226 results about "Sound recognition" patented technology

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 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 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 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.

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 provides a power plant equipment sound abnormity identification and health prediction method based on granular computing and an LSTM network, and the method comprises the steps: employing an array pickup and a high-dynamic-range microphone array in a complex and high-noise background environment of a power plant, and combining an anti-interference filtering and beam forming algorithm, thereby achieving the sound abnormity identification and health prediction of the power plant equipment. According to the method, directional, multi-channel and non-contact sound acquisition is carried out on key parts of equipment, acquired sound signals are preprocessed, converted into time domain, frequency domain and time-frequency domain representations and coded into multi-dimensional numerical vectors, and compared with a rule-based expert system, the method has higher generalization ability and real-time response ability; a large language model is introduced, so that the output is closer to an engineering language and is suitable for operation and maintenance personnel to understand and execute; a self-defined knowledge base or safety semantic filtering is supported, and closed-loop deployment in an industrial field is facilitated; the system can be in butt joint with an intelligent inspection system, and full-link linkage of voice recognition, health assessment and suggestion generation is achieved.

The invention relates to the technical field of vehicle safe driving, in particular to an alcohol detection and vehicle control system for safe driving of a driver, which comprises an alcohol detection system, a core control system and an application monitoring system, the alcohol detection system comprises an air pressure detection sensor, a sound recognition sensor, a passive alcohol detection sensor, an active alcohol detection sensor, an infrared body temperature sensor, a camera, an NFC module and a fingerprint recognition module; the core control system comprises an ignition switch control circuit, a 4G communication module, a positioning module, a power supply circuit, a voice module, an automobile CAN bus module and a master control core system. The application monitoring system is connected with the cloud application system through the Internet, and the collected local data and the detection result are reported to the server application monitoring system, so that the risk of alcohol in the body of the driver to safe driving can be reduced.

The invention discloses a construction and recognition method for a sound source recognition network of vehicles in a highway tunnel, and the method comprises the steps: setting a distributed microphone array in the tunnel, and collecting a vehicle audio signal; a MobileNetV3 model based on the Mel frequency spectrum is constructed; the Mel spectrum feature extraction module is used for taking the Mel spectrum feature extracted by the Mel spectrum feature extraction module as input, taking a vehicle audio signal type as output, and training a MobileNetV3 model based on the Mel spectrum to obtain a sound recognition model; constructing a sound source localization model; according to the method, the MobileNetV3 model based on the Mel frequency spectrum is adopted for sound recognition, the sound source positioning model is constructed in a combined mode for sound source positioning, the MobileNetV3 model and the sound source positioning model work cooperatively, the feature description capability of abnormal sound of a vehicle is enhanced, the influence of tunnel echo and environment noise on recognition is effectively reduced, accidents in the tunnel are found in time and positioned accurately, and the method is suitable for popularization and application. The recognition and positioning accuracy of the vehicle sound source in the complex tunnel environment is improved, and the technical problem that in the prior art, the recognition precision of the accident sound in the tunnel is not high is solved.

The invention discloses a wild boar activity intelligent early warning and grading prevention and control method based on AI and thermal imaging, a sensing system carries out thermal imaging processing and camera shooting monitoring on wild boars in corresponding areas in the air through thermal imaging and camera shooting functions of an unmanned aerial vehicle, and a ground infrared camera array carries out infrared imaging processing on the wild boars around the ground; the sound sensor recognizes the sound of the wild boars, and the ground vibration sensor detects the running of the wild boars and the digging of the ground, and relates to the technical field of early warning, prevention and control of the activities of the wild boars. According to the wild boar activity intelligent early warning and grading prevention and control method based on AI and thermal imaging, a sensing module is arranged in a system, and an unmanned aerial vehicle module, a ground infrared imaging module, a sound recognition processing module and a ground vibration sensing module are matched with one another to perform thermal imaging processing on wild boars so as to obtain specific information of a wild boar group; subsequent driving and marking operations are facilitated while continuous monitoring is carried out, and the danger level of the wild boar herd is analyzed through the analysis module.

