of the next measurement area includes: for the updated current measurement area, determining the grid division size of the updated current measurement area; and performing meshing on the updated current measuring area according to the meshing size to determine a plurality of assumed sound sources, so as to determine a target sound source of the updated current measuring area from the plurality of assumed sound sources, and dividing a next measuring area with a smaller size from the updated current measuring area according to the position of the target sound source in the updated current measuring area.
In some embodiments of the present disclosure, based on the foregoing scheme, before meshing the current measurement area according to the meshing size, the method further includes: judging whether the measurement precision corresponding to the current measurement area meets a preset precision requirement or not; and if so, taking the target sound source of the current measurement area as a final sound source.
According to an aspect of the present disclosure, there is provided a sound source localization apparatus including:
a size determination module configured to: for a current measurement area, determining the size of the current measurement area and determining the grid division size of the current measurement area; a meshing module configured to: performing meshing on the current measurement area according to the meshing size to determine a plurality of assumed sound sources, and determining a target sound source of the current measurement area from the plurality of assumed sound sources; a region segmentation module configured to: cutting a next measurement area with a smaller size in the current test area according to the position of the target sound source in the current test area; an update module configured to: and updating the next measurement area to the current measurement area so as to locate the target sound source of the next measurement area.
According to an aspect of the present disclosure, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the sound source localization method of the first aspect described above.
According to an aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the sound source localization method of the first aspect described above via execution of the executable instructions.
As can be seen from the foregoing technical solutions, the sound source positioning method, the sound source positioning device, the computer storage medium and the electronic device in the exemplary embodiments of the present disclosure have at least the following advantages and positive effects:
in the technical solutions provided by some embodiments of the present disclosure, after a current measurement area is subjected to meshing based on a meshing size, a target sound source of the current measurement area is determined, and a next measurement area with a smaller size is divided in the current measurement area according to a position of the target sound source in the current measurement area. Further, the next measurement area is updated to the current measurement area to locate the sound source of the divided measurement area. Therefore, the technical scheme divides the measurement area based on the target sound source of the current measurement area so as to reduce the size of the current measurement area and further relocate the sound source in the measurement area with smaller size. Therefore, the technical scheme can be favorable for reducing the calculated amount under the condition of ensuring the sound source positioning precision, and further improves the sound source positioning efficiency.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.
In the drawings:
FIG. 1 is a schematic diagram of a system architecture for implementing a sound source localization method and apparatus according to an exemplary embodiment of the present disclosure;
FIG. 2 shows a schematic flow diagram of a sound source localization method according to an exemplary embodiment of the present disclosure;
FIG. 3 shows a schematic flow diagram of a sound source localization method according to another embodiment of the present disclosure;
FIG. 4 shows a schematic flow chart diagram of a sound source localization method according to yet another exemplary embodiment of the present disclosure;
FIG. 5 is a schematic view showing the structure of a sound source localization apparatus in an exemplary embodiment of the present disclosure;
FIG. 6 shows a schematic diagram of a structure of a computer storage medium in an exemplary embodiment of the disclosure; and the number of the first and second groups,
fig. 7 shows a schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The present exemplary embodiment first provides a system architecture for implementing a sound source localization method, which can be applied to various data processing scenarios. Referring to fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send request instructions or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a photo processing application, a shopping application, a web browser application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
At present, in order to improve the precision of positioning a sound source, the number of spatial scanning grid points needs to be increased, but the larger the number of grid points is, the larger the calculation amount is, most of the platforms which can meet the requirement of calculation time at present are high-performance PCs, and the hardware cost is increased in calculation.
In order to solve the above problems to a certain extent, the present technical solution provides a sound source positioning method and apparatus, a computer storage medium, and an electronic device, so as to reduce the amount of computation and further improve the sound source positioning efficiency under the condition of ensuring the sound source positioning accuracy. The following description will first be made of a sound source localization method:
fig. 2 shows a flow diagram of a sound source localization method according to an embodiment of the present disclosure. The embodiment provides a sound source positioning method. Referring to fig. 2, the sound source localization method provided in this embodiment includes:
step S210, for a current measurement area, determining the size of the current measurement area and determining the grid division size of the current measurement area;
step S220, performing meshing on the current measurement area according to the meshing size to determine a plurality of assumed sound sources, and determining a target sound source of the current measurement area from the plurality of assumed sound sources;
step S230, dividing a next measurement area with smaller size in the current test area according to the position of the target sound source in the current test area; and the number of the first and second groups,
step S240, updating the next measurement area to the current measurement area to locate the target sound source in the next measurement area.
