CN115865219A - Ultrasonic communication decoding method, ultrasonic communication encoding method and related device - Google Patents
Ultrasonic communication decoding method, ultrasonic communication encoding method and related device Download PDFInfo
- Publication number
- CN115865219A CN115865219A CN202211422555.6A CN202211422555A CN115865219A CN 115865219 A CN115865219 A CN 115865219A CN 202211422555 A CN202211422555 A CN 202211422555A CN 115865219 A CN115865219 A CN 115865219A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- bit
- coding
- data
- packet
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application provides an ultrasonic communication decoding method, an ultrasonic communication encoding method and a related device, wherein the decoding method comprises the following steps: framing the received ultrasonic signals, and extracting the frequency spectrum energy characteristics of each frame; the spectral energy characteristics of each frame are sent to a packet header detection model for classification, if the classification results of the continuous T frames are packet headers, the data packet is considered to be started, and if not, the detection is continued; if the data packet is detected to start, classifying subsequent data frames by adopting an ultrasonic coding classification model; for each data frame, the output of the ultrasonic coding classification model is M nodes corresponding to M ultrasonic frequency bands; and sequentially selecting the classification result of the frame with the maximum posterior probability from each ultrasonic coding bit interval as the decoding result of the coding bit. As the packet header detection and the bit decoding in the decoding process both adopt a classification method based on a model, the anti-interference performance of ultrasonic communication can be obviously improved, and the dependence on distance and equipment is reduced.
Description
Technical Field
The present invention relates to sound wave communication technologies, and in particular, to an ultrasound communication decoding method, an ultrasound communication encoding method, and related apparatuses.
Background
Acoustic communication is a Near Field Communication (NFC) scheme that has emerged in recent years, and is favored by electronic product developers due to its low cost and ease of deployment. Ultrasonic communication, in particular, is preferred due to its privacy. Ultrasonic communication employs a high-frequency carrier, frequency-encodes and then transmits data to be transmitted, and when decoding, a conventional method detects encoded information on each frequency band by a frequency domain energy threshold, thereby restoring the transmitted data. The traditional ultrasonic communication decoding method has the problems of weak anti-interference capability, limited transmission distance, equipment dependence and the like.
Disclosure of Invention
The invention aims to provide an ultrasonic communication decoding method, an ultrasonic communication encoding method and a related device, which can obviously improve the anti-interference performance of ultrasonic communication and reduce the dependence on distance and equipment.
The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
According to a first aspect of the present invention, there is provided an ultrasound communication decoding method for decoding an ultrasound encoded data packet composed of N encoded bits, wherein a packet header N 1 Bit, data n 2 Bit, check bit n 3 Bits, each encoded bit consisting of M ultrasound bands, the ultrasound communication decoding method comprising:
framing the received ultrasonic signals, and extracting the frequency spectrum energy characteristics of each frame;
the spectral energy characteristics of each frame are sent to a packet header detection model for classification, if the classification results of the continuous T frames are packet headers, the data packet is considered to be started, and if not, the detection is continued;
if the data packet is detected to start, classifying subsequent data frames by adopting an ultrasonic coding classification model;
for each data frame, the output of the ultrasonic coding classification model is M nodes corresponding to M ultrasonic frequency bands, if the output of one node is 1, the data frame contains the frequency band, otherwise, the data frame does not contain the frequency band;
and selecting the classification result of the frame with the maximum posterior probability from each ultrasonic coding bit interval in turn as the decoding result of the coding bit.
In one embodiment, the packet header detection model and the ultrasound coding classification model are deep learning models.
In one embodiment, the packet header detection model uses a lower complexity structure and a smaller step size than the ultrasound encoding classification model.
In one embodiment, the training data of the packet header detection model and the ultrasound coding classification model includes: the device comprises a plurality of transmission distances, a plurality of signal emission strengths, a plurality of types of transmitting and receiving devices, different receiving devices and relative orientations of the transmitting devices, and real collected data and simulated data in a plurality of noise environments.
