427 results about "Sound recognition" 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.

A multi-dimensional hydropower station control panel cabinet working condition abnormity monitoring method based on sound recognition is characterized in that a sound pickup, a mutual inductor, an infrared image monitor, a switch node sensor and the like are installed at different positions of a control panel cabinet to acquire multi-dimensional data including voiceprint, voltage, current, temperature, images and switch displacement signals; the voiceprint signals are subjected to pre-emphasis, framing, FFT transformation, Mel frequency filter bank application, MFCC feature extraction and the like, and feature vectors are extracted by using UBM, GMM and MAP algorithms. A PLDA algorithm is adopted for data analysis and fault judgment, multi-dimensional data comprehensive scoring is fused, the fault type is determined, alarm information and processing measures are output, and the system has the advantages of comprehensive multi-dimensional data acquisition, advanced signal processing technology, scientific and accurate fault judgment, high practicability and the like.

The invention discloses an automobile environment sound enhancement method and device, electronic equipment and a storage medium, which are used for solving the technical problems of low automobile external environment sound recognition precision and poor environment adaptability in related technologies. The method comprises the following steps: acquiring audio data outside a vehicle and video data outside the vehicle; scene recognition is carried out according to the vehicle exterior audio data and the vehicle exterior video data, and the current environment sound type and the current driving environment are obtained; extracting visual information from the video data outside the vehicle, and extracting audio information from the audio data outside the vehicle; carrying out multi-modal data fusion based on comprehensive confidence in combination with the visual information and the audio information to obtain an effective scene judgment result; and based on the current driving environment, the current environment sound type and the effective scene judgment result, the external environment sound is enhanced through a sound unvarnished transmission enhancement strategy. Therefore, environmental sound recognition accuracy can be improved based on multi-modal data fusion, environmental sound enhancement is realized in combination with a sound unvarnished transmission enhancement strategy, and environmental adaptability is improved.

The invention discloses a sound acquisition and processing system based on cooperation of multiple microphone arrays. The system comprises a sound acquisition module, a multi-channel signal preprocessing module, a sound signal feature extraction module, an abnormal sound recognition module, a sound source positioning module and an alarm module. A multi-channel mixed data signal is collected through a circularly-arranged multi-microphone array formed by a plurality of microphones, after echo cancellation, wave beam domain noise reduction and multi-sound-source separation, a single-sound-source feature vector is extracted, according to the single-sound-source feature vector, abnormal sound including explosion, screaming or glass breakage is recognized through a BiLSTM and an attention mechanism model, and the abnormal sound is recognized through an attention mechanism model. And the GCC-PHAT and MDS-MUSIC algorithms are combined to position abnormal sound production, and alarm information is generated. According to the invention, accurate identification, positioning and alarm of the abnormal sound can be realized, and the real-time performance, the accuracy and the multi-target processing capability of abnormal sound monitoring in a complex environment can be obviously improved.

The invention discloses a double-branch sound-vibration fusion event recognition and positioning method based on DAS and AI, and the method comprises the steps: synchronously collecting sound and vibration data, and constructing a sound recognition branch and a vibration positioning branch; the sound branches extract multi-scale joint features through time-frequency domain feature fusion, weights of CNN and BiLSTM are dynamically adjusted to realize adaptive fusion, and event types and confidence coefficients are output; and the vibration branch calculates an initial coordinate by using a four-point space-time weighted optimization method, performs position fine tuning in combination with an ASTCN network, and outputs a final event position. Performing probability distribution verification by fusing double branch results and adopting a dynamic likelihood ratio evaluation mechanism, and outputting a final judgment result; intelligent event classification is achieved through the voice recognition branch, high-precision event space-time positioning is achieved through the vibration positioning branch, intelligent cooperation and system optimization of multi-modal data are achieved through the fusion and verification module, and the bottlenecks of the traditional technology in the aspects of recognition precision, positioning errors and system robustness are effectively broken through.

