273 results about "Cepstrum coefficients" patented technology

The invention relates to the technical field of sound anomaly detection, in particular to a sound anomaly detection method and device based on a Transform model, equipment and a medium, and the method comprises the steps: collecting a sound signal during the operation of the equipment through a data collection interface, and obtaining an original sound signal; resampling is carried out on the collected sound signals, and normalization processing is carried out on the resampled data; mel-frequency cepstrum coefficient features are extracted from the sound signals after normalization processing, and the sound signals after normalization processing are input into a pre-training module to output high-dimensional features including time sequence and semantic information; splicing the Mel-frequency cepstrum coefficient features with the high-dimensional features to form a comprehensive feature vector; inputting the comprehensive feature vector into a support vector machine model, and performing abnormal sound recognition through a trained classification hyperplane; and detected abnormal information is fed back to the user in real time. Multi-feature fusion enables the model to identify abnormal sound more accurately.

The invention relates to the technical field of voice interaction, particularly discloses an AI intelligent robot voice interaction method and system, and aims to solve the problems of low voice interaction accuracy, insufficient reliability and lack of authority control in a complex noise environment. A dynamic noise feature library containing steady-state noise, impact noise and human voice interference features and a pre-stored gesture instruction library are constructed, audio signals are collected in real time, low-frequency-band, middle-frequency-band and high-frequency-band differential noise reduction is executed, Mel-frequency cepstral coefficient features are extracted, noise scenes are matched, corresponding voice recognition models are switched, and voice recognition is achieved. And calculating a confidence value of the voice instruction, outputting multi-modal verification data in combination with a dynamic confidence threshold, and outputting an authority control signal through voiceprint matching, authority verification and instruction consistency judgment. Through multi-modal fusion, dynamic adaptation and authority control, the voice recognition accuracy and interaction safety in a complex noise environment are remarkably improved, and the method is suitable for scenes such as factory intelligent inspection.

The invention relates to an audio feature extraction method and device based on a neural network. The method comprises the following steps: performing framing processing and fast Fourier transform on an original audio signal acquired by a vehicle-mounted microphone to obtain a frequency domain feature sequence; extracting short-time energy, a zero-crossing rate, a frequency spectrum centroid and a Mel-frequency cepstrum coefficient from the frequency domain feature sequence, and combining first-order difference and second-order difference features of each feature to obtain a multi-dimensional acoustic feature point sequence; performing time sequence arrangement on the multi-dimensional acoustic feature point sequence, constructing an original feature matrix, and performing principal component analysis on the original feature matrix to obtain a feature description matrix; inputting the feature description matrix into a dynamic time feature extraction network for deep time-frequency feature analysis to obtain vehicle-mounted voice deep time-frequency features; and performing voice detection classification based on the vehicle-mounted voice deep time-frequency features, and outputting a vehicle-mounted voice detection result. According to the invention, various noise interferences in a vehicle-mounted environment are effectively suppressed, and the anti-noise capability of the system is enhanced.

The invention provides a wind turbine generator voiceprint fault recognition method, and relates to the technical field of wind turbine generator state monitoring and fault diagnosis, and the method comprises the steps: carrying out the noise reduction of an original audio signal through variational mode decomposition, screening a target mode of which the frequency, energy and kurtosis accord with features, and reconstructing the signal; extracting a Mel frequency cepstrum coefficient and a sensing noise robust coefficient, and generating multi-dimensional voiceprint data in combination with statistical characteristics such as a frequency spectrum gravity center, a spectrum entropy, energy, kurtosis and a zero-crossing rate; constructing a support set based on the prototype network, realizing small sample fault classification by calculating the Euclidean distance between the feature vector and the prototype vector, and outputting a preliminary result; judging whether the voiceprint is abnormal according to a preset threshold value, if so, storing the voiceprint into a dynamic abnormal voiceprint knowledge base; frequently occurring abnormal samples are manually labeled and added into a support set, the prototype network is retrained to update the model, and continuous optimization of the fault recognition capability is achieved.