In one embodiment, the extracting the spectral energy feature of each frame includes:
FFT processing is carried out on each frame signal, and the spectral energy characteristic F of each frequency band is extracted i ；
Only preserving spectral energy characteristics within a specific frequency band range;
using the spectral energy of a fixed-frequency ultrasonic signal as a reference F ref For spectral energy F of other frequency components i Normalization is performed, and the formula is as follows:
wherein: f ref I is the spectral energy of the reference band, i is the band number;
extracting normalized spectral energy features
As the frequency spectrum of the frameEnergy characteristics.
In one embodiment, when no interval bit is set between the encoding bits of the ultrasonic encoding data packet, each encoding bit interval is determined by taking the detected position of the packet header as a reference;
when interval bits are arranged between the coding bits of the ultrasonic coding data packet, the interval bits are detected through an ultrasonic coding classification model to distinguish different coding bits.
According to a second aspect of the present invention, there is provided an ultrasound communication encoding method, comprising:
dividing the frequency band of each coding bit into M sub-bands, coding a symbol by taking each M sub-bands as a group, wherein M is less than or equal to M;
combining the N coding bits into an ultrasonic coding data packet, wherein the packet head N 1 Bit, data n 2 Bit, check bit n 3 A bit.
In one embodiment, the first subband of each coded bit is a null subband separating groups of subbands.
According to a third aspect of the present invention, there is provided an ultrasonic communication decoding apparatus comprising:
a receiving module for receiving the ultrasonic coding data packet, wherein the ultrasonic coding data packet is composed of N coding bits, and the packet head N 1 Bit, data n 2 Bit, check bit n 3 Bits, each coded bit consisting of M ultrasound bands;
the characteristic extraction module is used for framing the received ultrasonic signals and extracting the frequency spectrum energy characteristic of each frame;
the packet head detection module is used for sending the spectral energy characteristics of each frame into the packet head detection model for classification, if the classification results of the continuous T frames are packet heads, the data packet is considered to be started, and if not, the detection is continued;
the bit decoding module is used for classifying subsequent data frames by adopting an ultrasonic coding classification model when the beginning of a data packet is detected; the output of each data frame ultrasonic coding classification model is M nodes corresponding to M ultrasonic frequency bands; if the output of one node is 1, the data frame contains the frequency band, otherwise, the data frame does not contain the frequency band; and selecting a frame result with the maximum classification probability from each ultrasonic coding bit interval in turn as a decoding result of the coding bit.
According to a fourth aspect of the present invention, there is provided an ultrasonic communication encoding apparatus comprising:
the encoding module is used for generating an ultrasonic encoding data packet, the frequency band of each encoding bit of the ultrasonic encoding data packet is divided into M sub-bands, each M sub-band is used as a group to encode a symbol, M is less than or equal to M, N encoding bits form the ultrasonic encoding data packet, and the packet head N 1 Bit, data n 2 Bit, check bit n 3 A bit;
and the transmitting module is used for transmitting the ultrasonic coded data packet.
The embodiment of the invention has the beneficial effects that: in the decoding process, both packet header detection and bit decoding adopt a classification method based on a model, so that the anti-interference performance of ultrasonic communication can be obviously improved, and the dependence on distance and equipment is reduced. The encoding process may support parallel encoding and may encode multiple symbols with one encoded bit.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
The above features and advantages of the present disclosure will be better understood upon reading the detailed description of embodiments of the disclosure in conjunction with the following drawings. In the drawings, components are not necessarily drawn to scale, and components having similar relative characteristics or features may have the same or similar reference numerals.
FIG. 1 is a flowchart of a decoding method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of the encoding principle of the embodiment of the present application;
FIG. 3 is a schematic diagram of an encoded ultrasonic spectrum;
FIG. 4 is a block diagram of a decoding apparatus according to an embodiment of the present application;
fig. 5 is a block diagram of an encoding apparatus according to an embodiment of the present application.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. It is noted that the aspects described below in connection with the figures and the specific embodiments are only exemplary and should not be construed as imposing any limitation on the scope of the present invention.
