119 results about "Cepstrum" patented technology

The invention relates to the field of biological medicine, and discloses a method and system for analyzing cough sound by using disease characteristics to diagnose respiratory diseases, and the method comprises the steps: deploying a six-microphone annular array to achieve the precise positioning and triggering of a sound source; self-adaptive spectral subtraction and Wiener filtering cascade are adopted to enhance the audio; segmenting a cough segment based on energy envelope; fusing the Mel-cepstrum, the linear prediction residual error, the harmonic energy ratio and the transient zero-crossing rate to construct a pathological feature matrix; extracting local, medium-range and global time sequence features through a three-branch parallel convolutional network; inputting a disease specific classifier to discriminate asthma, pneumonia and laryngitis respectively, and applying a feature decoupling regular term to improve interpretability. The system correspondingly realizes the modularized processing flow. According to the method, the cough sound collection quality and the disease subtype recognition accuracy in a complex environment are improved, meanwhile, the thermodynamic diagram is output to assist clinical decision making, and the diagnosis credibility and practicability are enhanced.

The invention discloses a method for determining the position of a liquid inlet point by using a hydraulic fracturing water hammer signal. The method comprises the following steps: analyzing a main peak of a frequency spectrum through fast Fourier transform, and adaptively determining upper and lower cut-off frequencies of a Gaussian band-pass filter; an alpha-trimmed filter is used for removing peak noise, and an alpha-trimmed filter is used for removing peak noise; extracting a period T of the water hammer signal by adopting an autocorrelation algorithm; carrying out mean value removal processing on the signal after time domain filtering; short-time Fourier transform related parameters are adaptively determined according to the water attack signal period T, and short-time Fourier transform operation is executed to obtain a frequency domain two-dimensional matrix; performing Gaussian band-pass filtering and cepstrum transformation on each column of the two-dimensional matrix to construct a cepstrum matrix; and distinguishing the bridge plug and the liquid inlet points based on the symbolic characteristics of the cepstrum value, determining the actual position of each liquid inlet point in combination with time-depth conversion, and drawing a cepstrum cloud picture. Compared with the prior art, the method is improved in the aspects of adaptive filtering, period extraction accuracy and cepstrum cloud picture artifact removal, and has higher positioning precision and better real-time performance.

The invention relates to a transformer fault identification method based on voiceprint signals, and belongs to the technical field of cepstrum for extracting parameters in audio decoding or coding. The method comprises the following steps: setting a fault type and establishing a fault identification model for training; arranging an acoustic sensor to collect voiceprint signals of the transformer; utilizing a dream optimization algorithm to optimize the penalty factor and a successive variational mode decomposition method to decompose a plurality of mode components, and dividing the mode components into pure components and noisy components; noise reduction is carried out on the noisy component by adopting a designed threshold function in combination with wavelet threshold noise reduction, and the noisy component and the pure component after noise reduction are input into the recognition model to obtain a probability vector; and finally, fusing into a first fusion probability vector and a second fusion probability vector through fuzzy measurement, and taking the fault type corresponding to the maximum second fusion probability as the fault type of the transformer. The method can accurately capture the mapping relation between the acoustic features and the transformer fault state, and accurately identifies the transformer fault type.

The invention relates to the technical field of noise recognition, and discloses an intelligent recognition method and system for Bluetooth headset environment noise, and the method comprises the steps: collecting two paths of original audio of a Bluetooth headset, determining the dynamic evolution characteristics of environment noise components, carrying out the frequency domain cepstrum transformation of the environment noise components, and obtaining the frequency domain noise characteristics; carrying out attention fusion on the dynamic evolution features and the frequency domain noise features to obtain fused audio features, and constructing an association feature matrix of the fused audio features; constructing a noise scene candidate set of the Bluetooth headset, and performing noise type screening on the noise of the Bluetooth headset by using the associated feature matrix and the noise scene candidate set to obtain a noise type candidate list; and performing adversarial enhancement processing on the noise corresponding to each noise type in the noise type candidate list to obtain an enhanced noise set, extracting a dynamic characteristic spectrum of the enhanced noise set, and identifying the environmental noise of the Bluetooth headset. According to the invention, the recognition precision of the environment noise of the Bluetooth earphone can be improved.