The invention provides a converter valve fault identification method based on voiceprint small sample learning, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a to-be-identified target audio comprising converter valve environment noise, and carrying out the noise reduction processing based on FRCRN, and obtaining a noise-reduced audio signal; carrying out feature extraction based on the Mel frequency cepstrum coefficient and the Gammatone filter bank cepstrum coefficient, and carrying out dimension reduction on features based on a principal component analysis method to obtain feature vectors; inputting the feature vector into a voiceprint recognition model which is completely trained based on a voiceprint small sample for recognition, and obtaining a recognition result; according to the method, the to-be-recognized audio is denoised based on the FRCRN, most noise in the converter valve environment can be filtered out, and the technical effect of accurately recognizing the to-be-recognized audio is achieved; by adjusting the structure of the voiceprint recognition network, useful information of the features can be highlighted, redundancy of repeated information is reduced, and therefore the recognition accuracy of the voiceprint recognition model in the converter valve noisy environment is improved.

The invention relates to a steel structure engineering welding quality defect analysis method based on voiceprint monitoring, and the method comprises the steps: carrying out the multi-channel voiceprint synchronous collection, time-frequency feature fusion, wavelet packet analysis and Mel-frequency cepstral coefficient extraction for a plurality of defect features fused in voiceprint data in a welding process; a hierarchical semantic concept space and a dynamic causal relationship generation model are established in combination with a welding physical knowledge base, a causal knowledge graph is constructed, causal association between semantic concepts is deduced through a gating circulation unit and a graph neural network, anti-fact disturbance and path aggregation analysis is carried out on a causal graph structure, and a result is obtained. And finally, defect category probability output and causal traceability graph visual display are realized. According to the scheme, the accuracy, traceability and result interpretability of welding defect recognition are effectively improved, and data support is provided for intelligent diagnosis and continuous model optimization in the welding process.

The invention provides a speech recognition method and system based on artificial intelligence, and relates to the technical field of speech recognized.The speech recognition method comprises the steps that speech signals are collected in real time, and speech signal features are extracted through a Mel-frequency cepstrum coefficient after the speech signals are subjected to noise reduction; and combining the Mel-frequency cepstral coefficients and the first-order difference and the second-order difference of the Mel-frequency cepstral coefficients to form a speech feature vector. Meanwhile, a lip moving image is collected to serve as a visual signal, after graying processing is conducted on the image, an image feature vector is generated by calculating LBP values of pixel points in the image, the weight of the voice feature vector and the weight of the image feature vector are dynamically adjusted through a cross-modal attention mechanism, a fusion weight matrix is generated, and a fusion image is obtained. Different fusion weight matrixes correspond to different voice instructions, the original voice signals and the original visual images serve as a training set, the voice instructions corresponding to the fusion weight matrixes serve as labels to train a deep learning network model, and finally real-time voice recognition is carried out by inputting data collected in real time into the trained model.

The invention provides a PPG big data driven biological feature recognition method, which comprises the following steps: acquiring PPG signal data of trainees, and performing high-pass filtering and low-pass filtering preprocessing on the PPG signal data to obtain preprocessed PPG signals; framing is carried out on the preprocessed PPG signal, a Mel frequency cepstral coefficient feature and a Gammatone frequency cepstral coefficient feature are extracted respectively, the Mel frequency cepstral coefficient feature and the Gammatone frequency cepstral coefficient feature are fused, then principal component analysis dimension reduction is carried out, and a fusion feature is obtained; a universal background model UBM of a Gaussian mixture model is constructed based on the fusion features, zero-order, first-order and second-order Baum-Welch statistics are calculated, a global difference space matrix is estimated from the Baum-Welch statistics, and i-vector identity authentication vectors are extracted; and inputting the i-vector identity authentication vector into a long short-term memory network for training and classification to obtain an identity recognition result of the trainees. According to the invention, the influence of motion artifacts can be eliminated, the overall variability of PPG signals is captured, and an identity authentication scheme is provided for wearable equipment.