A system for presenting audio content to a user. The system comprises one or more microphones coupled to a frame of a headset. The one or more microphones capture sound from a local area. The system further comprises an audio controller integrated into the headset and communicatively coupled to an in-ear device worn by a user. The audio controller identifies one or more sound sources in the local area based on the captured sound. The audio controller further determines a target sound source of the one or more sound sources and determines one or more filters to apply to a sound signal associated with the target sound source in the captured sound. The audio controller further generates an augmented sound signal by applying the one or more filters to the sound signal and provides the augmented sound signal to the in-ear device for presentation to a user.

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 relates to the technical field of voice recognition, in particular to an implementation method and device of a multi-channel voiceprint recognition system, and the implementation method comprises the steps of multi-channel data acquisition and synchronization, signal preprocessing and enhancement, feature extraction and fusion, model training, real-time deployment and adaptive optimization. Compared with the problems that a traditional multichannel voiceprint recognition system depends on a fixed beam forming algorithm and an independent clock synchronization module, the synchronization error is large, manual parameter adjustment is needed for noise suppression, and generalization is poor, hardware-level clock synchronization is achieved through a PTP protocol, and the accuracy of noise suppression is improved. The method combines an end-to-end neural network to automatically learn noise distribution and a sound source space position, dynamically generates a beam forming weight, can improve the voice quality in a complex noise scene without manual intervention, remarkably reduces the interference of a synchronization error on sound source positioning, and enables the precision and stability of far-field voice enhancement to reach a new level.

The invention discloses a vehicle-mounted voice identification and positioning intelligent early warning system and method, and relates to the technical field of vehicle-mounted intelligent early warning. The system comprises a sound detector module which collects an audio signal of a surrounding environment in real time, and a sound recognition module which analyzes the audio signal through a deep learning model and recognizes a sound source type. And the calibration module performs space-time calibration to ensure data synchronization and alignment of the sensors. The positioning module combines time difference of arrival (TDOA) and a sound intensity attenuation model, and optimizes sound source positioning through particle swarm optimization (PSO) and extended Kalman filter (EKF) technologies. The risk assessment module assesses the collision risk based on the sound source position, the shielding state and the object type, gives an alarm to a driver in time through the early warning module, and automatically triggers a deceleration instruction. And the self-learning module dynamically adjusts the early warning sensitivity and the noise compensation coefficient through a federated learning framework updating model. The environmental adaptability of the vehicle-mounted early warning system is improved, and the vehicle-mounted early warning system has remarkable safety improvement and wide application prospects.

The invention relates to the technical field of sound recognition, in particular to an optical fiber sensing voiceprint feature analysis model construction method of a composite neural network, and the method comprises the steps: collecting a sound signal through distributed optical fiber sensing, setting a sound frequency amplitude threshold value, and extracting a sound signal of an abnormal interval; carrying out noise reduction processing on the collected signals and extracting voiceprint features; constructing an unsupervised model to calculate an outlier score value, and combining a threshold value to judge whether the signal is an abnormal signal; carrying out principal component analysis on the abnormal signal, and carrying out feature compression and mapping; a composite neural network model is trained based on the extracted features, and multi-class voiceprints are recognized; and an uncertainty evaluation mechanism is introduced, a classification result is dynamically adjusted according to confidence, low-confidence data is marked as unidentified and collected and classified again, and self-learning and iterative optimization of voiceprint recognition are realized. The method provided by the invention has high precision, high robustness and strong generalization ability, and is suitable for optical fiber voiceprint event recognition in a complex environment.

The invention discloses a power distribution line bird repelling method and system based on Internet of Things edge calculation, and relates to the technical field of power distribution network safety. The system comprises: a bird condition acquisition module configured to obtain a bird audio and a bird image to be detected; a model identification module configured to identify the bird audio by using a bird sound identification model and identify the bird image by using a bird image identification model; the controller module is configured to integrate the bird audio recognition result and the bird image recognition result to obtain the type of the bird; the intelligent decision-making module is configured to generate a bird repelling strategy according to the types of the birds; and the bird repelling module is configured to repel birds according to the bird repelling strategy. According to the invention, birds are identified by utilizing edge calculation, so that different bird repelling modes are adopted for different birds, and intelligent and effective modern bird repelling is realized.

