CN115831131A - Deep learning-based audio watermark embedding and extracting method - Google Patents
Deep learning-based audio watermark embedding and extracting method Download PDFInfo
- Publication number
- CN115831131A CN115831131A CN202310056386.7A CN202310056386A CN115831131A CN 115831131 A CN115831131 A CN 115831131A CN 202310056386 A CN202310056386 A CN 202310056386A CN 115831131 A CN115831131 A CN 115831131A
- Authority
- CN
- China
- Prior art keywords
- audio
- watermark
- decoder
- embedding
- encoder
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000013135 deep learning Methods 0.000 title claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 15
- 230000002708 enhancing effect Effects 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 6
- 239000000654 additive Substances 0.000 claims description 3
- 230000000996 additive effect Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 2
- 239000000969 carrier Substances 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000012952 Resampling Methods 0.000 abstract description 4
- 230000006835 compression Effects 0.000 abstract description 4
- 238000007906 compression Methods 0.000 abstract description 4
- 238000012360 testing method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses an audio watermark embedding and extracting method based on deep learning, which comprises the steps of firstly, embedding watermark information into carrier audio by utilizing an encoder to obtain audio containing watermarks; before the audio containing the watermark is input into a decoder, a distortion layer is inserted between the encoder and the decoder for enhancing the robustness of the audio dubbing process; the audio containing the watermark after the distortion layer is input to a decoder, and watermark information in the audio is extracted by the decoder. The method can extract the watermark information after the watermark is embedded into the target audio frequency and the target audio frequency is subjected to distortion such as noise adding, filtering, compression, resampling, requantization, dubbing and the like, thereby realizing the purposes of audio frequency divulgence and tracing and copyright protection.
Description
Technical Field
The invention relates to the technical field of digital watermarks, in particular to an audio watermark embedding and extracting method based on deep learning.
Background
Digital watermarking has been widely studied for many years as an effective method of tracking the source of leakage and copyright protection. The two most important attributes that an audio watermark should satisfy are fidelity, which ensures normal use of watermarked audio, and robustness, which ensures that the embedded watermark can be extracted without loss even if the audio is subject to distortion (MPEG encoding, noise addition, audio re-recording, etc.). Most conventional audio watermarking methods focus on the robustness of digital distortion in the electronic channel, since most audio reproduction occurs in the digital channel. However, with the miniaturization of recording devices, audio Re-recording (AR) has become a more convenient and efficient way to copy Audio, when Audio is used as a carrier for information transmission, for many important confidential Audio information (litigation recording, forensic Audio) and paid Audio piracy (network classroom Audio, movie piracy), since the dubbing can effectively retain Audio content and significantly destroy embedded watermark signals, by means of the dubbing, an attacker can easily and covertly perform Audio content information stealing and cannot leave evidence easily, as shown in fig. 1, which is a schematic diagram of leaked information in the prior art for dubbing operation, how to maintain robustness under a complex scene is one of the greatest challenges for Audio watermarking, and it is ensured that robustness to dubbing becomes a critical task for Audio watermarking at present.
At present, the field of audio watermark research still mainly uses a traditional mathematical algorithm to try to find features which are unchanged before and after distortion to embed the watermark, and most of the used features are in a transform domain, for example, the transform domain features of audio are obtained by using audio frequency domain conversion methods such as Discrete Cosine Transform (DCT), discrete Wavelet Transform (DWT), fast Fourier Transform (FFT) and the like. However, due to the complexity of the dubbing process itself, it is a very difficult task to quantitatively and finely analyze the distortion and find robust and invariant features in the process, and thus none of the prior art algorithms is very resistant to dubbing distortion.
Disclosure of Invention
The invention aims to provide an audio watermark embedding and extracting method based on deep learning, which can extract watermark information in a target audio after the watermark is embedded into the target audio and the target audio is subjected to distortion such as noise adding, filtering, compression, resampling, requantization, dubbing and the like, thereby realizing the purposes of audio leakage tracing and copyright protection.