The invention provides a casting industry abnormal sound detection and grading response method based on voiceprint recognition, and belongs to the technical field of casting industry detection. A high-temperature-resistant microphone array is arranged at an easy-to-leak part of cast aluminum equipment, and three-stage filtering noise reduction and amplitude normalization preprocessing are adopted, so that the problem of poor signal quality caused by noise interference in a complex environment is effectively solved; the characteristics of the molten aluminum leakage sound in different frequency bands and different stages can be captured through variable window long-short time Fourier transform and extended Mel frequency cepstrum coefficient in combination with extraction of an energy change rate and a frequency spectrum gravity center; a Transform-CNN hybrid deep learning model based on an attention mechanism is constructed, and feature screening is optimized through principal component analysis and recursive feature elimination, so that the recognition and generalization ability of the model to the abnormal sound in the casting industry is significantly improved; and meanwhile, graded response measures are made based on the detection result, so that the abnormal conditions of molten aluminum leakage with different severity degrees are processed.

The invention provides a high-voltage circuit breaker voiceprint denoising method based on data enhancement and a storage medium, and the method comprises the steps: processing a collected original voiceprint data sequence, extracting stable and effective Mel-frequency cepstrum coefficient features, and constructing a two-dimensional feature matrix; a parallel mixed data enhancement strategy is adopted to generate a positive sample pair, and an encoder is trained in combination with a contrast learning mechanism, so that the representation robustness of the model under different voiceprint change conditions is improved. The method comprises the following steps: decomposing an original signal containing noise fringes into a plurality of modal components by using variational modal decomposition, extracting low-frequency effective components, introducing Gaussian white noise, constructing a corrosion target signal as a decoder training target, learning through a denoising automatic encoder, and finally outputting a denoised voiceprint feature signal. The method has the advantages of high robustness, high noise suppression capability, excellent feature expression capability and the like, is suitable for the field of online monitoring and intelligent diagnosis of the state of high-voltage circuit breaker equipment, and has good application prospect and engineering value.

The invention relates to the technical field of voiceprint recognition, in particular to a photovoltaic equipment fault detection method and system based on voiceprint recognition, and the method comprises the following steps: collecting the sound of the surrounding environment of a current photovoltaic power station, and building scene associated equipment spectrum peak features; according to the method, classification of environment sound is introduced in the sound acquisition stage, and scene association is performed on the operation sound of the photovoltaic equipment and the surrounding background sound in combination with Mel-frequency cepstrum coefficient extraction and acoustic scene recognition, so that a more targeted reference framework is provided for subsequent analysis. Modeling of multi-source sound features is achieved by synchronously collecting operation sound of an inverter and a cooling fan in equipment and extracting spectrum peak frequency points and amplitudes. In the signal processing process, multiple sub-bands are divided on the basis of scene correlation spectrum peak frequency points, so that each sub-band is aligned with the acoustic characteristics of equipment, the structural precision of short-time energy envelope extraction is improved, and it is ensured that the cross-correlation analysis result is more reliable.

The invention relates to a speech emotion recognition method and system based on multi-scale adaptive feature fusion. A speech signal is acquired and preprocessed to obtain a Mel-frequency cepstrum coefficient; time features and frequency features of Mel-frequency cepstrum coefficients are extracted and fused to obtain multi-scale features, the multi-scale features are divided into a global information estimation branch and an efficient self-attention branch through channel expansion, the efficient self-attention branch extracts fine-grained local features through self-attention, the global information estimation branch extracts low-frequency content through downsampling, and the high-efficiency self-attention branch extracts low-frequency content through down-sampling. Non-local information is captured in combination with global variance modulation; by fusing the global features and the local features obtained by the two branches, the relevance between different features is mined, deep feature representation is obtained, and fused deep time-frequency features are obtained; and classifying the fused deep-layer time-frequency features by using a full-connection network, and determining an emotion category corresponding to the voice signal.

A method of constructing a water supply pipeline leakage identification model based on deep learning and an application thereof are provided, which relate to the technical field of nondestructive detection and positioning of municipal water supply pipeline leakage. By extracting Mel-frequency cepstral coefficient of leakage sound signals as a basis for distinguishing pipeline leakage, a neural memory network is introduced to learn leakage features and establish a leakage feature neural network model, and the features of a signal of a point to be detected are input into the model to determine whether the point leaks, so as to realize accurate positioning of the pipeline leakage position.