The invention relates to an equipment fault diagnosis method and system. The method comprises the following steps: performing signal decomposition on an original vibration signal to obtain a group of intrinsic mode components; for each intrinsic mode component, calculating a kurtosis value and an order cyclic spectral density amplitude; based on the kurtosis value and the order cyclic spectral density amplitude, constructing a frequency band selection index used for representing fault impact energy and periodical modulation certainty; determining one or more intrinsic mode components enabling the frequency band selection index to be optimized, and determining an optimal filtering frequency band according to the center frequency and the bandwidth of the optimized intrinsic mode components; performing Hilbert transform on the filtered signal to obtain an analytic signal; extracting the instantaneous amplitude of the analysis signal to obtain an envelope signal; performing cepstrum editing on the envelope signal to obtain an enhanced envelope signal, and performing fast Fourier transform on the enhanced envelope signal to obtain an enhanced envelope spectrum; and performing fault diagnosis based on the fault characteristic frequency in the enhanced envelope spectrum.

The invention discloses an Internet of Things anomaly detection method and system based on quaternion state space diffusion enhancement, and belongs to the technical field of network security and artificial intelligence. The method comprises the following steps: mapping a flow time sequence feature into a quaternion tensor to maintain an internal coupling relationship of a multi-dimensional feature; a double-flow encoder is designed, a quaternion selective state space model is adopted to extract continuous fluid features, and a dynamic hypergraph neural network is adopted to model discrete protocol features; carrying out self-supervised pre-training on a resistance pseudo-anomaly sample by utilizing potential diffusion model generation, and optimizing characterization by combining quaternion cepstrum distance loss; the injected learnable prompt vector is optimized in the small sample fine tuning stage, and a category prototype is corrected by using a semi-supervised expectation maximization algorithm; and calculating a sample anomaly score based on an energy model to realize known attack classification and unknown anomaly judgment. According to the method, the generalization ability of the model under the small sample condition and the unknown threat detection ability are remarkably improved.

The invention discloses an open hole vertical well fracturing crack position identification method based on density clustering, which belongs to the technical field of hydraulic fracturing, and comprises the following steps: collecting a water hammer signal at the moment of pump stop by using a high-frequency pressure monitor; performing filtering processing on the signal by using an FIR filter; carrying out deconvolution processing on the filtered signal by adopting a cepstrum analysis method, and extracting crack reflection characteristics; determining the position of a liquid inlet point by combining an impedance identification technology; and performing dynamic analysis by using a density clustering method according to the determined liquid inlet point position, and identifying the crack number and the main body position based on the liquid inlet point space density. By the adoption of the method, the spatial distribution of the liquid inlet points is obtained through water hammer signal processing, the spatial density of the liquid inlet points is analyzed based on the density clustering analysis method, and therefore crack position recognition in the complex liquid inlet process such as vertical well open hole fracturing is achieved.

The invention relates to the field of voice signal processing and voice recognition, and discloses a voice recognition enhancement method and system based on harmonic model fundamental frequency optimization and RNN noise suppression, and the method comprises the steps: collecting a voice signal in a noise environment in real time, carrying out the framing and windowing of the voice signal, and generating multi-dimensional time-frequency data; estimating the fundamental frequency of each frame of voice through a cepstrum analysis method, and screening effective fundamental frequency frames according to a confidence coefficient threshold to form a fundamental frequency characteristic matrix; dynamically adjusting the noise power spectrum of the Wiener filter under the drive of the fundamental frequency characteristic matrix, and carrying out dislocation fusion on the filtering output and the original spectrum to form an enhanced spectrum first draft; inputting the enhanced spectrum first draft into a recurrent neural network in a framing manner, predicting the gain of each frequency band, calculating an inhibition factor, and generating a multi-frame continuous enhanced spectrum sequence; multiple frames of continuous enhanced spectrum sequences are synthesized into voice signals through inverse short-time Fourier transform, an end-to-end enhanced recognition process is formed, and the method has the advantage of improving accuracy.