The invention discloses an audio coal gangue identification method. The method comprises the following steps: S1, collecting audio signal data in a coal caving process of a related field of a fully-mechanized face; s2, preprocessing the audio signal data to obtain the audio signal data after noise reduction; s3, performing data calibration on the audio signal features; s4, constructing an audio coal gangue recognition algorithm model; and S5, outputting a coal and gangue recognition result by using the audio coal and gangue recognition algorithm model. According to the invention, a novel audio identification system mainly based on the audio acquisition sensor is utilized, automation of top coal caving of the fully-mechanized caving face is realized through voice identification of coal caving, gangue caving and non-coal caving of the fully-mechanized caving face, and the system has the characteristics of high-precision coal caving and gangue identification and improvement of coal caving efficiency.

The invention discloses a newborn cry recognition system based on machine learning, which belongs to the technical field of intelligent newborn nursing and comprises a data acquisition module, a feature extraction module, a feature selection module, a newborn cry recognition module and a recognition result feedback module. According to the method, the improved badger optimization algorithm is adopted to perform feature selection on the cry audio feature set, key features beneficial to distinguishing different cry categories are automatically selected, manual intervention errors are avoided, feature selection can be better and flexibly adjusted according to individual differences, and it is ensured that the system has high recognition accuracy on different newborn cry; according to the method, the mixed kernel function support vector machine model combined with the K nearest neighbor algorithm is adopted to carry out newborn cry recognition, local similarity improvement between samples is captured, boundaries between different cry categories are accurately divided, and overlapping between the categories is avoided, so that different types of cry are recognized more accurately and efficiently, and the overall usability of cry recognition is improved.

The invention belongs to the technical field of traditional Chinese medicine and software, and particularly relates to a traditional Chinese medicine syndrome differentiation aid decision-making method based on trans-modal attention Transform. The invention provides traditional Chinese medicine syndrome differentiation based on cross-modal attention Transform, and aims to explore a more scientific and systematic traditional Chinese medicine syndrome differentiation method by integrating multi-modal data such as visual sense, auditory sense, language, pulse condition and the like. Specifically, information such as complexion and tongue coating is obtained by inspection diagnosis through an image processing technology; the auscultation and diagnosis obtains sound information such as respiration and cough through a sound recognition technology; the inquiry analyzes the chief complaint and symptom description of the patient through a natural language processing technology; pulse condition data are collected through the sensor technology in the clinics. A multi-modal hierarchical dialectical logic framework is constructed, an exclusive attention mechanism is designed for each dialectical method, the overall view and dialectical thinking of traditional Chinese medicine are fully reflected, and a more reasonable dialectical result is generated.

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 discloses a monitoring and traceability system for agricultural product supply chain transportation, and particularly relates to the field of supply chain transportation monitoring and traceability, which comprises the following steps: carrying out damage resistance quantitative evaluation of sliding, collision and extrusion on each agricultural product category in a supply chain, training a sound recognition model based on marked audio signal time-frequency domain features, collecting cargo information and audio data of each link segment in the transportation line, and uploading the cargo information and the audio data to a monitoring center; classifying and recognizing the audio data through a voice recognition model, and calculating a damage assessment score of each link segment in combination with a damage resistance quantitative index; and carrying out visual labeling on a damage evaluation result, sending an abnormal signal to a corresponding link segment, adjusting the transportation density to reduce the damage risk, realizing accurate traceability of the transportation link with abnormal loss, and ensuring that the damage degree of goods in transportation is controllable.