The invention provides a laying hen voice recognition method and system fusing acoustic features and deep learning features. The method comprises the steps of obtaining a to-be-recognized original audio signal and a voice recognition model; wherein the voice recognition model comprises a feature extraction network, a feature fusion network and a classification recognition network; performing feature extraction on the original audio signal by using the feature extraction network to obtain a spectrogram feature, a Mel-frequency cepstrum coefficient feature and a deep speech feature; the feature fusion network performs feature fusion on the spectrogram features, the Mel-frequency cepstrum coefficient features and the deep speech features by using a collaborative attention mechanism or a multi-head attention mechanism to obtain fused features; and inputting the fused features into a classification recognition network to obtain a voice recognition result. According to the method, the advantages of various characteristics can be fully utilized, and the sound signals are described and analyzed from multiple angles, so that the voiceprint of the laying hen is more accurately recognized, and the voiceprint recognition accuracy of the laying hen is remarkably improved.

The invention discloses a spoken English man-machine conversation interaction training method and system, and relates to the technical field of spoken English training, spoken English audio signals of a user are monitored in real time through a microphone, and the frequency spectrum information of the audio signals is refined into each frame of spectrogram and cepstrum coefficient feature vectors by using Fourier transform and feature extraction technologies; therefore, the voice signal characteristics of the user can be completely captured; three core dimensions of semantic similarity, grammatical structure similarity and fluency are incorporated into an evaluation model, a comprehensive oral English training evaluation system is formed, a text sequence is generated by analyzing a time sequence dependency relationship through a convolutional neural network, and the oral English training evaluation model of a deep learning technology is combined, so that the oral English training evaluation accuracy is improved. According to the method, the expressions of the user in the aspects of semantics, grammar and fluency can be accurately measured, the oral training level of the user can be comprehensively judged by the system by comparing the comprehensive evaluation coefficient with the preset qualified threshold value, and a personalized learning guide is provided according to a result.

The invention discloses a forest fire audio recognition method based on a BP neural network, a medium and a product in the technical field of forest fire recognition. The method comprises the following steps: acquiring forest fire audio data to be detected; extracting a Mel-frequency cepstrum coefficient (MFCC) based on the frequency domain features of the forest fire audio data to be detected; inputting the Mel-frequency cepstral coefficient MFCC into a pre-trained forest fire audio recognition model based on a BP neural network, and outputting a forest fire category; wherein the forest fire category comprises a forest fire and a non-forest fire. Compared with a traditional visual monitoring means, the method can cover a wider forest area, in the same monitoring range, in addition, model training based on the BP neural network can efficiently process a large amount of audio data and rapidly output an identification result, the efficiency and accuracy of forest fire identification are further improved, and the method is suitable for popularization and application. The problems of limited coverage range, high cost and low accuracy in the existing forest fire identification technology are solved.

The invention belongs to the technical field of power equipment state monitoring, and discloses a transformer fault detection method based on feature fusion. The method comprises the following steps: acquiring and preprocessing a transformer sound signal; feature extraction of a Mel frequency cepstrum coefficient (MFCC) and a power regularization cepstrum coefficient (PNCC) is carried out on the preprocessed sound signals; using a Fisher criterion-based feature fusion algorithm to perform weighted fusion on the MFCC feature parameters and the PNCC feature parameters to generate fused feature parameters; inputting the fusion feature parameters into a deep neural network model for training; inputting the obtained fusion feature parameters of the sound signals of the transformer to be detected into the trained deep neural network model to obtain a detection result of the fault category of the transformer; according to the method, MFCC and PNCC feature parameters are fused, MPFC features are obtained through dynamic weighting, frequency domain information, anti-noise information and sensitive frequency band information are integrated, and the detection accuracy and the anti-interference capacity are improved.