Provided are a signal processing device, a diagnostic system, and a signal processing method with which it is possible to improve the accuracy of a determination value for determining a lubrication state in a rolling device. A signal processing device (3), which calculates a determination value for determining a lubrication state in a rolling device on the basis of a measurement signal acquired by a sensor (2), is provided with: a first processing unit (321) which converts the measurement signal into a time-domain signal by performing band limitation and envelope processing on the measurement signal; a second processing unit (322) that converts the time-domain signal into a first frequency-domain signal; a third processing unit (323) that converts the logarithmic spectrum of the first frequency domain signal into a first inverse frequency domain signal; a fourth processing unit (324) that generates a second inverted-frequency-domain signal in which the high-order cepstrum domain, which includes the rotation frequency of the scrolling device, of the first inverted-frequency-domain signal is set to a prescribed value; a fifth processing unit (325) that converts the second inverted frequency domain signal into a second frequency domain signal; and a determination value calculation processing unit (33) that calculates a determination value on the basis of the second frequency domain signal.

The invention relates to the technical field of deep learning voiceprint recognition, in particular to a voiceprint recognition method based on a double-feature branch structure. The voiceprint recognition method comprises the steps that Mel cepstrum features and wavelet transform features are extracted from original voice signals respectively, and two branches are formed; respectively inputting the features into a self-attention network and a convolutional TDNN network to carry out multi-scale feature modeling, and fusing two paths of outputs; further calculating multi-level discrimination loss for the fused voiceprint representation so as to enhance the speaker discrimination degree in a noisy or mismatched environment; and performing decoding or up-sampling operation on the fused output and taking the fused output as the input of next-stage processing, and finally generating multi-resolution and more robust voiceprint features through a cascade codec structure. The method aims to overcome the defects of single path feature extraction in a complex environment, and the capture and recognition capability of multi-resolution speech features is remarkably improved by combining the advantages of self-attention and convolution TDNN.

The invention belongs to the technical field of buildings, and particularly relates to a cable defect positioning and intelligent identification system and method based on a broadband impedance spectrum. The system comprises a vector network analyzer which can inject a sweep frequency excitation signal into a target cable to be detected, a high-precision receiver which is used for collecting signal reflection / transmission response so as to obtain full-band complex impedance spectrum data, and computer equipment which receives test data. The positioning method based on Nuttall-Kai ser mixed window and cepstrum coupling does not need to depend on an intact cable parameter database, is high in anti-interference capability, can accurately identify defect positions, and is high in positioning precision; the one-dimensional impedance spectrum is converted into the two-dimensional image through the GAF, the automatic identification of the defect type is realized by combining the residual neural network (ResNet), the manual intervention is reduced, and the automation degree is high; the deep feature learning capability of ResNet is utilized, and a CBAM attention module is combined, so that the capture of a fine defect mode is enhanced, and the recognition accuracy is improved.

The invention discloses an automatic audio quality scoring method and system combining MFCC and time domain statistical characteristics, and the method comprises the steps: carrying out the segmentation according to seconds on the basis of reference and to-be-detected signal resampling and time alignment, and further extracting cepstrum and time domain statistical characteristics according to 100 ms sub-segments; the method comprises the following steps: forming 170-dimensional second-level features by performing hierarchical aggregation of mean value + maximum value on sub-segment features, splicing the 170-dimensional second-level features with corresponding reference segments to form 340-dimensional joint features, and inputting the 340-dimensional joint features into a pre-trained support vector machine model to output second-by-second discrete scores from 0 to 5, thereby realizing high-time-resolution automatic quality evaluation and anomaly positioning under the conditions of light calculation power and small samples.