In the technical solution provided by the embodiment shown in fig. 2, in the technical solution provided by some embodiments of the present disclosure, in the process of meshing the current measurement area based on the meshing size, a target sound source of the current measurement area is calculated and determined, and according to the position of the target sound source in the current test area, a next measurement area with a smaller size is divided in the current test area. Further, the next measurement area is updated to the current measurement area to locate the sound source of the divided measurement area. Therefore, the technical scheme divides the measurement area based on the target sound source of the current measurement area so as to reduce the size of the current measurement area and further relocate the sound source in the measurement area with smaller size. Therefore, the technical scheme can be favorable for reducing the calculated amount under the condition of ensuring the sound source positioning precision, and further improves the sound source positioning efficiency.
The following explains a specific embodiment of each step in the method shown in fig. 2:
in an exemplary embodiment, fig. 3 shows a schematic view of a region of a sound source to be located according to an embodiment of the present disclosure. The technical scheme realizes the region D0The sound source positioning can finally obtain the sound source meeting the measurement precision in a mode of one or more times of regional segmentation. Specifically, the method comprises the following steps: first, region D is mapped based on the mesh partition size by steps S210 and S2200Performing mesh division, and positioning sound source in multiple assumed sound sources determined by mesh division as region D0Target sound source S0(as shown in fig. 3). Further, based on the target sound source S in step S2300For region D0Cutting to obtain region D with small size1(as shown in fig. 3). In step S240, the next measurement area is updated to the current measurement area to be used for area D1Performing sound source localization to obtain regionsD1Target sound source S1(as shown in fig. 3). Further, it is also possible to base the target sound source S on1For region D1Cutting to obtain region D with small size2(as shown in FIG. 3); to region D2Positioning a sound source, … …, repeating the steps until the measurement precision meets the preset requirement, and obtaining the region D0The final sound source of (1).
The following section is directed to the region D in conjunction with FIG. 30Region D1And region D2The sound source localization is described.
(1) For region D0：
In step S210, the area D is determined0And determining the pair of areas D0The mesh partition size of (1). Here, the measurement accuracy is a minimum unit that is gridded to determine an assumed sound source of the current measurement region.
In an exemplary embodiment, region D is acquired0The first side length L and the second side length W of the inscribed rectangle are obtained to obtain the size of the current measuring area, wherein L is more than or equal to W, and the grid division size of the current measuring area in the first side direction is L/n1The mesh division size of the current measurement area in the second edge direction is W/n1，n1Is an even number.
Further, in step S220, the area D is divided according to the mesh division size0And (3) carrying out grid division: i.e. the first and second edge are divided into n, respectively1And (4) dividing into equal parts. Referring to fig. 3, it is found that the region belongs to the region D0[ (n) of1+1)*(n1+1)]The division area size obtained by meshing the assumed sound source (indicated by solid black dots in FIG. 3) is L/n1And W/n1. Then, in the region D0Determine the region D from a plurality of assumed sound sources0Corresponding target sound source S0. Wherein n is1Is even and is at L/n1Greater than the corresponding measurement accuracy bLOr W/n1Greater than the corresponding measurement accuracy bWIn the case of (2), the power of each assumed sound source is calculated:
in an exemplary embodiment, the power of each assumed sound source is determined according to the basic framework of fixed beamforming. I.e. for region D0Calculating a time delay between each acoustic sensor and a reference sensor, wherein the reference sensor is the acoustic sensor closest to the assumed sound source in the acoustic array; further, the signal time shift is performed on each acoustic sensor according to the above delay, and the weighted summation is performed to obtain the power of the assumed sound source x. Specifically, the method comprises the following steps:
illustratively, the acoustic sensor is a microphone. And assuming that the microphone array comprises m (m is more than or equal to 4) microphones, and assuming that the microphone closest to the assumed sound source x is y, the time t from the sound source x to each microphone is assumedi,xAnd the time t from the assumed sound source x to the microphone yy,xDifference vector TDOAxExpressed as: TDOAx＝[ty,1,x,ty,2,x,ty,3,x,…,ty,i,x,…ty,m,x]T。
Wherein, ty,i,x＝ty,x-ti,x＝(dy,x-di,x)/v，ty,i,xRepresenting the time delay between the microphone y located closest to the assumed sound source x and the i-th microphone from the assumed sound source x, v representing the speed of sound traveling in air, di,xRepresenting a straight line distance from the assumed sound source x to the i-th microphone.
Meanwhile, the sample point number difference can be represented as sd, and the corresponding vector can be represented as:
sdx＝[sdy,2,x,sdy,3,x,sdy,4,x,…,sdy,i,x,…sdy,m,x]Tassuming that the signal sampling frequency is sf, then: sdy,i,x＝round(sf*abs(ty,i,x))。
Where round () is an rounding-up function and abs () is an absolute value function, thereby calculating the number of delay points from the assumed sound source x to the nearest microphone y and other microphones. Then max (sd) is calculated1,i,x) If the signal received by the microphone y closest to the microphone y is s (t), the signal received by the ith microphone is s (t)Number s (t-t)y,i,x,). The number of delay points with the microphone y is subtracted from the signal received by each microphone, and then all the signals are subjected to time domain superposition to obtain the power of the assumed sound source x.