As shown in fig. 1, an embodiment of the present application provides an ultrasound communication decoding method for decoding an ultrasound encoded data packet, where the ultrasound encoded data packet is composed of N encoded bits, where a packet header N is included 1 Bit, data n 2 Bit, check bit n 3 Bits, each encoded bit consisting of M ultrasound bands, the ultrasound communication decoding method comprising:
and framing the received ultrasonic signals, and extracting the spectral energy characteristics of each frame. First, FFT (fast fourier transform) processing is performed on each frame signal to extract spectral energy characteristics of each frequency band. Only the spectral energy characteristic in a specific frequency band, typically 16kHz to 24kHz, is then retained. For example, if the ultrasound encoded data packet is signal encoded using the 16kHz-18kHz band, only the spectral energy features that remain between 16kHz-18kHz are extracted here. Then using the spectrum energy of a fixed frequency ultrasonic signal as a reference, and using the spectrum energy F of other frequency components i Normalization is performed, and the formula is as follows:
wherein: f ref Is the spectral energy of the reference band.
And extracting the normalized spectral energy characteristic as the spectral energy characteristic of the frame. And sending the spectral energy characteristics of each frame into a packet header detection model for classification. If the packet header is received, outputting 1; otherwise, outputting 0; if the classification results of the continuous T frames are all packet headers, the data packet is considered to start, otherwise, the detection is continued.
If the beginning of the data packet is detected, an ultrasonic coding classification model is adopted to classify the subsequent data frames.
For each data frame, the output of the ultrasonic coding classification model is M nodes, corresponding to M ultrasonic frequency bands, if the output of one node is 1, the data frame contains the frequency band, otherwise, the data frame does not contain the frequency band. In other words, the classification model is in frames, and each frame data model outputs M0/1 values, and the M0/1 values represent one code symbol.
And sequentially selecting the classification result of the frame with the maximum posterior probability from each ultrasonic coding bit interval as the decoding result of the coding bit.
Fig. 2 is a schematic diagram of a code, wherein f1 and f2 represent two different frequency components, respectively, and the horizontal axis represents time, the time and duration of the occurrence of the frequency component, thereby representing different information, and the lowest represented 0/1 information bit. Fig. 3 shows a spectrum of an encoded ultrasonic wave.
Preferably, the packet header detection model and the ultrasound coding classification model used in the method are deep learning models, for example, a basic DNN/CNN + DNN structure model, an encoder/decoder structure model, or a model with a more complex structure may be used, and may be specifically selected according to the computational power of a deployment platform, the complexity of an application environment, and the like. The packet head detection model should adopt a lower complexity structure and a smaller step size than the ultrasonic coding classification model.
The packet header detection model and the ultrasonic coding classification model are trained in advance, and training data comprise: the system comprises a plurality of transmission distances, a plurality of signal transmitting strengths, a plurality of types of transmitting and receiving devices, different relative orientations of the receiving devices and the transmitting devices, and a large amount of real collected data and analog data in a plurality of noise environments, so that the passing interference resistance is improved.
In the method, when no interval bit is set between coding bits of the ultrasonic coding data packet, each coding bit interval is determined by taking the detected position of a packet header as a reference; when interval bits are arranged among the coding bits of the ultrasonic coding data packet, the interval bits are detected through an ultrasonic coding classification model to distinguish different coding bits, an inter-code interval is equivalent to an area with zero energy of all ultrasonic frequency bands, and M nodes output by the model are all 0.
One specific decoding example is provided below:
each coding bit of the ultrasonic coding data packet codes a symbol, the time length is 0.04s, the coding bit consists of 8 frequency sub-bands, the frequency band of 16kHz-18kHz is adopted for signal coding, the data packet head consists of 1 bit, the data bit is 8 bits, the CRC check bit is 1 bit, and the received ultrasonic signal is sampled at 48 kHz.