An object of a system according to an embodiment is to accurately identify the pitch of a sound and provide visual and auditory feedback.SOLUTION: A system includes a sound recognition and analysis unit, a visual display unit, and an auditory feedback unit. The sound recognition and analysis unit identifies the pitch of the sound using the generated AI. The visual display unit visually displays the pitch of the sound identified by the sound recognition and analysis unit. The auditory feedback unit aurally feeds back the pitch of the sound specified by the sound recognition and analysis unit.SELECTED DRAWING: Figure 1

The invention relates to an abnormal sound identification method and device for an electric drive speed reducer, a vehicle and a readable storage medium, and the method comprises the steps: collecting the abnormal sound data of the electric drive speed reducer of at least one vehicle model; constructing an abnormal sound fault tree of the electric drive speed reducer according to the fault category of the abnormal sound data; and at least one abnormal sound key feature of the fault category is extracted according to the abnormal sound fault tree to construct a structured abnormal sound feature database, and an abnormal sound recognition model of the electric-driven speed reducer is constructed by using the abnormal sound feature database, so that an abnormal sound recognition result of the target electric-driven speed reducer is output by using the abnormal sound recognition model. The abnormal sound fault tree of the electric drive system can be constructed by combining abnormal sound feature engineering and knowledge modeling, the abnormal sound intelligent identification model is established based on a knowledge and data dual-drive method, and a maturely trained AI program is put into a service store end, so that the market support frequency of research and development personnel can be greatly reduced, and the development efficiency is improved. And efficient and accurate fault judgment of abnormal sound of the electric-driven speed reducer is realized.

The application discloses a baby crying sound recognition method for white noise equipment, relates to the field of audio processing and intelligent acoustic recognition, and comprises the following steps: collecting pure reference signals, first signals and second signals for synchronization and preprocessing, and obtaining mixed audio signals based on the first signals; calculating residual signals through a self-adaptive echo cancellation algorithm; calculating acoustic masking parameters based on the residual signals, the pure reference signals and environmental noise estimation; constructing a three-level recognition processing path comprising light feature detection, registered voiceprint comparison and multi-modal information fusion; selecting a recognition processing path based on the numerical range of the acoustic masking parameters, confirming the crying event of the target baby from the residual signals; and triggering corresponding graded alarms based on the crying event confirmation result. The three-level recognition path is scheduled through the acoustic masking parameters, multi-modal information is fused, and accurate and low-power baby crying monitoring under strong interference is realized.

The present invention discloses an intelligent stop-barking method, device, and computer-readable storage medium. The method runs on an embedded terminal worn by a pet. The embedded terminal is built in with a preset pet barking model. The method includes: sound collection: obtaining a decibel value of ambient sound of the pet's surrounding environment; model comparison: if the decibel value of the sound is greater than a preset decibel value, then the sound collected is compared with the pet barking model and a comparison result is output; and output punishment: if the comparison result is greater than a preset punishment value, then the punishment module is triggered to stop the pet from barking. The technical solution, through machine learning models and signal processing techniques, enables high-accuracy dog barking sound recognition. It reduces reliance on powerful computing resources, and achieves stand-alone operation of data model, thereby improving feasibility and popularization.

The application provides a diversity biological collection and identification system, a high-definition camera and a microphone are mounted on a UAV platform, a plurality of groups of biological species and living habits are included in a database, the biological species and the living habits are in one-to-one correspondence, the living habits include sound characteristics, living traces, habitats and the like; a habit analysis module is used for obtaining animal traces in an image to be analyzed in an image analysis technology, a habit influence value is obtained by calculating the living trace reliability of all marked animal traces; a sound recognition module is used for obtaining animal calls or activity sounds in sound data as audio segments to be analyzed, a sound influence value is obtained by calculating the sound similarity of the marked audio to be analyzed; a comprehensive evaluation module is used for obtaining the number of biological samples to be analyzed, the habit influence value and the sound influence value, and obtaining the expected number of biological samples in a specified area by using a statistical algorithm.