The invention discloses an IPO-based multi-mode fusion power equipment fault identification method and system, and the method comprises the steps: carrying out the variational mode decomposition of an original vibration signal and a voiceprint signal, and obtaining a denoised vibration signal and a denoised voiceprint signal; processing the denoised vibration signals and voiceprint signals through a Mel filter bank, a Barker filter bank and a Gammatone filter bank to obtain a cepstrum group; performing Gaussian filtering and image segmentation on the infrared image to obtain an infrared target image; and inputting the obtained multi-modal data into the multi-modal fusion power transformer fault identification model after the hyper-parameters are optimized by the improved Meland spar optimization algorithm, and carrying out power equipment fault identification. According to the method, the limitation of a traditional single-mode diagnosis method is overcome, and the accuracy and efficiency of power transformer fault identification are improved.

To provide a technique for detecting abnormal sound having a relatively small amplitude in a rotating body such as a motor.SOLUTION: A rotating body inspection device includes a frequency spectrum generation unit, a cepstrum generation unit, an order cepstrum generation unit, and an abnormal sound detection unit. The frequency spectrum generation unit generates a frequency spectrum for each measurement section in time series from vibration data that is data of vibration for each rotation speed of the rotating body. The cepstrum generation unit generates a cepstrum from the frequency spectrum for each measurement section. The order cepstrum generation unit generates an order cepstrum that is data obtained by converting a quefrency of the cepstrum into an order for each measurement section. The abnormal sound detection unit detects abnormal sound of the rotating body based on the order cepstrum for each measurement section.SELECTED DRAWING: Figure 2

The invention discloses an earphone defect detection method and device based on voiceprint feature analysis and a storage medium, and relates to the technical field of electroacoustic quality control. According to the method, human ear hearing characteristics are simulated, Mel-cepstrum voiceprint characteristics are extracted from sound response signals, an adaptive weight mechanism based on an equal-loudness curve is introduced, and a voiceprint abnormal deviation index model conforming to human ear subjective perception is constructed; in order to solve the problem that tiny abnormal noise is difficult to recognize, high-order statistics such as kurtosis and skewness are adopted for feature fusion enhancement, and a support vector machine is combined to achieve accurate capture of transient impulse noise. According to the invention, various defect types such as voice coil friction, imbalance of balance degree, diaphragm damage and the like can be fully automatically distinguished, the problems that a traditional test means is disjointed with subjective hearing sense and the omission ratio of hidden defects is high are effectively solved, and the quality inspection efficiency and accuracy of earphone production lines are remarkably improved.

The invention discloses a method for classifying various arrhythmia signals, belongs to the technical field of arrhythmia signal classification methods, and the accurate classification of arrhythmia has important significance for disease diagnosis and clinical treatment. However, the traditional detection method is often interfered by various factors such as signal non-stationarity, feature non-specificity, artifacts and noise caused by arrhythmia when processing various arrhythmia, and the classification precision and efficiency are difficult to meet the requirements. Therefore, the invention provides an improved power normalized cepstrum coefficient (SPNCC) method based on singular spectrum analysis (SSA), which is used for extracting key features from a photoplethysmogram (PPG) signal and reducing the influence of noise, and constructing a deep learning classification model in combination with a convolutional neural network and a bidirectional long short-term memory network (CNN-BiLSTM). Therefore, accurate identification of various arrhythmias can be realized.

The invention discloses a fracturing-based water hammer wave velocity inversion method, a readable storage medium and a fracturing-based water hammer wave velocity inversion device, and belongs to the technical field of fracturing. Performing noise reduction processing to obtain a noise reduction signal; converting the noise reduction signal to a reverse frequency domain; establishing a relationship between the cepstrum amplitude and the liquid inlet response time, generating a two-dimensional curve graph, identifying a peak point, and correspondingly obtaining the liquid inlet response time; designing a water hammer wave velocity value, and converting to obtain a liquid inlet depth value; and solving the minimum value of the difference sum between the liquid inlet depth value and the designed depth value. The readable storage medium stores the method. The device is provided with a computer program for storing and executing the method. According to the method, the water hammer wave velocity can be effectively determined under the conditions that the bridge plug slides and the actual bridge plug position is not matched with the designed bridge plug position, the liquid inlet position of the fracturing liquid is promoted to be better matched with the designed perforation position, then fracturing liquid inlet point recognition is guided, a fracturing construction scheme is optimized, and the fracturing transformation effect is improved.