Similarly, region D is calculated0All assumed sound sources have power, and the assumed sound source with the largest power is taken as the region D0The target sound source of (1). In the present embodiment, referring to fig. 3, a sound source S0Is region D0The assumed sound source with the maximum medium power passes through the step (n)1+1)*(n1+1)]Calculating the sub-power to obtain region D0Target sound source S0。
In an exemplary embodiment, reference is made to fig. 4, which illustrates an embodiment based on fig. 2. In step S410, it is determined whether the size of the divided region corresponding to the current measurement region meets a preset accuracy requirement. If not, the process continues to step S210-step S240. That is, when the divided region size does not satisfy the preset accuracy requirement, the sound source localization is still required to be continued.
In this embodiment, if the predetermined sound source positioning accuracy is: in the region D0Corresponding measurement accuracy b in the first lateral directionLCorresponding measurement accuracy b in the direction of the second sideWWherein b isLLess than or equal to half of the first side length L, bWLess than or equal to half of the second side length W.
Then, the region D is determined0Corresponding division area size L/n1Greater than bLOr W/n1Greater than bWThen the next measurement zone (i.e., zone D as shown in fig. 3) needs to be determined1) And further to the region D1Performing area division and area D after grid division1Locate the target S among a plurality of assumed sound sources1。
Illustratively, referring to FIG. 3, the target sound source S is based on0For region D0Cutting to obtain region D with small size1. Specifically, in the region D0And (3) cutting out: with a target sound source S0In the region D0Is located at the centerIn the region D0Has an edge length of (2 x L/n) in the first edge direction1) Simultaneously in the region D0Has an edge length of (2W/n) in the direction of the second edge1) Corresponding region (i.e. region D in FIG. 3)0Inner shaded area D1) And obtaining the next measuring area.
(2) For region D1：
Acquisition region D1The first side length is (2 x L/n)1) The second side length is (2 x W/n)1) And to the region D1The mesh division size in the first side direction is [ (2 x L/n)1)/n2]And a second edge direction having a mesh division size of [ (2 x W/n)1)/n2]。
Further, according to the region D1Is divided into a mesh size to region D1And (3) carrying out grid division: i.e. respectively dividing the region D1Is divided into n2And (4) dividing into equal parts. Referring to fig. 3, it is found that the region belongs to the region D1[ (n) of2+1)*(n2+1)]The division area size obtained by meshing the assumed sound source (indicated by solid black dots) was [ (2 x L/n ]1)/n2]And [ (2W/n)1)/n2]Wherein n is2Is an even number. Then, in the region D1Determine the region D from a plurality of assumed sound sources1Target sound source S1. Specific determination region D1The detailed description of the embodiments of the power of each assumed sound source is omitted.
Further, the assumed sound source having the largest power is set as the region D1The target sound source of (1). In this embodiment, the sound source S1Is region D1The assumed sound source with the maximum medium power passes through the step (n)2+1)*(n2+1)]Calculating the sub-power to obtain region D1Target sound source S1。
Step S410 is executed again to determine whether the divided region size of the current measurement region meets the preset precision requirement. If the area D is determined in the present embodiment1The divided region size of (2 x L/n) fails to satisfy the predetermined accuracy requirement1)/n2]Greater than correspondingAccuracy of measurement bL、[(2*W/n1)/n2]Greater than the corresponding measurement accuracy bWThen the next measurement zone (i.e., zone D shown in fig. 3) needs to be determined2) And further to the region D2Performing region division, and region D after grid division2Locate the target S among a plurality of assumed sound sources2。
Illustratively, referring to FIG. 3, the target sound source S is based on1For region D1Cutting to obtain region D with small size2. Specifically, in the region D1And (3) cutting out: with a target sound source S1In the region D1Is located at the center and in the region D1Has a length in the first edge direction of:
(3) For region D2：
Acquisition region D2The size of (c): first side length of
The second side length is
And a region D2The mesh division size of (a): the first edge direction is divided into a mesh size of
And a second edge direction is divided into a size of
Further in accordance withFor region D2Is divided into a mesh size to region D2And (3) carrying out grid division: i.e. respectively dividing the region D2Is divided into n3And (4) dividing into equal parts. Get to belong to region D2[ (n) of3+1)*(n3+1)]A hypothetical sound source (not shown) having a mesh division area size of
And
wherein n is3Is an even number. Then, in the region D2Determine the region D from a plurality of assumed sound sources2Target sound source S2. Specific determination region D2The detailed description of the embodiments of the power of each assumed sound source is omitted.