The multifunctional electric heating surrounding furnace comprises a columnar machine body and an electric ceramic furnace, the electric ceramic furnace is arranged at the top of the columnar machine body, a main control circuit and a control panel are arranged in the columnar machine body, a loudspeaker and an atmosphere lamp are arranged on the columnar machine body, and the main control circuit is provided with a micro-control chip and a Bluetooth module which are electrically connected with each other. The loudspeaker, the atmosphere lamp, the control panel and the electric ceramic cooker are electrically connected with the main control circuit respectively; the main control circuit is further provided with a sound recognition module, the sound recognition module is electrically connected with the micro-control chip, the sound recognition module is provided with a sound pickup, and the sound pickup is arranged beside the loudspeaker. The Bluetooth module can be in communication connection with playing equipment (such as a mobile phone), receive audio signals of the mobile phone and send the audio signals to the micro-control chip, and the micro-control chip controls the loudspeaker to play music; in addition, the micro-control chip can control the atmosphere lamp to be turned on so as to generate a lamplight atmosphere.

The invention provides a motor abnormal sound detection method and device, and the method comprises the steps: collecting a sound pressure signal and a rotating speed signal of the operation of a motor, carrying out the synchronous processing of the sound pressure signal and the rotating speed signal, obtaining a synchronous original signal, carrying out the feature extraction of the synchronous original signal, and obtaining a feature vector; the feature vector comprises at least one feature component of a rotating speed deviation coefficient, a frequency band energy ratio, a dominant frequency and harmonic relation index and an amplitude attenuation rate, calculating an abnormal sound risk index by using the feature vector, determining an abnormal sound judgment threshold through a dynamic threshold updating strategy, and determining the abnormal sound by comparing the abnormal sound risk index with the abnormal sound judgment threshold. And outputting a motor abnormal sound detection result. According to the motor abnormal sound detection method provided by the embodiment of the invention, the sound pressure signal and the rotating speed signal are synchronously acquired, the multi-dimensional feature vector is extracted, the abnormal sound risk index is calculated, and self-adaptive judgment is performed based on the dynamic threshold strategy, so that an automatic abnormal sound recognition process based on multi-source signal fusion is realized, and the motor abnormal sound detection efficiency is improved.

The invention discloses a multi-mode underwater sound recognition method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: firstly collecting the current multi-source perception data of a target underwater sound signal; preprocessing the current multi-source sensing data, inputting the preprocessed data into a pre-trained multi-modal underwater acoustic signal classification model to discriminate the type, and outputting target acoustic signal type information; and finally, generating and outputting an identification result report according to the type information. Through multi-modal acoustic data fusion and deep model classification, the accuracy and robustness of underwater acoustic signal recognition are effectively improved, the method adapts to acoustic recognition requirements in a complex underwater environment, and reliable technical support is provided for acoustic signal analysis in the ocean field.

The invention discloses a pet voice recognition translation cloud training method and application, and relates to the technical field of voice recognition and machine learning, and the method comprises the steps of data set construction and preprocessing, model architecture establishment, two-stage training, lightweight optimization, incremental learning iteration, model evaluation and deployment, and application coverage of a multi-terminal scene. The emotion recognition accuracy is improved, the intention recognition accuracy is improved, knowledge distillation and quantitative perception training achieve model lightweight, and incremental learning enables iteration efficiency to be improved. According to the pet voice recognition translation cloud training method and the application, the problems of poor data adaptation, insufficient model optimization and low iteration efficiency of a traditional method are solved, the method is adaptive to various pets and complex environments, multi-terminal deployment is supported, an accurate human-pet communication solution is provided for scenes such as family pet raising and pet medical treatment, and the user experience is improved. And the method has high precision, practicability and expandability.