The invention relates to the technical field of rotating machinery fault monitoring, and discloses a method and system for monitoring a torsional vibration fault of a shaft system of a steam turbine generator unit, and the method comprises the steps: obtaining a single-point torsional vibration signal, and converting the single-point torsional vibration signal into an angular domain sequence; extracting a narrow-band modulation component of a specific order band and calculating a torsional vibration logarithmic response spectrum; performing inverse transformation on the logarithmic spectrum to obtain cepstrum data reflecting the periodicity of the shafting structure; delimiting a structure reflection propagation time delay interval according to the geometric distance from the sealing end to the rigid coupling and the material wave velocity; identifying a sealing-coupling boundary reflection peak value and a series structure in the interval, and constructing a series enhancement index; reversely deducing an equivalent reflection intensity and an equivalent structure distance, and generating a health index; and finally, mapping the health index into a binarization result through a step function, and outputting normal or abnormal judgment for the sealed end. According to the invention, the high-sensitivity and deterministic monitoring of the local abnormity of the sealing end is realized by using the echo structure information.

The invention discloses an engineering vehicle chassis transmission system operation noise source accurate positioning system and method, and the method comprises the steps: S1, installing a vibration sensor on a key part of an engineering vehicle chassis transmission system, and collecting the vibration signal of each key part; s2, carrying an acoustic sensor on a mobile device, wherein the acoustic sensor can sequentially move to the corresponding position of each key component along with the mobile device to carry out acoustic signal acquisition; s3, performing cross-correlation analysis on the acquired acoustic signals and vibration signals, calculating cross-correlation coefficients among the signals acquired by different sensors, and preliminarily determining position information of a noise source by comparing the cross-correlation coefficients of all key components; and S4, performing cepstrum analysis on sensor signals near the preliminarily positioned noise source position, identifying periodic components in the signals, verifying the position of the noise source, and accurately positioning the noise source in combination with a cross-correlation analysis result and a cepstrum verification result.

The invention relates to a voice emotion recognition method and system, and belongs to the technical field of intelligent interaction. Comprises: acquiring an original voice signal; calculating a frame-level score of the original voice signal, and dividing the original voice signal into a high-reliability frame signal and a low-reliability frame signal according to the frame-level score; performing feature extraction on the high-reliability frame signal, and determining Mel-frequency cepstrum features; performing feature extraction on the low-reliability frame signal to determine rhythmic features; performing feature fusion on the Mel-frequency cepstrum features and the rhythm features to obtain target features; constructing a voice emotion recognition model; and inputting the target feature into a voice emotion recognition model, and determining an emotion category. According to the invention, the accurate judgment of the emotion is realized, and the accuracy of voice emotion recognition and the stability in a complex environment are remarkably improved.

The application discloses an audio quality automatic scoring method and system combining MFCC and time domain statistical features, comprising the following steps: on the basis of resampling and time alignment of a reference signal and a to-be-detected signal, extracting cepstrum and time domain statistical features according to second segmentation and further 100 ms subsegment extraction, forming 170-dimensional second-level features through mean value+maximum value hierarchical aggregation of subsegment features, splicing the corresponding reference segment into 340-dimensional joint features, inputting the pre-trained support vector machine model to output a second-by-second discrete score of 0 to 5, and realizing high-time-resolution automatic quality evaluation and abnormal positioning under the conditions of light computing power and small samples.