Further, the assumed sound source having the largest power is set as the region D2The target sound source of (1). In this embodiment, the sound source S2Is region D2The assumed sound source with the maximum medium power passes through the step (n)3+1)*(n3+1)]Calculating the sub-power to obtain region D2Target sound source S2。
And step S410 is executed again to determine whether the mesh division size of the current measurement region meets the preset precision requirement. In this embodiment, if the region D is determined2Can meet a predetermined accuracy requirement, i.e. the division area size
Less than corresponding measurement accuracy bLAnd are
Less than corresponding measurement accuracy bWThen, step S420 is executed: a target sound source S2As region D0The final sound source of (1). If the region D is judged2Is divided into regionsThe dimensions not meeting the predetermined accuracy requirements, i.e.
Greater than the corresponding measurement accuracy bL、
Greater than the corresponding measurement accuracy bWThen continue to the region D2And performing meshing, positioning a target sound source in the assumed sound source points after the meshing, segmenting a next measurement area based on the positioned target sound source, and further repeatedly executing the step S410 until the meshing size precision of the current measurement area meets the requirement.
That is to say, in the present technical solution, based on the position of the target sound source in the area after each meshing division, the area is further segmented to obtain the next area to be measured, an assumed sound source is determined in the segmented area, and the assumed sound source with the maximum power is used as the target sound source of the area. Until the size precision of the grid division meets the requirement, the calculated maximum power assumed sound source point is the area D0The final sound source.
In an exemplary embodiment, boundary problems may be involved in the region segmentation process. The specific treatment method comprises the following steps: sound sources that are outside the boundary portion are directly dropped to avoid unnecessary calculations.
According to the technical scheme, the measurement area is segmented based on the target sound source of the current measurement area so as to reduce the size of the current measurement area and further relocate the sound source in the measurement area with smaller size. Therefore, the technical scheme can be favorable for reducing the calculated amount under the condition of ensuring the sound source positioning precision, and further improves the sound source positioning efficiency.
Illustratively, for a region of size L W, sound source localization is performed, where the predetermined accuracy is b-bL＝bWIf the sound source localization scheme provided according to the related art is used, (round (L/b) +1) × (round (W/b) +1) assumed sound sources are determined, and further, the power of each assumed sound source is determined in timeFor example, if L ═ W is 100 m and the minimum positioning accuracy b is 1 m, then the number of power calculations is 101 × (101) × (10201).
In addition, in the present embodiment, if the sound source is located in the L × W area, and if m times of area division are performed, and n values are the same and 8 are all determined each time the mesh division is performed (that is, based on the above-mentioned scheme, m is 3, and n1 is n2 is n3 is 8), reference may be made to the area D in fig. 30Then the region D0The number of assumed sound sources in (1) is
The power calculation times are 243 times which is much smaller than 10201 times required in the related art, 10201/243 ≈ 42 times.
Therefore, by adopting the sound source positioning scheme provided by the technical scheme, the calculated amount can be effectively reduced, so that the calculation time and the calculation resource are saved, and the sound source positioning efficiency is improved. Meanwhile, the method is favorable for saving the calculation cost. The technical scheme is not only suitable for the application occasions of the traditional server and the PC to reduce the calculation amount and energy consumption, but also suitable for the embedded application occasions, so that the application which cannot be realized due to large calculation amount can be realized. Meanwhile, the device has the advantages of strong environmental adaptability and capability of working in severe environments such as low temperature, high vibration and the like.
Those skilled in the art will appreciate that all or part of the steps implementing the above embodiments are implemented as computer programs executed by a CPU. When executed by the CPU, performs the functions defined by the above-described methods provided by the present disclosure. The program may be stored in a computer readable storage medium, which may be a read-only memory, a magnetic or optical disk, or the like.
Furthermore, it should be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Embodiments of the interface adaptation system of the present disclosure are described below, which may be used to perform the above-described adaptable methods of the present disclosure.
Fig. 5 shows a schematic configuration diagram of a sound source localization apparatus in an exemplary embodiment of the present disclosure. As shown in fig. 5, the sound source localization apparatus 500 includes: a size determination module 501, a meshing module 502, a region segmentation module 503, and an update module 504.
Wherein the size determining module 501 is configured to: for a current measurement area, determining the size of the current measurement area and determining the grid division size of the current measurement area;
the above-mentioned meshing module 502 is configured to: performing meshing on the current measurement area according to the meshing size to determine a plurality of assumed sound sources, and determining a target sound source of the current measurement area from the plurality of assumed sound sources;
the region segmentation module 503 is configured to: cutting a next measurement area with a smaller size in the current test area according to the position of the target sound source in the current test area;
the update module 504, configured to: and updating the next measurement area to the current measurement area so as to locate the target sound source of the next measurement area.