The purpose of the invention is realized by the following technical scheme:
a method of deep learning based audio watermark embedding extraction, the method comprising:
step 1, embedding watermark information into carrier audio by using an encoder to obtain audio containing a watermark;
step 2, before the audio containing the watermark is input into a decoder, a distortion layer is inserted between the encoder and the decoder for enhancing the robustness of the audio copying process;
and 3, inputting the audio containing the watermark after the distortion layer into a decoder, and extracting the watermark information by the decoder.
According to the technical scheme provided by the invention, after the watermark is embedded into the target audio, the watermark information in the target audio can still be extracted after the target audio is subjected to distortion such as noise addition, filtering, compression, resampling, requantization, dubbing and the like, so that the aims of audio leakage tracing and copyright protection are fulfilled.
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 description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic diagram of a dubbing operation on leaked information in the prior art.
Fig. 2 is a flowchart of a method for embedding and extracting an audio watermark based on deep learning according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments, and this does not limit the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
Embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. Details which are not described in detail in the embodiments of the invention belong to the prior art which is known to the person skilled in the art. Those not specifically mentioned in the examples of the present invention were carried out according to the conventional conditions in the art or conditions suggested by the manufacturer. The reagents or instruments used in the examples of the present invention are not specified by manufacturers, and are all conventional products available by commercial purchase.
Fig. 2 is a schematic flow chart of a method for embedding and extracting an audio watermark based on deep learning according to an embodiment of the present invention, where the method includes:
step 1, embedding watermark information into a carrier audio by using an encoder to obtain an audio containing a watermark;
in this step, in step 1, with
To express a length of
The mono original carrier audio; first by differentiable Discrete wavelet transform (Discrete)Wavelet Transform, DWT) to convert the original carrier audio
Transferring to frequency domain to obtain corresponding approximate coefficient
And detail coefficient
Namely:
wherein the approximation coefficient
And detail coefficient
Is the original carrier audio
Is one half, i.e.
；
Inspired by traditional audio watermarking, watermarking information
Embedding into original carrier audio
In low frequencies, i.e. using approximation coefficients
As carriers of watermark information while preserving detail coefficients
For subsequent audio reconstruction;
the encoder is used for encoding watermark information
Is embedded into
As shown in fig. 2, the encoder En generates a residual R and marks it further to
Thereby generating approximate coefficients containing the watermark
Namely:
wherein 
Is an intensity factor, set to 1 by default; en (.) denotes encoder processing.
In addition, to meet fidelity requirements, approximate coefficients containing watermarks are used
As far as possible identical to the original
Keeping the same introduces a fundamental loss in the encoder training
By mean square error
As
Namely:
wherein i represents an index number;
represents the ith approximation coefficient;
representing the ith watermarked approximation coefficient;
to further improve fidelity and minimize
And
the domain gap between them, an additional discriminator D is introduced for forming a countertrain with the encoder, to counter the loss
For better embedding of watermark information by the encoder, making it indistinguishable by the discriminator
And
thereby minimizing
And
the domain gap between, namely:
where D (.) represents discriminator processing.