Firstly, performing framing processing, wherein the frame length is 1024, and the frame shift is 256; then, FFT processing is carried out on each frame of signal, and the spectral energy characteristic of each frequency band is extracted; only the spectral energy characteristics between 16000Hz and 18000Hz are reserved; adopting the spectral energy of the frequency band (frequency band number: 345) nearest to 16200Hz to normalize the energy of all the spectral energy characteristics, and extracting the spectral energy characteristics between 16200Hz and 18000Hz as the final characteristics; sending the characteristics into a pre-trained packet header detection model, wherein the step length is 256, and if 3 continuous frames are detected as packet headers, starting to receive data; otherwise, continuing to detect; with the 2 nd frame of the detected packet header as a reference, respectively stepping forward by 7+8 × i frames (i = 0.. Once, 8, which is the number of encoding bits), and sending the corresponding frame characteristics to an ultrasonic encoding classification model to obtain a symbol encoding and check bit corresponding to each data bit; and performing CRC to confirm that the data is correct and outputting a corresponding coding symbol.
In the above embodiment, after the FFT, the band energy between numbers 343 to 383 is extracted, corresponding to the ultrasonic energy feature between 16100Hz and 18000Hz, to extract 41-dimensional spectral energy features in total, the packet header detection model adopts a 4-layer DNN model of 16 × 8 × 2, and the ultrasonic coding classification model adopts a 2-layer 2D-CNN + 2-layer DNN structure.
As shown in fig. 2 and fig. 3, an embodiment of the present application further provides an ultrasound communication encoding method, including:
dividing the frequency band of each coding bit into M sub-bands, coding a symbol by taking each M sub-bands as a group, wherein M is less than or equal to M;
combining the N coding bits into an ultrasonic coding data packet, wherein the packet head N 1 Bit, data n 2 Bit, check bit n 3 A bit.
The first subband of each coded bit is a null subband separating groups of subbands.
One specific example of encoding is provided below:
the frequency band of 16 kHz-24 kHz is evenly divided into 40 sub-bands at intervals of 200Hz, and each 10 sub-bands encode a symbol in a group. The 10 subband functions are assigned as follows: setting the starting frequency as f, and setting the 1 st sub-band as a null sub-band for separating sub-band groups; the 2 nd sub-band has the center frequency of (f + 400) Hz and contains an ultrasonic signal with the frequency of (f + 400) Hz which is used as a sub-band energy reference; the 3 rd to 10 th subband center frequencies are respectively (f + 600) Hz, ·, and (f + 2000) Hz, and sequentially correspond to 8-bit binary codes of one character, and if the binary codes are 1, the subband center frequency signals are included; if the binary code is 0, the subband frequency signal is not included. Thus, 4 characters can be encoded in one encoded bit, and at the time of decoding, the corresponding band sections can be sequentially divided according to the preset subband grouping, and then bit decoding is performed.
The sub-bands in a frequency band may or may not be uniformly spaced. In another embodiment, the 16 kHz-24 kHz band is divided non-uniformly into 40 sub-bands at variable intervals, with each 10 sub-band encoding a symbol for a group.
As shown in fig. 4, an embodiment of the present application provides an ultrasonic communication decoding apparatus 300, including:
a receiving module 301, configured to receive an ultrasound encoded data packet, where the ultrasound encoded data packet is composed of N encoded bits, and a packet header N 1 Bit, data n 2 Bit, check bit n 3 Bits, each coded bit consisting of M ultrasound bands. The receiving module 301 may be a receiving device such as a microphone.
A feature extraction module 302, configured to perform framing on the received ultrasonic signal, and extract a spectral energy feature of each frame;
a packet header detection module 303, configured to send the spectral energy characteristic of each frame to a packet header detection model for classification, and if the classification results of consecutive T frames are packet headers, consider that a data packet starts, otherwise, continue to detect;
a bit decoding module 304, configured to classify subsequent data frames by using an ultrasound coding classification model when a start of a data packet is detected; the output of each data frame ultrasonic coding classification model is M nodes corresponding to M ultrasonic frequency bands; if the output of one node is 1, the data frame contains the frequency band, otherwise, the data frame does not contain the frequency band; and selecting the result of one frame with the maximum classification probability from each ultrasonic coding bit interval in turn as the decoding result of the coding bit.
The feature extraction module 302, the packet header detection module 303 and the bit decoding module 304 may be integrated in the form of software in the processor.