The invention relates to the technical field of machine room monitoring, in particular to an Internet of Things monitoring method for unattended machine room monitoring, comprising an environment monitoring module, a comprehensive gateway, a radar module, a sound collection module and a machine room camera group, the environment monitoring module is used for monitoring machine room environment data; the sound collection module is used for collecting sound data in the machine room in different time periods and transmitting the sound data to the sound analysis module; the machine room camera group is used for acquiring video data in a machine room and monitoring intruders; the radar module is used for multi-target tracking and positioning; the comprehensive gateway comprises a video analysis module and a sound analysis module, and is used for generating an alarm signal according to the machine room environment data, the sound data and a video analysis result. According to the method, video monitoring, millimeter wave radar detection and sound recognition technologies are comprehensively applied, comprehensive monitoring of the internal environment of the machine room is achieved, the detection precision of abnormal events and the accuracy of fault diagnosis are improved, and meanwhile the visual effect of environment monitoring is enhanced.

The invention provides a method for tracking a speaker based on a panoramic camera and a close-up camera. The method comprises the steps that the panoramic camera shoots all people into a panoramic picture; based on a sound source of a speaker and / or analyzing facial actions of all people in the panoramic picture, positioning face position information of the speaker in the panoramic picture; based on the position relation between the panoramic camera and the close-up camera and the face position information of the speaker, the angle and the focal length of the close-up camera are determined, and close-up shooting is carried out on the speaker; the face position of the speaker in the close-up picture is analyzed, and the close-up camera is finely adjusted, so that the speaker is centered in the close-up picture. The position of the speaker is positioned by combining face detection and voice recognition technologies, and the close-up camera picture is triggered to track the close-up picture of the speaker, so that the conference control operation is avoided, and the intelligence of the conference terminal is remarkably improved.

The invention belongs to the technical field of biodiversity observation, and relates to an animal species recognition method based on a microphone array and a sound recognition model, which comprises the following steps of: 1) acquiring three-dimensional space environment sound in real time by using the microphone array; 2) processing the collected three-dimensional space environment sound to obtain a sound signal with improved quality; and 3) based on the quality-improved sound signal, an edge-arranged convolutional attention neural network sound recognition model is adopted to carry out animal species recognition. Accurate recognition of animal sound in a complex acoustic environment is realized, so that animal species categories can be effectively detected and recognized.

The invention discloses a baby cry recognition method for white noise equipment, and relates to the field of audio processing and intelligent acoustic recognition, and the method comprises the steps: collecting a pure reference signal, a first-path signal and a second-path signal, carrying out the synchronization and preprocessing, and obtaining a mixed audio signal based on the first-path signal; a residual signal is calculated through an adaptive echo cancellation algorithm; calculating an acoustic masking parameter based on the residual signal, the pure reference signal, and the ambient noise estimate; constructing a three-level recognition processing path including lightweight feature detection, registration voiceprint comparison and multi-modal information fusion; based on the numerical range of the acoustic masking parameter, selecting an identification processing path, and determining a crying event of the target infant from the residual signal; and triggering a corresponding grading alarm based on a crying event confirmation result. A three-level identification path is scheduled through acoustic masking parameters, and accurate and low-power-consumption baby crying monitoring under strong interference is realized by fusing multi-modal information.

The invention discloses an electric blanket control method and system based on AI voice interaction, and the method comprises the steps: collecting a noisy voice signal through a microphone array, carrying out the filtering of an analog front-end circuit, the echo elimination of an AEC chip, and the noise reduction of a DSP, and obtaining a high-signal-to-noise-ratio pure voice. The AI or voice recognition chip extracts features and matches the features with a pre-stored template, and the master control MCU drives the voltage regulation circuit to regulate the heating power according to an instruction through PWM (Pulse Width Modulation). And dynamically adjusting the power of each region according to the temperature difference by using a closed-loop control algorithm according to ergonomic partitioning. The intelligent electric blanket solves the problems that a traditional electric blanket is inconvenient to operate, inaccurate in temperature adjustment and lack of effective safety protection, and an existing intelligent electric blanket is insufficient in voice interaction function, convenient voice control, accurate partition temperature control and comprehensive safety protection are achieved, and the user experience is improved.