The invention relates to the technical field of voice recognition, in particular to a Bluetooth headset AI voice control method and system, and the method comprises the following steps: collecting a voice sample, carrying out the feature extraction of a voice signal through employing a Mel-frequency cepstrum coefficient, and generating voice feature data; and inputting the voice feature data into an acoustic model, and improving the recognition rate of the key instruction words by the acoustic model through learning features to obtain an optimized acoustic model. According to the method, acoustic feature capture is realized through voice signal feature extraction, the recognition accuracy of the key instruction is improved in cooperation with deep learning of acoustic features, the influence of different user speech speeds on the recognition effect is overcome by applying the time alignment technology of voice input, and the stability of the control instruction in different use scenes and speech speed changes is ensured. In addition, the recognition capability of a specific command is further mined and optimized by means of statistical characteristic analysis of voice, and efficient and automatic recognition and extraction of key control commands in continuous speech streams are completed.

The invention provides a track inspection robot abnormal sound detection method based on a convolution auto-encoder, and the method comprises the steps: firstly collecting sound data of the normal work of coal mine transportation equipment in an inspection region through sound pickup equipment carried on a track inspection robot, and carrying out the environment noise reduction of the sound data through a noise reduction algorithm; secondly, extracting Mel-frequency cepstral coefficient features of the sound of the coal mine transportation equipment through a feature extraction algorithm, inputting normal audio features into a convolutional auto-encoder network for training to obtain reconstructed audio features, and calculating a mean square loss function of the input normal audio features and the reconstructed normal audio features to obtain a reconstruction threshold value; and finally, calculating a mean square loss function of other audio features input into the auto-encoder network, and detecting the abnormal sound of the coal mine transportation equipment in a mode of judging whether the mean square loss function exceeds a reconstruction threshold value or not. According to the detection method, the problem that enough abnormal samples are difficult to accumulate in a short time due to the fact that the abnormal sound of the coal mine transportation equipment has occasionality and diversity can be solved, and the abnormal sound of the coal mine transportation equipment can be detected by the track inspection robot under the condition that the abnormal samples are lacked; and the production safety problem caused by the abnormity of the coal mine transportation equipment in the coal mine production can be early warned in time.

The invention relates to the field of mine intelligent management, and discloses an artificial intelligence autonomous identification model, which comprises a data acquisition module used for acquiring visual data, infrared data, audio data and environmental data from a coal mine site; the data preprocessing module is used for carrying out scale normalization, data enhancement, short-time Fourier transform, Mel frequency cepstrum coefficient extraction and normalization processing on the collected data; and the feature extraction module is used for extracting features from the visual data, the infrared data, the audio data and the environment data through a deep neural network. And through a multi-modal information fusion technology, the adaptability to a complex environment in mine operation is improved, the complementarity of different modal data is fully mined, and the recognition precision and robustness are remarkably improved. And an introduced feedback and self-learning optimization mechanism enables the model to be automatically adjusted according to real-time data, so that the stability and adaptability in a mine environment are enhanced.

The invention relates to a water supply network leakage identification method and device based on data enhancement and hybrid neural network architecture, equipment and a medium, and the method comprises the steps: employing a generative adversarial network to generate a simulation pipeline vibration audio signal, and combining the simulation pipeline vibration audio signal with a real pipeline vibration audio to construct a pipeline vibration audio signal data set; performing feature fusion on the Mel-frequency cepstral coefficient feature matrix and a first-order difference matrix of Mel-frequency cepstral coefficients to determine a feature fusion matrix of each pipeline vibration audio signal frame; by taking the feature fusion matrix as a training sample and the leakage state of the pipeline vibration audio signal as a sample label, training a CNN-Bi LSTM hybrid neural network model to determine a water supply network leakage detection model; and inputting the to-be-identified pipeline vibration audio signal into the water supply network leakage detection model to determine whether the to-be-identified pipeline vibration audio signal is in a leakage state or a non-leakage state. According to the invention, the precision, robustness and generalization ability of leakage detection are significantly improved.