In some embodiments of the present disclosure, based on the foregoing solution, the size determining module 501 is specifically configured to:
obtaining a first side length L and a second side length W of an inscribed rectangle of the current measurement region to obtain the size of the current measurement region, wherein L is larger than or equal to W, L and W are both positive numbers, obtaining a grid division size of L/n for the current measurement region in the first side direction, and obtaining a grid division size of W/n for the current measurement region in the second side direction, wherein n is a positive integer.
In some embodiments of the present disclosure, based on the foregoing scheme, determining a target sound source of the current measurement area among the plurality of assumed sound sources includes:
calculating a power of each of the assumed sound sources based on an acoustic array composed of a plurality of acoustic sensors;
and determining the assumed sound source with the maximum power as the target sound source of the current measuring area.
In some embodiments of the present disclosure, based on the foregoing scheme, the above-mentioned meshing module 502 is specifically configured to:
calculating a time delay between each acoustic sensor and a reference sensor for each assumed sound source, wherein the reference sensor is the acoustic sensor closest to the assumed sound source in the acoustic array; and carrying out signal time shift on each acoustic sensor according to the time delay, and carrying out weighted summation to obtain the power of the assumed sound source.
In some embodiments of the present disclosure, based on the foregoing scheme, the region segmentation module 503 is specifically configured to:
and determining the side length of the next measurement area according to the grid division size by taking the position of the target sound source in the current test area as the center of the next measurement area, and cutting the next measurement area in the current test area.
In some embodiments of the present disclosure, based on the foregoing scheme, the update module 504 is specifically configured to:
for the updated current measurement area, determining the grid division size of the updated current measurement area; and performing meshing on the updated current measurement area according to the meshing size to determine a plurality of assumed sound sources, so as to determine a target sound source of the updated current measurement area from the plurality of assumed sound sources, and dividing a next measurement area with a smaller size from the updated current measurement area according to the position of the target sound source in the updated current measurement area.
In some embodiments of the present disclosure, based on the foregoing solution, the sound source localization apparatus 500 further includes: and a judging module.
Wherein the determining module is configured to: before the mesh division module 502 performs mesh division on the current measurement region according to the mesh division size, whether the measurement precision corresponding to the current measurement region meets a preset precision requirement is judged; and if so, taking the target sound source of the current measurement area as a final sound source.
For details that are not disclosed in the embodiments of the sound source localization apparatus of the present disclosure, please refer to the embodiments of the sound source localization method of the present disclosure described above for details that are not disclosed in the embodiments of the sound source localization apparatus of the present disclosure, since each functional module of the sound source localization apparatus of the exemplary embodiments of the present disclosure corresponds to a step of the exemplary embodiments of the sound source localization method described above.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, there is also provided a computer storage medium capable of implementing the above method. On which a program product capable of implementing the above-described method of the present specification is stored. In some possible embodiments, various aspects of the present disclosure may also be implemented in the form of a program product including program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present disclosure described in the "exemplary methods" section above of this specification when the program product is run on the terminal device.
Referring to fig. 6, a program product 600 for implementing the above method according to an embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a 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.
The program product described above may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A 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 readable storage medium include: an electrical connection having one or more wires, a portable disk, 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 disk Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with 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 readable signal medium may also be any readable medium that is not a 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 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.
The program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including AN object oriented programming language such as Java, C + +, etc., as well as conventional procedural programming languages, such as the "C" language or similar programming languages.
In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 700 according to this embodiment of the disclosure is described below with reference to fig. 7. The electronic device 700 shown in fig. 7 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 7, electronic device 700 is embodied in the form of a general purpose computing device. The components of the electronic device 700 may include, but are not limited to: the at least one processing unit 710, the at least one memory unit 720, and a bus 730 that couples various system components including the memory unit 720 and the processing unit 710.
Wherein the storage unit stores program codes, which can be executed by the processing unit 710, so that the processing unit 710 executes the steps according to various exemplary embodiments of the present disclosure described in the "exemplary method" section above in this specification. For example, the processing unit 710 described above may perform the following as shown in fig. 2: step S210, for a current measurement area, determining the size of the current measurement area and determining the grid division size of the current measurement area; step S220, performing meshing on the current measurement area according to the meshing size to determine a plurality of assumed sound sources, and determining a target sound source of the current measurement area from the plurality of assumed sound sources; step S230, dividing a next measurement area with smaller size in the current test area according to the position of the target sound source in the current test area; and step S240, updating the next measurement area to the current measurement area to locate the target sound source of the next measurement area.
Illustratively, the processing unit 710 may also perform a sound source localization method as shown in fig. 3.
The storage unit 720 may include readable media in the form of volatile storage units, such as: a Random Access Memory (RAM) 7201 and/or a cache Memory 7202, and may further include a Read-Only Memory (ROM) 7203.