Step 2, before the audio containing the watermark is input into a decoder, a distortion layer is inserted between the encoder and the decoder for enhancing the robustness of the audio copying process;
in this step, it is essential to make the distortion layer differentiable, which can prevent the gradient interruption in the end-to-end learning process, however, the dubbing process is a complicated non-differential process, so the inserted distortion layer is set to the differential audio re-recording operation DAR, including ambient reverberation, band-pass filtering and gaussian noise; in a specific implementation, in order to realize robustness to dubbing, a dubbing process is analyzed from the influence of sound propagation in the air and the processing of a microphone and a loudspeaker; based on the analysis, the present example elaborately models transcription distortion through several differential operations (ambient reverberation, band-pass filtering and gaussian noise) and uses these as distortion layers with the proposed framework;
DAR cannot be applied directly to approximate coefficients containing watermarks, since it is a process running in the time domain
Therefore, inverse DWT (Inverse Discrete Wavelet Transform) is used to watermark the approximate coefficients
And corresponding detail coefficients
Transforming back watermarked audio
Namely:
wherein the ambient reverberation is specifically:
the impulse response is the reaction of the environment upon receipt of a brief input signal, describing the acoustic properties of the environment, in particular the spatial reverberation behavior, and reproduces the reverberation in the environment by convolution, collecting different basic impulse responses from different microphones, room environments and loudspeakers to form a set
Given a target audio
From the set
In which a basic impulse response is randomly selected
And by aggregation
For target audio
Performing convolution
Operate to simulate the ambient reverberation ER (), namely:
the band-pass filtering specifically comprises:
since the frequency band of human hearing is limited, the widely used normal frequency range is 500Hz to 2000 Hz, based on which the commonly used speaker does not play audio with too high or too low frequency band, while the microphone also processes the played audio, usually by cutting off the frequency band outside the normal range to reduce noise, i.e. a basic noise removal process, so that the audio with watermark is processed in order to simulate the distortion caused by the inherent characteristics of the speaker and microphone
Using band-pass filtering
Operation, given target Audio
Is carried out as follows
：
wherein 
And
respectively representing low-pass filtering and high-pass filtering;
and
to represent
And
a corresponding threshold value;
the gaussian noise is specifically:
in addition to the above two components, the random noise caused by uncertain factors in the dubbing process is simulated by introducing gaussian noise, which is an additive noise and widely used in the current automatic speech recognition scheme to enhance the robustness to the random environmental noise, specifically by directly superposing the gaussian noise
At the target audio
To implement additive Gaussian noise operation
Namely:
wherein ,
representing gaussian noise;
represents a mean of 0 and a variance of
A gaussian distribution of (a).
And 3, inputting the audio containing the watermark after the distortion layer into a decoder, and extracting the watermark information by the decoder.
In this step, the processing procedure of the distortion layer DAR is as follows:
for audio with watermark
Finally, the audio containing the watermark after being subjected to the DAR processing of the distortion layer is obtained
Namely:
obtaining the same by Discrete Wavelet Transform (DWT)
Corresponding approximation coefficient
And detail coefficient
And combining the approximation coefficients
Input to a decoder De, the watermark being extracted by the decoder De
Namely:
where De (.) denotes decoder processing.
In a specific implementation, watermark loss is further introduced
I.e. watermark information
And watermark extracted by decoder
Mean Square Error loss MSE (Mean Square Error) between, i.e.:
when using binary watermarking
Rather than to
This is more advantageous for model watermark embedding and extraction, in this case for watermarked audio
Watermark extracted by decoder
Should be as close as possible to-1 and 1; for audio without watermarks, watermarks extracted by the decoder
The distribution should be close to 0, which helps the MSE based constraint work.
It is noted that those skilled in the art will recognize that the embodiments of the present invention described in detail herein are not limited to the embodiments of the present invention described in detail herein.
To illustrate the effects of the embodiments of the present invention, the following experiments are described in detail:
1) Fidelity test
First, the fidelity of the method described in the present application was compared to the existing baseline method, and as shown in table 1, the method achieved an SNR of 25.86, which is superior to the existing baseline method.
Table 1 quantitative comparison with baseline method
| Index (I) | Method for producing a composite material | Base line 1 | Base line 2 |
| SNR(dB) | 25.86 | 25.81 | 24.94 |
| ACC(%) | 99.18 | 77.09 | 56.0 |
2) Robustness testing for audio dubbing
The robustness of the audio re-recording was compared in this experiment and quantitative results are provided in table 2, with the method being significantly better than the baseline method (over 20% and 40%, respectively) at comparable fidelity. In addition to the default distance (5 cm), further control comparisons were made with the baseline method under different conditions. As shown in table 2, the method described in the embodiment of the present application performs better over a wide range of distances, and as the distance increases, the robustness to dubbing decreases accordingly, but is still acceptable (both above 90%).
TABLE 2 comparison of robustness of dubbing at different distances
| Distance (cm) | 5 | 20 | 50 | 100 |
| Method for producing a composite material | 99.18 | 98.55 | 93.40 | 92.68 |
| Base line 1 | 77.09 | 82.64 | 74.76 | 66.02 |
3) Robustness testing for other common distortions
To compare robustness more fully, further evaluations were made at other common distortions in the digital transmission process, namely gaussian noise at different signal-to-noise ratios (20 dB, 30 dB, 40 dB, 50 dB), MP3 compression (64 kbps, 128 kbps), bandpass (1 kHz high pass, 4 kHz), resampling, clipping, amplitude modification, re-quantization and median filtering. As shown in table 3, the method employed in the present application is robust against all types of distortions.