The invention discloses an agricultural disease and pest dialect speech intelligent recognition method based on a deep learning technology, and the method comprises the steps: combining a Mel-frequency cepstral coefficient with a convolutional neural network, and dividing a whole process into two stages, the pre-training stage comprises the steps of recording and storing a long voice file, extracting the characteristics of voice signals in the file and training a neural network model, and the retraining stage comprises the steps of recording and storing a short voice file, extracting the characteristics of the voice signals in the file, verifying a test result, adjusting model parameters and storing an optimal model; the dialect voice information reported by monitoring personnel in an agricultural field is intelligently recognized by considering accent of people in different regions, so that the recognition accuracy of complex dialect voice signals is effectively improved, and the recognition method is particularly suitable for understanding related terms of agricultural diseases and insect pests.

The invention discloses an agricultural product wholesale market voice automatic order generation system based on artificial intelligence, and relates to the technical field of order management. Comprising an order template generation unit used for generating an order template; the acquisition unit is used for acquiring voice information; the first extraction unit is used for extracting Mel-frequency cepstral coefficient characteristics and residual Mel-frequency cepstral coefficient characteristics of the voice information; the feature splicing unit is used for splicing the features; the operation unit is used for taking the splicing features as input of a speech recognition model to obtain text information; the second extraction unit is used for extracting product names and product quantities in the text information; the matching unit is used for matching the product names with agricultural product names in an agricultural product database to determine agricultural products; and the adding unit is used for adding the agricultural products and the product quantity to the order template to obtain an agricultural product wholesale order. The system disclosed by the invention can improve the order generation efficiency, improve the user experience and improve the operation efficiency of the market.

The invention discloses a bird sound recognition method based on multi-model integration. The method comprises the following steps: (1) obtaining a bird sound signal and preprocessing data; (2) extracting key features from the bird sound data by combining Mel-frequency cepstrum coefficient, short-time Fourier transform and decibel conversion feature extraction methods; (3) a plurality of improved pre-training convolutional neural network models are used for training; each convolutional neural network model has different structures or parameter settings so as to capture different features of bird sounds; (4) designing an integration module by using an exponential smoothing method and a weighted smoothing method, and integrating a plurality of trained convolutional neural network models; output results of all the models are fused; (5) carrying out comprehensive performance evaluation on the integrated model; according to the method, the overall accuracy of bird sound recognition is remarkably improved.

The invention provides a smart classroom interaction analysis method based on double-layer architecture voice segmentation, and relates to the technical field of voice segmentation, and the method specifically comprises the following steps: extracting the voice features of a voice signal through employing a Mel-frequency cepstrum coefficient MFCC; designing a text-enhanced multi-scale time sequence-based perception time delay neural network, performing coarse screening on voice features, and dividing an audio clip into a single-speaker clip and a multi-speaker clip; and inputting the coarsely screened multi-speaker segment into a sliding window segmentation model SW-NIF fused with adjacent window information, and positioning speaker conversion points in the multi-speaker segment. And training the constructed model on the data set and verifying the model. According to the technical scheme, the problems that in the prior art, the segmentation problem of the classroom audio is neglected, and only the classroom audio is simply segmented for subsequent tasks, so that speakers in audio clips are mixed, and the analysis effect is affected are solved.

The invention provides a blood pressure detection and classification system and method based on a neural network, a medium and a terminal. Mel-frequency cepstral coefficient feature extraction, first heart sound time domain feature extraction and second heart sound time domain feature extraction are performed on acquired heart sound signal real-time data; the extracted Mel frequency cepstral coefficient feature data, the first heart sound time domain feature data and the second heart sound time domain feature data are used as model features to be input, time domain features and frequency domain features are included, and comprehensive coverage of time domain information and frequency domain information is achieved. The multi-input time domain convolutional neural network model is used for processing the three feature inputs and fusing the three feature inputs, the current blood pressure state of the user can be accurately detected, convenience and rapidness are achieved, and the result is accurate. The algorithm for extracting the frame where the heart sound peak point is located based on the MFCC0 is achieved, the influence of noise can be effectively avoided, the algorithm is simpler and more accurate, meanwhile, higher fault tolerance is achieved, and the first heart sound and the second heart sound can be accurately distinguished.