The application discloses a kind of based on DAS and AI's double-branch sound vibration fusion event identification and positioning method, including synchronous acquisition sound and vibration data, construct sound identification branch and vibration positioning branch;Sound branch is extracted multi-scale joint feature by time-frequency domain feature fusion, the weight of dynamic adjustment CNN and BiLSTM is realized adaptive fusion, output event type and confidence;Vibration branch uses four-point space-time weighted optimization method to calculate initial coordinate, position fine-tuning is carried out in combination with ASTCN network, and the final event position is output.The results of fusion double-branch are used, and the probability distribution verification is carried out using dynamic likelihood ratio evaluation mechanism, and the final judgment result is output;The application realizes intelligent event classification by sound identification branch, high-precision event space-time positioning is realized by vibration positioning branch, and intelligent collaboration and system optimization of multi-modal data are realized through fusion and verification module, effectively break through the bottleneck of traditional technology in identification accuracy, positioning error and system robustness.

The invention belongs to the field of voice recognition, and discloses a voice recognition method based on an acoustic model, computer equipment and a storage medium. The method comprises the following steps: acquiring voice features of to-be-recognized voice; inputting the voice features into an acoustic model, and outputting a recognition result by the model; wherein the time sequence processing network layer firstly determines the ratio of current input future frames needing to be pre-watched to context information through a pre-trained gating fusion unit, then calculates the number of the future frames needing to be pre-watched based on the ratio, obtains the corresponding future frames, calculates long-time context representation in combination with the future frames, processes the long-time context representation and outputs the long-time context representation to the next layer of network. According to the method and the device, the problem of static binding of delay and accuracy in the prior art is solved by dynamically adjusting the number of the future frames to be pre-watched, low-delay response to simple command words is realized, the recognition accuracy is improved through multiple future frames to be pre-watched for easily-confused instructions, the balance of the delay and the accuracy is realized, and the performance of a voice recognition system and the user experience are improved.

The invention discloses a chicken abnormal sound recognition method, system and device for a large-scale farm and a storage medium. The method comprises the following steps: acquiring sound data of a chicken as a first audio; taking the preprocessed first audio as a second audio; taking the second audio frequency after the secondary noise reduction as a third audio frequency; performing sound endpoint detection on the third audio, and taking an obtained effective sound fragment as a fourth audio; performing data enhancement on the fourth audio, and taking the fourth audio after data enhancement as a fifth audio; converting the audio clip of the fifth audio into a Mel spectrogram, extracting a corresponding first-order difference Mel spectrogram and a corresponding second-order difference Mel spectrogram based on the Mel spectrogram, and performing feature fusion to obtain corresponding three-channel Mel fusion features; and inputting the Mel fusion feature into a model for identification to obtain an event category result corresponding to the audio. According to the invention, abnormal chicken sounds in the chicken farm can be accurately identified, and the breeding efficiency is improved.

The invention discloses a water turbine fast gate working condition abnormity monitoring method based on sound recognition, and the method comprises the steps: evaluating the working condition of a water turbine fast gate through multi-feature data, which comprises a voiceprint signal, an infrared temperature measurement signal and a vibration signal collected on a fast gate hoist, and a position signal above a fast gate as the features of fault state recognition; and constructing a state evaluation model based on linear probability discrimination, training the feature information, integrating to form a database under different fault types of the water turbine fast gate, and inputting real-time data to obtain the fault type with the highest PLDA ratio, namely the fault type of the to-be-diagnosed feature sequence. Fault features and fault diagnosis of the rapid gate of the water turbine can be extracted in real time.

The invention discloses a green peacock ecology monitoring method and system based on chirp. The method comprises the following steps: firstly, constructing a target data set; the target data set comprises a green peacock chirp data set, a bird sound data set, an interference sound data set and an environment sound data set; constructing a deep learning network model according to the target data set; carrying out sound data acquisition on the target monitoring area to obtain target sound data; performing sound information extraction on the target sound data to obtain target information, and identifying the target information through a deep learning network model to obtain a sound identification result; the voice recognition result comprises green peacock whistling, various bird whistling, interference sound and environment sound; and finally, according to a voice recognition result, green peacock ecological data statistics is carried out. The green peacock ecological monitoring method can improve the green peacock ecological monitoring accuracy, and can be widely applied to the technical field of sound signal processing.