TABLE 3 robustness to other common distortions, ACC Default/enhanced version
The above experimental results show that: the method of the embodiment of the invention can automatically realize the embedding of the audio watermark and the robust extraction under various distortions, and can achieve higher extraction accuracy rate compared with the prior method.
In summary, after the watermark information is embedded in the Audio, the method according to the embodiment of the present invention can implement robust extraction on the watermark in a common Audio processing distortion scene, a watermark attack scene, and recording (AR) distortion, thereby implementing the purposes of divulgence and tracing to the source and copyright protection.
In addition, it is understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by using a program to instruct the relevant hardware to implement, and the corresponding program may be stored in a computer-readable storage medium, where the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims. The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Claims (6)
1. A method for deep learning-based audio watermark embedding and extraction is characterized in that the method comprises the following steps:
step 1, embedding watermark information into carrier audio by using an encoder to obtain audio containing a watermark;
step 2, before the audio containing the watermark is input into a decoder, a distortion layer is inserted between the encoder and the decoder for enhancing the robustness of the audio copying process;
and 3, inputting the audio containing the watermark after the distortion layer into a decoder, and extracting the watermark information by the decoder.
2. The method for embedding and extracting audio watermark based on deep learning of claim 1, wherein in step 1, the method uses
To express a length of
The mono original carrier audio; first by differentiable discrete wavelet transform
Audio of original carrier
Transferring to frequency domain to obtain corresponding approximate coefficient
And detail coefficient
Namely:
wherein the approximation coefficient
And detail coefficient
Is the original carrier audio
Is one half, i.e.
；
Watermarking information
Embedding into original carrier audio
In low frequencies, i.e. using approximation coefficients
As carriers of watermark information while preserving detail coefficients
For subsequent audio reconstruction;
the encoder is used for encoding watermark information
Is embedded into
In particular: the encoder generates a residual and marks it further to
Thereby generating approximate coefficients containing the watermark
Namely:
wherein 
Is an intensity factor, set to 1 by default; en () denotes encoder processing.
3. The method for deep learning based audio watermark embedding extraction as claimed in claim 2, wherein, in step 1,
in order to approximate the coefficients with the watermark
As far as possible identical to the original
Keeping the same introduces a fundamental loss in the encoder training
By mean square error
As
Namely:
wherein i represents an index number;
represents the ith approximation coefficient;
representing the ith watermarked approximation coefficient;
to minimize
And
the field gap between them, an additional discriminator is introduced for forming a countertraining with the encoder, to counter the loss
For better embedding of watermark information by the encoder, making it indistinguishable by the discriminator
And
thereby minimizing
And
the domain gap between, namely:
where D (.) represents discriminator processing.
4. The method for deep learning based audio watermark embedding extraction as claimed in claim 3, wherein in step 2, the inserted distortion layer is a difference audio re-recording operation DAR comprising ambient reverberation, band-pass filtering and Gaussian noise;
DAR cannot be applied directly to approximate coefficients containing watermarks, since it is a process running in the time domain
Therefore, the approximate coefficients of the watermark will be contained using the inverse DWT, i.e. IDWT
And the corresponding detailsNumber of
Transforming back watermarked audio
Namely:
wherein the ambient reverberation is specifically:
the impulse response reproduces reverberation in the environment by convolution, collecting different base impulse responses from different microphones, room environments and loudspeakers to form a set
Given a target audio
From the set
In which a basic impulse response is randomly selected
And by aggregation
For target audio
Performing convolution
Operate to simulate the ambient reverberation ER (), namely:
the band-pass filtering specifically comprises:
for audio containing watermarks, in order to simulate distortions caused by the inherent characteristics of the loudspeaker and microphone
Using band-pass filtering
Operation, given target Audio
Is performed as follows
：
wherein 
And
respectively representing low-pass filtering and high-pass filtering;
and
to represent
And
a corresponding threshold value;
the gaussian noise is specifically:
simulating random noise caused by uncertain factors in the copying process by introducing Gaussian noise, specifically by directly superposing Gaussian noiseNoise(s)
At the target audio
To implement additive Gaussian noise operation
Namely:
wherein ,
representing gaussian noise;
represents a mean of 0 and a variance of
A gaussian distribution of (a).