The invention relates to the technical field of power equipment monitoring, and particularly discloses a transformer fault voiceprint detection method and system based on multi-spectrum feature fusion, and the method comprises the steps: obtaining voiceprint sample data of a transformer, carrying out the processing of the de-noised voiceprint data, obtaining a Mel-frequency cepstrum coefficient, and carrying out the detection of the Mel-frequency cepstrum coefficient; calculating a first-order difference coefficient and a second-order difference coefficient based on the Mel-frequency cepstral coefficient to obtain Mel-frequency cepstral coefficient characteristics, first-order difference coefficient characteristics and second-order difference coefficient characteristics; the first-order difference coefficient features and the second-order difference coefficient features are endowed with weights, and in combination with the Mel-frequency cepstral coefficient features, weighted Mel-frequency cepstral coefficient feature vectors are obtained; performing feature extraction on the de-noised voiceprint data to obtain voiceprint slice feature vectors; according to the method, effective features can be accurately extracted in a complex noise environment, and the reliability and adaptability of transformer fault detection are improved.

The invention relates to a forged voice detection method adopting two-dimensional map attention, and the method comprises the steps: carrying out the pre-emphasis processing of an original voice, and extracting the linear frequency cepstrum coefficient features of each frame; gMM modeling is carried out on real voice and forged voice by using a BP algorithm according to linear frequency cepstrum coefficient features, iterative operation is carried out on training data by using an expectation maximization algorithm until convergence, the number of voice frames is counted, the LGP of each frame of voice feature in each Gaussian component is calculated, a constant term is subtracted, and standardization processing is carried out; according to the method, the Gaussian mixture model is modeled by adopting a bidirectional subdivision method (BP), so that the difference of mean vectors of adjacent Gaussian components is relatively small, the dependency relationship between the Gaussian components can be effectively captured by two-dimensional convolution, a clearer and tighter feature relationship is provided for a graph attention module, and the image attention is more accurate. According to the method, the feature space structure is optimized from local to global, and the performance of forged voice detection is improved.

The invention discloses a voice emotion recognition method based on multiple scales and multiple features, and belongs to the technical field of artificial intelligence. The method comprises the following steps: firstly, preprocessing an audio signal and extracting a spectrogram and a Mel-frequency cepstral coefficient; then, a residual network, a bidirectional long-short-term memory network and a HuBERT pre-training model are respectively utilized to extract spectrogram high-order spatial features, time sequence context features and voice semantic embedding features; secondly, inputting the first two features into a multi-dimensional multi-scale feature extraction module to extract richer time-frequency features, performing deep fusion by using a multi-layer cross attention mechanism, and performing weighted fusion with speech semantic embedded features; and finally, all the advanced features are spliced, and a final emotion category is recognized through a full-connection classifier. According to the invention, through combination of multi-scale feature extraction and an advanced fusion mechanism, the problem of insufficient complex emotion modeling ability in the prior art is effectively overcome, and the accuracy and robustness of voice emotion recognition are significantly improved.

The invention relates to the technical field of equipment monitoring, in particular to a loss and fatigue monitoring method for water gate opening and closing equipment. The method comprises the following steps that multi-mode time sequence data are synchronously collected through a vibration sensor, a temperature sensor and an acoustic emission sensor, and the multi-mode time sequence data comprise a vibration signal, a temperature signal and an acoustic emission signal; performing wavelet packet decomposition on the vibration signal, and extracting an energy ratio of a preset frequency band as a vibration energy feature; calculating a temperature rise rate and a local range of a sliding window of the temperature signal as temperature characteristics; extracting a Mel-frequency cepstrum coefficient from the acoustic emission signal as an acoustic feature; the vibration energy characteristics, the temperature characteristics and the acoustic characteristics are spliced into a multi-dimensional time sequence characteristic matrix according to time steps. According to the method, the maximum probability state transition path is solved by using the hidden Markov model, and accurate identification and prediction of the equipment loss and the fatigue state are realized.