The utility model relates to the technical field of dam spreading pig breeding, and discloses a pig house comprehensive environment automatic measuring device, which comprises a hanger rail and a breeding inspection machine, and the breeding inspection machine comprises a conveyor running on the hanger rail and an inspection box; an inspection camera, a programmable logic controller, an image analysis module, a sound recognition module, an environment sensing module, a communication module and a power supply module are mounted on the inspection box; the environment sensing module comprises a temperature and humidity sensor, an ammonia gas sensor and a carbon dioxide sensor; the environment parameters, such as temperature, humidity, ammonia gas and carbon dioxide concentration, of the pig house are monitored in real time through the sensors and automatically adjusted according to needs so as to maintain the optimal breeding environment, the breeding environment is optimized, healthy growth of pigs is promoted, diseases are reduced, the breeding quality is improved, an automatic system reduces dependence on manual inspection and management, and the breeding efficiency is improved. And the labor cost is reduced.

The invention discloses a hierarchical tag generation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring audio information in a vehicle-mounted environment; performing voice recognition on the audio information, and extracting text information; in response to a received first prompt instruction, constructing a label to generate guide information; generating a plurality of basic tags of the text information by utilizing a first preset large model based on the tag generation guide information; in response to a received second prompt instruction, constructing label classification guide information; and based on the label classification guide information, generating hierarchical information of the plurality of basic labels by using a second preset large model. The first prompt instruction guides the generated basic label to capture deeper semantic association of the audio information, the second prompt instruction guides the label classification to find the implicit relationship between the labels, and the isolated labels establish a label system with hierarchical relationship. And the accuracy of the application of the tag in the fields of personalized recommendation and vehicle-mounted safety is improved.

A sound-recognition-based method for monitoring an operating condition abnormity of an oil pump electric motor and outlet pipes thereof. Applying soundprint recognition technology to a speed-regulating hydraulic system of a hydropower station, and rational layout of on-site soundprint sensors realize real-time monitoring of operating conditions of an oil pump electric motor and outlet pipes thereof, thereby improving the intelligence level of device management, and achieving an industrial demonstration effect. By means of deep learning analysis of a soundprint fault sample library combined with multi-dimensional factors such as pressure, liquid level and temperature, a soundprint-recognition-based multi-dimensional-factor logical determination process for abnormal operating conditions of an oil pump electric motor and outlet pipes is designed, such that real-time monitoring and rapid locating of abnormal operating conditions such as base vibration, lubricating oil deficiency in an oil pump electric motor, pump body blade fracture, check valve malfunction, incomplete closure or internal leakage of a drain valve, frequent loading and unloading of an oil pump, and servomotor pipe pulsation are realized, so as to promptly use response measures such as automatic switching of main and standby oil pump electric motor units or automatic adjustment of unit load. Using soundprint sensors and soundprint recognition technology to monitor the state of on-site devices in real time eliminates uncertainties in manual inspection, and improves the fault diagnosis and analysis efficiency.

The invention discloses a remote recognition system based on spatial respiratory tract abnormal sound, and relates to the technical field of sound recognition. The multi-mode sensor array is used for collecting breathing sound in a non-contact mode and obtaining sound source space information of the breathing sound, the cross infection risk is eliminated, and the limitation that a traditional stethoscope can only collect sound signals is broken through. The spatial audio processing module performs preset audio processing on the breathing sound to obtain a breathing sound signal, and obtains sound source control characteristics based on the sound source spatial information; the feature extraction module extracts time-frequency joint features and nonlinear dynamic features from the breath sound signals, and performs feature fusion on the time-frequency joint features and the nonlinear dynamic features and sound source control features to obtain multi-dimensional feature vectors; and the abnormal sound recognition model performs abnormal sound type recognition and spatial positioning on the multi-dimensional feature vector. Therefore, the environmental sound interference can be effectively solved, the type and position of the breathing sound can be intelligently identified, detected and positioned, the identification accuracy of the breathing sound is effectively improved, and meanwhile, the dependence on medical staff is also reduced.