5. The method for deep learning based audio watermark embedding and extraction according to claim 4, wherein in step 3, the processing procedure of the distortion layer DAR is as follows:
for audio with watermark
Finally, the audio containing the watermark after being subjected to the DAR processing of the distortion layer is obtained
Namely:
obtaining the same by discrete wavelet transform DWT
Corresponding approximation coefficient
And detail coefficient
And combining the approximation coefficients
Input to a decoder De, the watermark being extracted by the decoder De
Namely:
where De (.) denotes decoder processing.
6. The method for deep learning based audio watermark embedding and extraction according to claim 5, wherein in step 3, watermark loss is further introduced
I.e. watermark information
And watermark extracted by decoder
Mean square error loss MSE between, i.e.:
when using binary watermarking
Rather than to
In this case, for watermarked audio
Watermarks extracted by decoders
Should be as close as possible to-1 and 1; for audio without watermarks, watermarks extracted by the decoder
Should be close to 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310056386.7A CN115831131B (en) | 2023-01-15 | 2023-01-15 | Audio watermark embedding and extracting method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310056386.7A CN115831131B (en) | 2023-01-15 | 2023-01-15 | Audio watermark embedding and extracting method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115831131A true CN115831131A (en) | 2023-03-21 |
| CN115831131B CN115831131B (en) | 2023-06-16 |
Family
ID=85520711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310056386.7A Active CN115831131B (en) | 2023-01-15 | 2023-01-15 | Audio watermark embedding and extracting method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115831131B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19852805A1 (en) * | 1998-11-15 | 2000-05-18 | Florian M Koenig | Telephone with improved speech understanding, several microphones, and special speech signal processing |
| WO2001054053A1 (en) * | 2000-01-24 | 2001-07-26 | Ecole Polytechnique Federale De Lausanne | Transform domain allocation for multimedia watermarking |
| US20080027734A1 (en) * | 2006-07-26 | 2008-01-31 | Nec (China) Co. Ltd. | Media program identification method and apparatus based on audio watermarking |
| CN101290772A (en) * | 2008-03-27 | 2008-10-22 | 上海交通大学 | Embedding and extracting method for audio zero water mark based on vector quantization of coefficient of mixed domain |
| CN102074238A (en) * | 2010-12-13 | 2011-05-25 | 山东科技大学 | Linear interference cancellation-based speech secrete communication method |
| CN102074237A (en) * | 2010-11-30 | 2011-05-25 | 辽宁师范大学 | Digital audio watermarking method based on invariant characteristic of histogram |
| JP2011197619A (en) * | 2010-03-18 | 2011-10-06 | Yasuo Sano | Perception improving means for acoustic signal using electronic watermark |
| CN103221997A (en) * | 2010-09-21 | 2013-07-24 | 弗兰霍菲尔运输应用研究公司 | Watermark generator, watermark decoder, method for providing a watermarked signal based on discrete valued data and method for providing discrete valued data in dependence on a watermarked signal |
| CN108962267A (en) * | 2018-07-09 | 2018-12-07 | 成都信息工程大学 | A kind of encryption voice content authentication method based on Hash feature |
| CN111292756A (en) * | 2020-01-19 | 2020-06-16 | 成都嗨翻屋科技有限公司 | Compression-resistant audio silent watermark embedding and extracting method and system |
| CN113808557A (en) * | 2020-06-12 | 2021-12-17 | 比亚迪股份有限公司 | Vehicle-mounted audio processing system, method and device |
-
2023
- 2023-01-15 CN CN202310056386.7A patent/CN115831131B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19852805A1 (en) * | 1998-11-15 | 2000-05-18 | Florian M Koenig | Telephone with improved speech understanding, several microphones, and special speech signal processing |