The storage unit 720 may also include a program/utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 700 may also communicate with one or more external devices 800 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 700, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 700 to communicate with one or more other computing devices. Such communication may be through an Input/Output (I/O) interface 750. Further, the I/O interface 750 is connected with the display unit 740 to transmit the content to be displayed to the display unit 740 through the I/O interface 750 for viewing by the user.
Further, electronic device 700 may communicate with one or more networks (e.g., a local Area Network (L) L AN), a Wide Area Network (WAN) and/or a public Network such as the Internet) via Network adapter 760 As shown, Network adapter 760 communicates with the other modules of electronic device 700 via bus 730.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (10)
1. A sound source localization method, characterized in that the method comprises:
for a current measurement area, determining the size of the current measurement area and determining the grid division size of the current measurement area;
performing meshing on the current measurement area according to the meshing size to determine a plurality of assumed sound sources, and determining a target sound source of the current measurement area from the plurality of assumed sound sources;
dividing a next measurement area with a smaller size in the current test area according to the position of the target sound source in the current test area;
and updating the next measurement area to the current measurement area so as to locate the target sound source of the next measurement area.
2. The sound source localization method according to claim 1, wherein determining the size of the current measurement area and the meshing size of the current measurement area comprises:
acquiring a first side length L and a second side length W of an inscribed rectangle of the current measurement area to obtain the size of the current measurement area, wherein L is greater than or equal to W, and L and W are positive numbers;
and obtaining that the mesh division size of the current measurement area in the first edge direction is L/n, the mesh division size of the current measurement area in the second edge direction is W/n, and n is positive integer.
3. The sound source localization method according to claim 1, wherein determining a target sound source of the current measurement area among the plurality of assumed sound sources comprises:
calculating a power of each of the assumed sound sources based on an acoustic array composed of a plurality of acoustic sensors;
and determining the assumed sound source with the maximum power as the target sound source of the current measuring area.
4. The sound source localization method of claim 3, wherein calculating the power of each of the assumed sound sources based on an acoustic array composed of a plurality of acoustic sensors comprises:
calculating a time delay between each acoustic sensor and a reference sensor for each assumed sound source, wherein the reference sensor is the acoustic sensor closest to the assumed sound source in the acoustic array;
and carrying out signal time shift on each acoustic sensor according to the time delay, and carrying out weighted summation to obtain the power of the assumed sound source.
5. The sound source localization method according to any one of claims 1 to 4, wherein cutting out a next measurement area with a smaller size in the current test area according to the position of the target sound source in the current test area comprises:
and determining the side length of the next measurement area according to the grid division size by taking the position of the target sound source in the current test area as the center of the next measurement area, and cutting the next measurement area in the current test area.
6. The sound source localization method according to claim 4, wherein updating the next measurement area to the current measurement area to localize a target sound source of the next measurement area comprises:
for the updated current measurement area, determining the grid division size of the updated current measurement area;
and according to the position of the target sound source in the updated current test area, dividing a next measurement area with a smaller size in the updated current test area.
7. The sound source localization method according to claim 4, wherein before the meshing the current measurement area according to the meshing size, the method further comprises:
judging whether the measurement precision corresponding to the current measurement area meets a preset precision requirement or not;
and if so, taking the target sound source of the current measurement area as a final sound source.
8. A sound source localization apparatus, characterized in that the apparatus comprises:
a size determination module configured to: for a current measurement area, determining the size of the current measurement area and determining the grid division size of the current measurement area;
a meshing module configured to: performing meshing on the current measurement area according to the meshing size to determine a plurality of assumed sound sources, and determining a target sound source of the current measurement area from the plurality of assumed sound sources;
a region segmentation module configured to: cutting a next measurement area with a smaller size in the current test area according to the position of the target sound source in the current test area;
an update module configured to: and updating the next measurement area to the current measurement area so as to locate the target sound source of the next measurement area.
9. A computer storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out a sound source localization method according to any one of claims 1 to 7.