As shown in fig. 5, an embodiment of the present application further provides an ultrasound communication encoding apparatus 400, including:
an encoding module 401, configured to generate an ultrasound encoded data packet, where a frequency band of each encoded bit of the ultrasound encoded data packet is divided into M subbands, each M subbands is used as a group to encode one symbol, M is equal to or less than M, N encoded bits constitute the ultrasound encoded data packet, and a packet header N is included in the ultrasound encoded data packet 1 Bit, data n 2 Bit, check bit n 3 A bit. The encoding module 401 may be integrated in the processor in the form of software.
A transmitting module 402, configured to transmit the ultrasound encoded data packet. The emitting module 402 may be a speaker or an ultrasonic generator, etc.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The above description is only a preferred example of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. An ultrasonic communication decoding method for decoding ultrasonic coded data packet, characterized in that the ultrasonic coded data packet is composed of N bit coded bits, wherein the packet head N 1 Bit, data n 2 Bit, check bit n 3 Bits, each encoded bit consisting of M ultrasound bands, the ultrasound communication decoding method comprising:
framing the received ultrasonic signals, and extracting the frequency spectrum energy characteristics of each frame;
the spectral energy characteristics of each frame are sent to a packet header detection model for classification, if the classification results of the continuous T frames are packet headers, the data packet is considered to be started, and if not, the detection is continued;
if the data packet is detected to start, classifying subsequent data frames by adopting an ultrasonic coding classification model;
for each data frame, the output of the ultrasonic coding classification model is M nodes corresponding to M ultrasonic frequency bands, if the output of one node is 1, the data frame contains the frequency band, otherwise, the data frame does not contain the frequency band;
and selecting the classification result of the frame with the maximum posterior probability from each ultrasonic coding bit interval in turn as the decoding result of the coding bit.
2. The ultrasonic communication decoding method according to claim 1, wherein: the packet header detection model and the ultrasonic coding classification model are deep learning models.
3. The ultrasonic communication decoding method according to claim 2, characterized in that: compared with an ultrasonic coding classification model, the packet header detection model adopts a lower complexity structure and a smaller step size.
4. The ultrasonic communication decoding method according to claim 2, wherein the training data of the packet header detection model and the ultrasonic coding classification model comprises: the device comprises a plurality of transmission distances, a plurality of signal emission strengths, a plurality of types of transmitting and receiving devices, different receiving devices and relative orientations of the transmitting devices, and real collected data and simulated data in a plurality of noise environments.
5. The method of decoding ultrasound communication according to claim 1, wherein said extracting spectral energy features of each frame comprises:
FFT processing is carried out on each frame signal, and the spectral energy characteristic F of each frequency band is extracted i ；
Only preserving spectral energy characteristics within a specific frequency band range;
using the spectral energy of a fixed-frequency ultrasonic signal as a reference F ref For spectral energy F of other frequency components i Normalization is performed, and the formula is as follows:
wherein: f ref I is the spectral energy of the reference band, i is the band number;
extracting normalized spectral energy features
As a spectral energy characteristic of the frame.
6. The ultrasonic communication decoding method according to claim 1, wherein:
when no interval bit is set between the coding bits of the ultrasonic coding data packet, determining each coding bit interval by taking the detected packet head position as a reference;
when interval bits are arranged between the coding bits of the ultrasonic coding data packet, the interval bits are detected through an ultrasonic coding classification model to distinguish different coding bits.
7. An ultrasound communication encoding method, characterized by:
dividing the frequency band of each coding bit into M sub-bands, coding a symbol by taking each M sub-bands as a group, wherein M is less than or equal to M;
the N coding bits are combined into an ultrasonic coding data packet, wherein the packet head N 1 Bit, data n 2 Bit, check bit n 3 A bit.
8. The ultrasound communication encoding method of claim 7, wherein: the first subband of each coded bit is a null subband separating groups of subbands.