Methods and vehicle with sound visualization are provided. A vehicle includes a graphic projection display; exterior microphones mounted to the vehicle; and a processing device programmed to receive audio signals from the exterior microphones; retrieve map data in a region around the vehicle; identify from the audio signals a sound of interest; identify a location of a source of the sound of interest; determine a stationary status or a moving status of the source; when the source has the moving status, determining a direction and speed of movement of the source; ascertain from the map data and from the location, stationary status, moving status, direction, and / or speed, a preferred driving maneuver; determine a graphic exemplifying the preferred driving maneuver; and display the graphic upon the graphic projection display.

The present application relates to the technical field of sound recognition, and particularly relates to a sound recognition system for sheep feeding behavior. The technical scheme comprises a sound collection module, a voice enhancement module, a voiceprint feature extraction module, a multi-modal classification module, a data fusion unit, the sound collection module is arranged on a wearable device on the neck of a sheep, is provided with an anti-wind-noise directional microphone array, and is used for collecting environmental sound signals in real time; the voice enhancement module is connected with the sound collection module. The present application realizes accurate recognition and analysis of sheep feeding behavior, effectively solves the problems of sound signal processing in a complex environment, individual and group monitoring, privacy protection and energy supply, not only improves the intelligent level and efficiency of pasture management, reduces labor costs, but also can timely find health problems of sheep, protect the health of the sheep, protect the privacy of sheep data, and improve the energy utilization efficiency of equipment.

To provide an action recognition device that enables more appropriate work management in production sites. [Solution] The behavior recognition device according to the present invention is a behavior recognition device that recognizes the behavior of a worker in a workspace for producing an object, and comprises: an authentication unit that authenticates the worker in the workspace based on skeletal information of the worker stored in advance; and a voice recognition unit that authenticates the worker's voice, recognizes the start and end of work in a predetermined process related to the object to be produced based on the worker's voice, and obtains the start time and end time of the work.

The sound processing system disclosed herein includes an input unit, a determination unit, and a sound recognition unit. The input unit receives a first sound, which is the sound emitted by a first speaker. The determination unit determines whether the location of the first speaker can be determined. The sound recognition unit outputs a sound command, determined based on the sound, as a signal for controlling the target device. If the determination unit determines that the location of the first speaker cannot be determined, the sound recognition unit restricts the output of a speaking position command, which is a command related to the speaker's location, from the sound command.

Provided is an in-vehicle information device that is mounted on a vehicle and that transmits, via a portable terminal, a sound signal including a sound emitted by a user to a server device that performs a sound recognition process such that the sound recognition process is performed in the server device, the in-vehicle information device being provided with: a controller that controls the in-vehicle information device to transmit the sound signal including the sound emitted by the user to the server device; when the voice recognition process via the portable terminal is being performed, the voice signal including analog noise is transmitted to the portable terminal.

To realize an information processing system that can determine the location information of a train car with a simple configuration. [Solution] An information processing system according to one aspect of the present disclosure includes a sound output unit provided in an elevator car that outputs a sound corresponding to the position of the elevator car, and an information terminal held by a worker, which includes a sound acquisition unit that acquires the sound, and an identification unit that identifies the position of the elevator car based on the acquired sound.

The invention provides a deep learning-based human mouth shape and voice matching recognition method, which comprises the following steps of: recognizing respective speaking mouth shape characteristics of all people in a surrounding environment through an image, and recognizing a sound source position and an audio characteristic of the surrounding environment through a pickup array; according to the speaking mouth shape features, correcting the sound source position so as to separate the audio features to obtain the subordinate audio features of each person; performing deep learning on the audio features and the speaking mouth shape features of each person to obtain voice information sent by each person; carrying out background noise processing on the voice information to obtain the speaking voice and the text content of each person; personnel around the hearing aid in a noisy environment are identified in a visual and voice recognition mode, voice of the personnel is recorded and converted, the cocktail problem of the hearing aid in far-field recognition is effectively solved, voice interference is effectively restrained, and voice recognition accuracy and definition are improved.