10. An electronic device, characterized in that the electronic device comprises:
one or more processors;
storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out the sound source localization method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010220486.5A CN111443329A (en) | 2020-03-25 | 2020-03-25 | Sound source positioning method and device, computer storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010220486.5A CN111443329A (en) | 2020-03-25 | 2020-03-25 | Sound source positioning method and device, computer storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111443329A true CN111443329A (en) | 2020-07-24 |
Family
ID=71648787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010220486.5A Pending CN111443329A (en) | 2020-03-25 | 2020-03-25 | Sound source positioning method and device, computer storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111443329A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024077366A1 (en) * | 2022-10-11 | 2024-04-18 | Perkons S/A | System and method for detecting motor vehicle noise and corresponding computer-readable memory |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60146166A (en) * | 1984-01-11 | 1985-08-01 | Hitachi Ltd | Location of sound source position |
| JPH02102413A (en) * | 1988-10-07 | 1990-04-16 | Furuno Electric Co Ltd | Water bottom shape detector |
| US20070005977A1 (en) * | 2003-04-25 | 2007-01-04 | Oki Electric Industry Co., Ltd | Watermark information detection method |
| JP2008096137A (en) * | 2006-10-06 | 2008-04-24 | Mitsubishi Electric Corp | Radar device and angle measuring instrument |
| CN103983946A (en) * | 2014-05-23 | 2014-08-13 | 北京神州普惠科技股份有限公司 | Method for processing singles of multiple measuring channels in sound source localization process |
| CN104407328A (en) * | 2014-11-20 | 2015-03-11 | 西北工业大学 | Method and system for positioning sound source in enclosed space based on spatial pulse response matching |
| EP2976898A1 (en) * | 2013-03-19 | 2016-01-27 | Koninklijke Philips N.V. | Method and apparatus for determining a position of a microphone |
| CN105549077A (en) * | 2015-12-16 | 2016-05-04 | 中国矿业大学(北京) | Micro-earthquake epicenter positioning method calculated based on multilevel multi-scale grid similarity coefficient |
| CN105954795A (en) * | 2016-04-25 | 2016-09-21 | 吉林大学 | Grid successive dissection method used for microseismic positioning |
| CN106093864A (en) * | 2016-06-03 | 2016-11-09 | 清华大学 | A kind of microphone array sound source space real-time location method |
| CN106355893A (en) * | 2016-10-28 | 2017-01-25 | 东方智测（北京）科技有限公司 | Method and system for real-time positioning of whistling motor vehicle |
| CN106772591A (en) * | 2017-04-05 | 2017-05-31 | 吉林大学 | A kind of combined positioning-method suitable for improving microseism reliability of positioning |
| CN108120955A (en) * | 2017-12-04 | 2018-06-05 | 中国科学院深海科学与工程研究所 | A kind of method for long baseline acoustic positioning system Performance Evaluation |
| CN108761279A (en) * | 2018-03-23 | 2018-11-06 | 广东电网有限责任公司东莞供电局 | A kind of polar grid searching method and system for Partial Discharge Sources positioning |
| CN108802674A (en) * | 2018-07-19 | 2018-11-13 | 中国人民解放军战略支援部队信息工程大学 | It is a kind of for the combined method for searching and device that directly position |
| CN108828526A (en) * | 2018-06-25 | 2018-11-16 | 大连大学 | The method that expression of the signal S in space-frequency domain in more auditory localizations in two-dimensional grid has block sparsity |
| CN109709517A (en) * | 2018-12-10 | 2019-05-03 | 东南大学 | SRP-PHAT auditory localization trellis search method based on simulated annealing |
| CN109992640A (en) * | 2019-04-11 | 2019-07-09 | 北京百度网讯科技有限公司 | Determination method and device, equipment and the storage medium of position grid |
| CN110412505A (en) * | 2019-06-28 | 2019-11-05 | 同方电子科技有限公司 | A kind of quick positioning using TDOA trellis search method |
| CN110532342A (en) * | 2019-08-16 | 2019-12-03 | 南京王师大数据有限公司 | Global space target area position coding method and device |
| CN110850371A (en) * | 2019-11-28 | 2020-02-28 | 合肥工业大学 | High-resolution sound source positioning method based on Green function correction |
-
2020
- 2020-03-25 CN CN202010220486.5A patent/CN111443329A/en active Pending
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60146166A (en) * | 1984-01-11 | 1985-08-01 | Hitachi Ltd | Location of sound source position |
| JPH02102413A (en) * | 1988-10-07 | 1990-04-16 | Furuno Electric Co Ltd | Water bottom shape detector |
| US20070005977A1 (en) * | 2003-04-25 | 2007-01-04 | Oki Electric Industry Co., Ltd | Watermark information detection method |
| JP2008096137A (en) * | 2006-10-06 | 2008-04-24 | Mitsubishi Electric Corp | Radar device and angle measuring instrument |
| EP2976898A1 (en) * | 2013-03-19 | 2016-01-27 | Koninklijke Philips N.V. | Method and apparatus for determining a position of a microphone |
| CN103983946A (en) * | 2014-05-23 | 2014-08-13 | 北京神州普惠科技股份有限公司 | Method for processing singles of multiple measuring channels in sound source localization process |