The present invention discloses a method for structural health monitoring of rail transit, belonging to the technical field of structural health monitoring of rail transit. In this method, vibration sensors are symmetrically arranged on both sides of the track to obtain a pair of vibration signals. The cepstrum is extracted from each segment of the vibration signal to obtain the real and imaginary cepstrum data. The cepstrum features of both are respectively extracted and corresponding feature vectors are constructed. Furthermore, the mismatch degree of a pair of vibration signals on the feature vectors is obtained, resulting in the real and imaginary mismatch degrees. The various mismatch degrees are evenly divided into three parts in chronological order and the mean values are extracted to calculate the coefficient of variation. The real and imaginary eigenvalue features of the mismatch degree of each part are extracted, and feature enhancement is performed using the coefficient of variation, finally obtaining the structural health value of the rail transit. This method processes and analyzes the vibration signals through multiple steps, improving the accuracy of structural health monitoring of rail transit.

The speech synthesis method, the speech synthesis device, the electronic equipment and the storage medium provided by the embodiment of the present application relate to the technical field of financial technology. The method comprises the following steps: performing spectrum feature extraction on original speech data to obtain original speech mel-frequency cepstrum and original speech linear spectrum; performing feature coding on the original speech mel-frequency cepstrum through a preset speaker encoder to obtain original speaker features; performing posterior coding on the original speech linear spectrum through a preset posterior encoder to obtain speech posterior features; performing content feature extraction according to the original speaker features and the speech posterior features to obtain target speech content features; and performing speech synthesis according to preset target speaker features and the target speech content features to obtain synthesized speech data; wherein the synthesized speech data is used to represent speech uttered by a target speaker object according to original speech content. The embodiment of the present application can guarantee the quality of speech synthesis and can perform speech conversion for any speaker.

The invention provides a method and device for determining a fracturing crack based on a fracturing pump stop water hammer signal, and the method comprises the steps: firstly obtaining the fracturing pump stop water hammer signal of a target well, and determining a first cluster crack and the crack position of the first cluster crack through cepstrum analysis according to the fracturing pump stop water hammer signal; determining a plurality of candidate cracks according to the crack positions of the first cluster cracks; determining a plurality of actually opened fracturing fractures and fracture positions of the fracturing fractures from the plurality of candidate fractures according to the fracturing pump stop water hammer signal of the target well by determining and according to the related frequency spectrum envelope; according to the fracturing pump stop water hammer signal of the target well, determining a reflection coefficient of a fracturing crack by determining and according to a target reflection response sequence; and according to the reflection coefficient of the fracturing crack, determining the liquid inlet strength of the fracturing crack. Therefore, the number and the positions of the underground fracturing cracks can be accurately identified, and meanwhile, the liquid inlet strength of the underground fracturing cracks can be accurately determined.

The application discloses a bearing composite fault diagnosis method and system, first, a bearing composite fault vibration observation signal is acquired; then, the observation signal is subjected to short-time Fourier transform and cepstrum threshold processing, two-dimensional time-frequency mask blind source separation, inverse short-time Fourier transform is performed on the obtained time-frequency domain separation signal and band-pass filtering is performed, independent time domain estimation signals are obtained; then, the estimation signals are subjected to Hilbert envelope demodulation and Fourier transform, envelope spectra of the filtered signals are obtained; finally, each order characteristic frequency band of a target fault is searched, a harmonic energy impact index is constructed, and an impact pulse value is calculated; the calculated impact pulse value is compared with a threshold value, and whether the bearing has a target type fault is diagnosed.

The present application relates to a kind of data-independent anti-multipath radio frequency fingerprint extraction method and system, for extracting the radio frequency fingerprint of wireless device.The method implementation steps include: sampling and preprocessing to wireless signal, obtain received signal;The time-domain signal of received signal is transformed in frequency domain and logarithm operation to obtain cepstrum domain signal;Select two frames of signals experiencing channel incoherence to do cross-correlation operation and further remove the correlation caused by local signal, as radio frequency fingerprint expression;The cross-correlation value between multiple symbols is superimposed and averaged to enhance fingerprint, while eliminating noise.The method of the present application effectively decouples the radio frequency fingerprint component in wireless signal from wireless multipath channel component, varying transmission data component, while enhancing the representation of radio frequency fingerprint, improving the stability of fingerprint, and suppressing noise, which is an effective data-independent anti-multipath radio frequency fingerprint extraction method for any wireless transmission signal.