The invention relates to an intelligent newborn nursing system and method based on cry recognition. The system comprises a real-time data acquisition module for acquiring real-time sound, environment data and a surrounding image sequence of the newborn; the voiceprint anomaly judgment module filters the sound signals to extract features, classifies cry types through a support vector machine, and fuses environment data to generate an anomaly demand identifier; the image attitude decision-making module takes the identifier as a trigger, analyzes the image sequence to obtain abnormal attitude information of the newborn, and integrates related data to obtain an emergency demand comprehensive decision-making basis; the instruction iteration planning module generates a response instruction sequence based on the basis, combines execution feedback update parameters, fuses historical nursing data and a current deviation level, and generates a nursing execution plan containing dynamic execution opportunity, hierarchical monitoring nodes and an adaptive feedback period. According to the system, the problems that traditional nursing depends on manpower, response lags behind and the misjudgment rate is high are solved through cooperation of the modules, and continuous and accurate intelligent nursing is provided for newborns.

This invention discloses a bird sound recognition method based on voiceprint recognition, comprising the following steps: collecting bird sound signals from a natural environment and preprocessing them to obtain a sound frame sequence; extracting acoustic features and calculating a frame feature vector sequence; performing segmented processing to calculate a structure consistency score and comparing it to obtain a frame weight sequence, constructing a weighted covariance matrix sequence; performing symmetric positive definite matrix constraint processing and mapping it to a symmetric positive definite matrix manifold space to obtain a manifold representation matrix sequence; combining the manifold representation matrix sequences to construct a covariance manifold trajectory; calculating shape invariants and constructing voiceprint feature vectors; inputting an improved supervised metric learning model to calculate similarity and determine the bird species category or individual bird voiceprint information corresponding to the bird sounds; and outputting the bird sound recognition result. This invention achieves bird sound recognition through a covariance manifold trajectory voiceprint recognition method, possessing the advantage of high recognition accuracy.

The invention relates to the technical field of vehicle control, and particularly provides a vehicle locking control method, electronic equipment and a vehicle. The method comprises the following steps: acquiring vehicle state data; determining that the vehicle is in a locked state and a non-flameout state according to the vehicle state data, starting an external voice recognition function, and monitoring a human voice signal of an external area of the vehicle; in response to the monitored human voice signal, performing sound wave offset processing on the human voice signal; and turning off the external sound recognition function in response to the received vehicle unlocking signal. In this way, after the vehicle is in the locked state and in the non-flameout state, the external voice recognition function is started, and after an external voice signal is monitored, in order to avoid voice control over the vehicle by the external voice signal, sound wave offset processing is conducted on the voice signal, and the vehicle is unlocked after a vehicle unlocking signal is received. According to the physical noise reduction mode utilizing sound wave counteracting treatment, the situation that the vehicle is awakened by external personnel through voice is effectively avoided, and the safety of the vehicle is improved.

This invention provides a voiceprint recognition method based on the DR-Res2net module. This method provides rich and effective feature information when processing voiceprint data, exhibits strong generalization ability, and has a lower error rate in classification, thus achieving more ideal recognition results. In this invention, the characteristics of the dense DenseNet model are integrated into the Res2Net model to construct the DR-Res2net model. In the voice recognition model, DR-Res2Block is used as the core module for voiceprint data recognition. During the recognition process, each DR-Res2net module performs residual and dense connections on each output feature simultaneously to obtain richer features. The addition processing in the module increases the amount of information contained in each feature, while the concatenation processing ensures that the features include both high-semantic low-resolution and low-semantic high-resolution features, preserving features from different receptive fields to the greatest extent possible.