| CN104407328A (en) * | 2014-11-20 | 2015-03-11 | 西北工业大学 | Method and system for positioning sound source in enclosed space based on spatial pulse response matching |
| CN105549077A (en) * | 2015-12-16 | 2016-05-04 | 中国矿业大学(北京) | Micro-earthquake epicenter positioning method calculated based on multilevel multi-scale grid similarity coefficient |
| CN105954795A (en) * | 2016-04-25 | 2016-09-21 | 吉林大学 | Grid successive dissection method used for microseismic positioning |
| CN106093864A (en) * | 2016-06-03 | 2016-11-09 | 清华大学 | A kind of microphone array sound source space real-time location method |
| CN106355893A (en) * | 2016-10-28 | 2017-01-25 | 东方智测（北京）科技有限公司 | Method and system for real-time positioning of whistling motor vehicle |
| CN106772591A (en) * | 2017-04-05 | 2017-05-31 | 吉林大学 | A kind of combined positioning-method suitable for improving microseism reliability of positioning |
| CN108120955A (en) * | 2017-12-04 | 2018-06-05 | 中国科学院深海科学与工程研究所 | A kind of method for long baseline acoustic positioning system Performance Evaluation |
| CN108761279A (en) * | 2018-03-23 | 2018-11-06 | 广东电网有限责任公司东莞供电局 | A kind of polar grid searching method and system for Partial Discharge Sources positioning |
| CN108828526A (en) * | 2018-06-25 | 2018-11-16 | 大连大学 | The method that expression of the signal S in space-frequency domain in more auditory localizations in two-dimensional grid has block sparsity |
| CN108802674A (en) * | 2018-07-19 | 2018-11-13 | 中国人民解放军战略支援部队信息工程大学 | It is a kind of for the combined method for searching and device that directly position |
| CN109709517A (en) * | 2018-12-10 | 2019-05-03 | 东南大学 | SRP-PHAT auditory localization trellis search method based on simulated annealing |
| CN109992640A (en) * | 2019-04-11 | 2019-07-09 | 北京百度网讯科技有限公司 | Determination method and device, equipment and the storage medium of position grid |
| CN110412505A (en) * | 2019-06-28 | 2019-11-05 | 同方电子科技有限公司 | A kind of quick positioning using TDOA trellis search method |
| CN110532342A (en) * | 2019-08-16 | 2019-12-03 | 南京王师大数据有限公司 | Global space target area position coding method and device |
| CN110850371A (en) * | 2019-11-28 | 2020-02-28 | 合肥工业大学 | High-resolution sound source positioning method based on Green function correction |
Non-Patent Citations (2)
| Title |
|---|
| 李焜 等: ""非合作水声脉冲信号的单水听器匹配场定位研究"", 《电子与信息学报》 * |
| 李焜 等: ""非合作水声脉冲信号的单水听器匹配场定位研究"", 《电子与信息学报》, 3 November 2012 (2012-11-03), pages 2541 - 2547 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024077366A1 (en) * | 2022-10-11 | 2024-04-18 | Perkons S/A | System and method for detecting motor vehicle noise and corresponding computer-readable memory |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR20200109230A (en) | Method and apparatus for generating neural network | |
| KR20190130636A (en) | Machine translation methods, devices, computer devices and storage media | |
| CN109783490B (en) | Data fusion method and device, computer equipment and storage medium | |
| WO2020207174A1 (en) | Method and apparatus for generating quantized neural network | |
| CN112364860A (en) | Training method and device of character recognition model and electronic equipment | |
| US11651198B2 (en) | Data processing method and apparatus for neural network | |
| US11769481B2 (en) | Unsupervised alignment for text to speech synthesis using neural networks | |
| CN111597825B (en) | Voice translation method and device, readable medium and electronic equipment | |
| US20210329373A1 (en) | Methods and apparatus to determine a location of an audio source | |
| CN109598344B (en) | Model generation method and device | |
| CN111443329A (en) | Sound source positioning method and device, computer storage medium and electronic equipment | |
| EP4226612A1 (en) | Quantization of tree-based machine learning models | |
| US20220246167A1 (en) | Speaker adaptive end of speech detection for conversational ai applications | |
| CN110009101B (en) | Method and apparatus for generating a quantized neural network | |
| CN116798027A (en) | Three-dimensional point cloud real-time cloud matching method and device based on multi-scale feature extraction | |
| CN111312224A (en) | Training method and device of voice segmentation model and electronic equipment | |
| CN113554149B (en) | Neural network processing unit NPU, neural network processing method and device | |
| US20220113943A1 (en) | Method for multiply-add operations for neural network | |
| CN111858916A (en) | Method and device for clustering sentences | |
| CN115272760A (en) | Small sample smoke image fine classification method suitable for forest fire smoke detection | |
| CN110222777B (en) | Image feature processing method and device, electronic equipment and storage medium | |
| CN113778078A (en) | Positioning information generation method and device, electronic equipment and computer readable medium | |
| CN111797263A (en) | Image label generation method, device, equipment and computer readable medium | |
| CN113361701A (en) | Quantification method and device of neural network model | |
| CN111368556B (en) | Performance determination method and confidence determination method and device of translation model |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200724 |