9. An ultrasonic communication decoding apparatus comprising:
a receiving module for receiving the ultrasonic coding data packet, wherein the ultrasonic coding data packet is composed of N coding bits, and the packet head N 1 Bit, data n 2 Bit, check bit n 3 Bits, each coded bit consisting of M ultrasound bands;
the characteristic extraction module is used for framing the received ultrasonic signals and extracting the frequency spectrum energy characteristic of each frame;
the packet header detection module is used for sending the spectral energy characteristics of each frame into the packet header detection model for classification, if the classification results of the continuous T frames are all packet headers, the data packet is considered to start, and if not, the detection is continued;
the bit decoding module is used for classifying subsequent data frames by adopting an ultrasonic coding classification model when the beginning of a data packet is detected; the output of each data frame ultrasonic coding classification model is M nodes corresponding to M ultrasonic frequency bands; if the output of one node is 1, the data frame contains the frequency band, otherwise, the data frame does not contain the frequency band; and selecting a frame result with the maximum classification probability from each ultrasonic coding bit interval in turn as a decoding result of the coding bit.
10. An ultrasound communication encoding apparatus comprising:
the encoding module is used for generating an ultrasonic encoding data packet, the frequency band of each encoding bit of the ultrasonic encoding data packet is divided into M sub-bands, each M sub-band is used as a group to encode a symbol, M is less than or equal to M, N encoding bits form the ultrasonic encoding data packet, and the packet head N 1 Bit, data n 2 Bit, check bit n 3 A bit;
and the transmitting module is used for transmitting the ultrasonic coded data packet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211422555.6A CN115865219A (en) | 2022-11-15 | 2022-11-15 | Ultrasonic communication decoding method, ultrasonic communication encoding method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211422555.6A CN115865219A (en) | 2022-11-15 | 2022-11-15 | Ultrasonic communication decoding method, ultrasonic communication encoding method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115865219A true CN115865219A (en) | 2023-03-28 |
Family
ID=85663389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211422555.6A Pending CN115865219A (en) | 2022-11-15 | 2022-11-15 | Ultrasonic communication decoding method, ultrasonic communication encoding method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115865219A (en) |
-
2022
- 2022-11-15 CN CN202211422555.6A patent/CN115865219A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Weng et al. | Semantic communication systems for speech transmission | |
| CN1306472C (en) | System and method for transmitting speech activity in a distributed voice recognition system | |
| US8942298B2 (en) | Data communications | |
| CN109347568B (en) | Dolphin whistle-imitating continuous phase multi-element frequency modulation underwater acoustic communication method | |
| LaDue et al. | A data modem for GSM voice channel | |
| CN103971695B (en) | A kind of underwater digital voice communication system of channel self-adapting and its method | |
| Ahani et al. | A sparse representation-based wavelet domain speech steganography method | |
| JP4875249B2 (en) | Automatic speech recognition execution method | |
| WO2012089288A1 (en) | Method and system for robust audio hashing | |
| CN103368660A (en) | Differential pattern time delay shift coding-based bionic underwater sound communication method | |
| CN102870155A (en) | Method and apparatus for processing an audio signal | |
| CN106899357B (en) | Disguised and concealed underwater communication device simulating dolphin whistle | |
| Li et al. | Blind detection of underwater acoustic communication signals based on deep learning | |
| CN105391708A (en) | Audio data detection method and device | |
| CN105448302A (en) | Environment adaptive type voice reverberation elimination method and system | |
| CN1447963A (en) | Method for noise robust classification in speech coding | |
| CN112183582A (en) | Multi-feature fusion underwater target identification method | |
| CN113707160A (en) | Echo delay determination method, device, equipment and storage medium | |
| EP4102500A1 (en) | System and method for robust wakeword detection in presence of noise in new unseen environments without additional data | |
| CN113300993A (en) | Transmission method for bit field superposition pseudo-random sequence and sparse cascade coding | |
| CN103456307B (en) | In audio decoder, the spectrum of frame error concealment replaces method and system | |
| CN111246469A (en) | Artificial intelligence secret communication system and communication method | |
| CN112992189B (en) | Voice audio detection method and device, storage medium and electronic device | |
| CN115865219A (en) | Ultrasonic communication decoding method, ultrasonic communication encoding method and related device | |
| CN1592161A (en) | M-ary spread spectrum communication method |
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 |