The invention provides a method and device for determining a hydraulic fracturing temporary plugging transformation effect and computer equipment. On the basis of the method, a first water hammer wave signal before temporary plugging operation and a second water hammer wave signal after temporary plugging operation of a current transformation well section of a target well are obtained, and the cepstrum response energy proportion before temporary plugging and the cepstrum response energy proportion after temporary plugging of each cluster of cracks in the current transformation well section are determined through cepstrum operation according to the first water hammer wave signal before temporary plugging operation and the second water hammer wave signal after temporary plugging operation; determining the temporary plugging efficiency of each cluster of cracks in combination with a first type of distribution function constructed based on the cepstrum response energy proportion of each cluster of cracks before temporary plugging; meanwhile, according to the cepstrum response energy proportion before and after temporary plugging of each cluster crack in the current transformation well section, in combination with a second type of distribution function constructed based on the cepstrum response energy proportion during well section crack uniform development, determining a temporary plugging efficiency penalty coefficient of each cluster crack; and the temporary plugging efficiency and the temporary plugging efficiency penalty coefficient of each cluster of cracks in the current transformed well section are used in a combined mode, and the temporary plugging transformation effect of the current transformed well section is accurately determined.

The application belongs to the technical field of speech recognition and semantic understanding, and discloses a high-precision speech recognition and semantic understanding method. The method comprises the following steps: collecting a far-field multi-sound-source original speech signal to generate a discrete speech sampling sequence; performing frequency domain transformation on the original speech signal to extract an amplitude-frequency distortion quantization parameter; segmenting the original speech signal to generate a speech frame sequence and calculating a non-steady-state speech speed quantization parameter; extracting an original mel-frequency cepstrum feature and performing distortion correction to obtain a weighted acoustic feature through dynamic weighting; constructing a preset semantic feature library and mapping to generate an initial semantic matching vector; and recursively iterating to calibrate the semantic confidence and screening an optimal term to output a result. The application solves the problem of low far-field speech recognition accuracy in the prior art, realizes high-precision speech recognition and semantic understanding through multi-link collaborative optimization, and improves recognition stability.

The invention relates to the technical field of speech processing, and particularly provides a disguise speech recognition method based on a Transform model and mixed features, which is carried out from two aspects of feature extraction and model establishment. A resonance peak parameter is calculated by adopting a cepstrum method, a cepstrum coefficient (GFCC) is obtained through a Gammatone filter bank, then the resonance peak, the GFCC and a difference coefficient of the GFCC are combined into a mixed characteristic parameter, and complementary correlation between mixed characteristics is mined. From the perspective of model establishment, the mixed features are used as the input of the model, and the Transform network model is used as the acoustic model of the voiceprint recognition system, so that the feature distribution is better fitted, the classification effect is remarkably improved, and the performance of the camouflage voice voiceprint recognition system is effectively improved. The problem of performance degradation caused by feature redundancy and modal noise in a traditional method is solved.

The application discloses an Internet of Things anomaly detection method and system based on quaternion state space diffusion enhancement, and belongs to the technical field of network security and artificial intelligence. The method comprises the following steps: mapping traffic time sequence features into a quaternion tensor to maintain the internal coupling relationship of multi-dimensional features; designing a double-flow encoder, extracting continuous flow features by using a quaternion selective state space model, and modeling discrete protocol features by using a dynamic hypergraph neural network; generating an adversarial pseudo-anomaly sample by using a latent diffusion model to perform self-supervised pre-training, and combining a quaternion cepstrum distance loss to optimize the representation; optimizing the injected learnable prompt vector in the small sample fine-tuning stage, and correcting the class prototype by using a semi-supervised expectation maximization algorithm; calculating sample anomaly scores based on an energy model to realize known attack classification and unknown anomaly determination. The application significantly improves the generalization ability of the model under the condition of small samples and the detection ability of unknown threats.