| WO2001054053A1 (en) * | 2000-01-24 | 2001-07-26 | Ecole Polytechnique Federale De Lausanne | Transform domain allocation for multimedia watermarking |
| US20080027734A1 (en) * | 2006-07-26 | 2008-01-31 | Nec (China) Co. Ltd. | Media program identification method and apparatus based on audio watermarking |
| CN101290772A (en) * | 2008-03-27 | 2008-10-22 | 上海交通大学 | Embedding and extracting method for audio zero water mark based on vector quantization of coefficient of mixed domain |
| JP2011197619A (en) * | 2010-03-18 | 2011-10-06 | Yasuo Sano | Perception improving means for acoustic signal using electronic watermark |
| CN103221997A (en) * | 2010-09-21 | 2013-07-24 | 弗兰霍菲尔运输应用研究公司 | Watermark generator, watermark decoder, method for providing a watermarked signal based on discrete valued data and method for providing discrete valued data in dependence on a watermarked signal |
| CN102074237A (en) * | 2010-11-30 | 2011-05-25 | 辽宁师范大学 | Digital audio watermarking method based on invariant characteristic of histogram |
| CN102074238A (en) * | 2010-12-13 | 2011-05-25 | 山东科技大学 | Linear interference cancellation-based speech secrete communication method |
| CN108962267A (en) * | 2018-07-09 | 2018-12-07 | 成都信息工程大学 | A kind of encryption voice content authentication method based on Hash feature |
| CN111292756A (en) * | 2020-01-19 | 2020-06-16 | 成都嗨翻屋科技有限公司 | Compression-resistant audio silent watermark embedding and extracting method and system |
| CN113808557A (en) * | 2020-06-12 | 2021-12-17 | 比亚迪股份有限公司 | Vehicle-mounted audio processing system, method and device |
Non-Patent Citations (2)
| Title |
|---|
| 徐甲甲;张卫明;蒋瑞祺;俞能海;胡校成;: "最优结构相似约束下的可逆信息隐藏算法研究" * |
| 徐甲甲;张卫明;蒋瑞祺;俞能海;胡校成;: "最优结构相似约束下的可逆信息隐藏算法研究", 网络与信息安全学报 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115831131B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hua et al. | Twenty years of digital audio watermarking—a comprehensive review | |
| JP3856652B2 (en) | Hidden data embedding method and apparatus | |
| Arnold et al. | A phase-based audio watermarking system robust to acoustic path propagation | |
| GB2431839A (en) | Correlation in audio processing | |
| Dhar et al. | Advances in audio watermarking based on singular value decomposition | |
| US20180144755A1 (en) | Method and apparatus for inserting watermark to audio signal and detecting watermark from audio signal | |
| Dhar et al. | Digital watermarking scheme based on fast Fourier transformation for audio copyright protection | |
| Xiang et al. | Digital audio watermarking: fundamentals, techniques and challenges | |
| Liu et al. | Dear: A deep-learning-based audio re-recording resilient watermarking | |
| US20080273707A1 (en) | Audio Processing | |
| Malik et al. | Robust audio watermarking using frequency-selective spread spectrum | |
| Hemis et al. | Digital watermarking in audio for copyright protection | |
| CN115831131B (en) | Audio watermark embedding and extracting method based on deep learning | |
| US20020184503A1 (en) | Watermarking | |
| Subhashini et al. | Robust audio watermarking for monitoring and information embedding | |
| Arnold et al. | Quality evaluation of watermarked audio tracks | |
| Lee et al. | Audio watermarking through modification of tonal maskers | |
| JP2006171110A (en) | Method for embedding additional information to audio data, method for reading embedded additional information from audio data, and apparatus therefor | |
| Shahriar et al. | Time-domain audio watermarking using multiple marking spaces | |
| Deshpande et al. | A substitution-by-interpolation algorithm for watermarking audio | |
| Li et al. | A novel audio watermarking in wavelet domain | |
| Patil et al. | Audio watermarking: A way to copyright protection | |
| Chore et al. | Survey on different methods of digital audio watermarking | |
| Cvejic et al. | Audio watermarking: Requirements, algorithms, and benchmarking | |
| Shokri et al. | Audio-speech watermarking using a channel equalizer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |