131 results about "Sound recognition" patented technology

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 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.

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 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 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.

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.

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 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 discloses a danger prompting method, device, equipment and product, and relates to the technical field of hearing aids, the method is applied to a hearing aid, the hearing aid comprises a danger sound recognition model, and the method comprises the following steps: collecting environment audio through a microphone of the hearing aid; performing dangerous audio detection on the environment audio through the dangerous sound recognition model to obtain a detection result; under the condition that the detection result is that the dangerous audio is detected, performing mode conversion on the hearing aid to obtain a conversion result; and generating prompt information and sending the prompt information to a user under the condition that the conversion result is conversion completion. Therefore, the problem that a user misses safety early warning due to the fact that a traditional hearing aid easily misjudges dangerous sound in a complex environment as excessive suppression of noise is solved, and the accuracy of danger prompt is improved.

One or more example embodiments also provide a server configured to register identification information associated with a voice of a user in an account of the user, and a system including the server.SOLUTION: In the system, the server 400 includes a communication unit that communicates with the electronic device 100 (the image display 100a, the air conditioner, the refrigerator, the air cleaner, the washing machine, the car, or the like), a database that stores a history of use of a text for each characteristic, and a controller. Generating a plurality of first texts corresponding to a voice signal received from an electronic device, generating first identification information corresponding to the voice signal, acquiring a characteristic of a user corresponding to the voice signal based on the first identification information, and determining a second text corresponding to the voice signal among the plurality of first texts based on a first text history in which each of the plurality of first texts is used in association with the characteristic of the user among a history in which texts are used for each characteristic; A result of performing intention analysis on the second text is sent to the electronic device.SELECTED DRAWING: Figure 1

The invention provides a model training method, a snore recognition method and related equipment, and is applied to the technical field of information processing. Performing multiple times of iterative training on the preset model based on the training data set until a target condition is reached, and obtaining a trained preset model; and generating a snore recognition model based on a feature extractor and a label classifier included in the trained preset model. In the method, the feature extractor in the obtained snore recognition model has good capability of extracting the public acoustic features irrelevant to the domain, so that the influence of the difference of sound recording equipment and room acoustics caused by different model deployment environments on the snore recognition model can be reduced, and the recognition accuracy of the snore can be improved.

The present disclosure relates to an information processing method, a post-correction that improves an error of a sound recognition result. An information processing method executed by an information processing apparatus, wherein, when a chat for acquiring a specialized skill from a user is performed using a language model, text information obtained by recognizing a sound signal of a voice of the user is displayed on a display section, and in accordance with a correction in the text information, other parts of the text information having relevance to a part after the correction are corrected.

The application discloses a transformer fault automatic alarm device and a use method thereof, and relates to the technical field of power equipment. The transformer fault automatic alarm device comprises a device base arranged at the bottom of a transformer body, an annular guide rail frame is arranged on the device base, a rotating ring is rotatably connected to the annular guide rail frame, a limiting seat is fixedly connected to the rotating ring, and a fault identification terminal is movably clamped on the limiting seat. The transformer fault automatic alarm device utilizes the design of the fault identification terminal and a microphone module, receives and processes the working sound signals of the transformer body, adopts an alarm component to automatically alarm when the sound signals are abnormal, and through the design of a driving unit, the device can perform omnibearing sound identification and detection on the transformer body, the detection sensitivity and accuracy are improved, meanwhile, the design of a noise reduction unit is matched, the rotating ring is automatically lubricated when moving along the annular guide rail frame, and the transmission position noise is prevented from affecting the fault sound detection effect.

The invention provides a system for testing vibration and noise performance of an object through NVH parameters, and relates to the technical field of NVH testing. The system is composed of a power supply, an adaptive clamp, a vibration noise detection sensor, a vibration noise test analyzer, computer analysis software and a tested object, and is characterized in that joint detection of five NVH key parameters including kurtosis, skewness, margin, peak-to-average ratio and pulse factor is integrated, an AI deep learning abnormal sound recognition algorithm is carried, a bone conduction contact type signal acquisition technology is adopted, and a bone conduction signal is acquired. And environmental noise interference is avoided. The system carries out full-process automatic testing through parameter self-adaptive setting, multi-channel synchronous acquisition, key parameter conjoint analysis, AI fault diagnosis and data tracing and archiving. The system solves the problems that a traditional testing environment is large in interference, depends on manpower, is low in detection efficiency and is disordered in data management, has the advantages of rapid detection, accurate diagnosis and convenient tracing, and is adaptive to production line batch detection and laboratory accurate analysis scenes.

The application discloses a bird chirp sound recognition method based on a combination of voiceprints and spatial distribution, and belongs to the technical field of intelligent sound classification and recognition. In view of the problems of ignoring geographical distribution prior knowledge and sample imbalance in the prior art, the application firstly constructs a voiceprint recognition model: a training data set is constructed by audio preprocessing, logarithmic mel spectrum and dynamic difference feature extraction, a model is trained based on DenseNet-121 by adopting a two-stage training strategy, and recognition confidence of each species is obtained; meanwhile, a spatial distribution model is constructed: based on public observation data, an average observer ability index is used to correct an original encounter rate, and spatial distribution probability of the species in a specific city is obtained; finally, a Sigmoid function is used to perform nonlinear fusion on the two, a joint recognition probability is calculated, and a classification result is output. The application introduces ecological spatial constraints into the recognition decision, effectively reduces false positive misjudgment, improves rare species monitoring capability, and makes the recognition result have ecological interpretability.

The invention relates to the technical field of access control, and provides an access control system with an alarm sound recognition function and a control method. The control method comprises the following steps: acquiring a current vehicle image at an entrance of an entrance guard to obtain a license plate recognition result of a current vehicle; acquiring an environment audio signal at the entrance of the entrance guard to obtain an alarm sound recognition result, the alarm sound recognition result representing whether an audio event conforming to a preset emergency vehicle alarm sound feature exists or not; obtaining a first door opening judgment signal based on the license plate recognition result and an authorized license plate database; based on the alarm sound recognition result, a second door opening judgment signal is obtained; based on the first door opening judgment signal and the second door opening judgment signal, a comprehensive door opening trigger signal is generated through logic or operation; and controlling the access control to work based on the comprehensive door opening trigger signal.

The application discloses an electrical equipment sound recognition method based on feature frequency band selection. The method comprises the following steps: sound time domain data acquisition and preprocessing, conversion to a frequency domain by using Fourier transform; a Metropolis-Hastings sampling method is used to randomly sample a set number of samples to establish a partial least squares regression model; a logarithmic attenuation function is used to filter the frequency band with the minimum absolute value weight of the regression coefficient; a set retention ratio of the frequency band is selected by using weighted sampling, and the corresponding frequency band with a smaller root mean square error of cross-validation is selected as a feature frequency band; a neural network is established to recognize the sound state. The application reduces the spatial dimension of the training sample, avoids data redundancy, and improves the training speed. The application effectively recognizes three states of normal working, normal air leakage and abnormal air leakage, and improves the recognition accuracy.

The invention discloses an intelligent acoustic positioning system for sick pigs in a hog house, and relates to the field of sound recognition and positioning. The problems that an existing sick pig acoustic positioning method is poor in voice recognition accuracy and large in positioning error in a complex acoustic environment are solved. According to the invention, a time difference and phase difference complementary positioning principle is adopted, and an adaptive beam forming technology is combined, so that the problem of inaccurate sound source positioning in a pig house environment with strong reflection and high noise is solved, multi-feature extraction and intelligent diagnosis are carried out on enhanced sound data through the sick pig sound recognition unit, and the recognition accuracy is improved. The method is mainly used for positioning sick pigs in a complex breeding environment.

The present application relates to the technical field of artificial intelligence, and discloses a song detection method and device, computer equipment and a storage medium. The method extracts dry sound from a to-be-processed audio file to obtain a dry audio signal after accompaniment removal. The extracted dry audio signal usually has a certain degree of noise. The method then extracts features from the dry audio signal to obtain dry sound features for subsequent song detection. A song recognition model is used to identify the dry sound features to obtain more accurate dry sound recognition results. The dry sound recognition results are filtered and de-noised to obtain final song detection results. The song recognition model is used to perform secondary detection on the dry sound features, thereby improving the accuracy of the song detection results.

The embodiment of the application relates to the technical field of audio recognition, and provides a snoring sound recognition method based on multi-feature fusion, which comprises the following steps: acquiring a plurality of snoring sound sample audio training sets and verification sets; extracting at least two types of first audio features corresponding to each snoring sound sample audio; acquiring a positive sample set and a confusion sample set according to the first audio features of different snoring sound sample audios and sample labels; determining a target feature comparison sequence according to the positive sample set, the confusion sample set and the verification set; and comparing the audio features of the snoring sound audio of a to-be-tested patient based on the target feature comparison sequence to determine an excitation position of the snoring sound caused by the to-be-tested patient. The method provided by the application can recognize snoring sound by using different snoring sound audio features for different patients, and the accuracy of recognizing the excitation position of the snoring sound of a patient is improved.

This invention provides a sound recognition-based smart guardianship method, comprising mobile guardian software installed on a mobile phone. This software includes a map and is accessible to the user after registration and login. A backend management system is also included, managed by an administrator. The mobile guardian software uses the phone's microphone to pick up and recognize sounds such as falls or cries for help, automatically sending a distress signal. Upon receiving the distress signal, other nearby users' mobile guardian software can view the location of the person seeking help on the map and provide assistance. The scope of protection of this invention includes, but is not limited to, the above embodiments. The scope of protection of this invention is defined by the claims, and any substitutions, modifications, or improvements readily conceived by those skilled in the art fall within the scope of protection of this invention.

The present application provides a kind of unmanned aerial vehicle target tracking method and unmanned aerial vehicle target tracking system.The unmanned aerial vehicle target tracking method includes the following steps: obtaining the sound signal around the unmanned aerial vehicle, and extracting sound features therefrom;Via pre-trained sound recognition model, whether the specified tracking target exists around the unmanned aerial vehicle is judged according to the sound features;In response to the judgment result that the tracking target exists, sound source localization is performed on the sound signal to determine the position information of the tracking target;And according to the position information, the flight instruction of the unmanned aerial vehicle is determined to control the unmanned aerial vehicle to track the tracking target.Through the execution of these steps, the unmanned aerial vehicle target tracking method can identify multiple sound types in a sound field environment with a relatively complex sound category, and achieve target tracking of the unmanned aerial vehicle based on sound signals with lower storage and processing difficulty.

The invention relates to the technical field of abnormal sound detection, in particular to a scraper abnormal sound recognition method and device and electronic equipment. The scrapper abnormal sound recognition method comprises the following steps: based on historical sound data of all working surfaces of a plurality of coal mines and an HTS-AT model, acquiring a universal audio recognition model divided according to a mining dimension; obtaining a target normal sound sample, a target fault sound sample and a target environment interference sound sample which are matched with the target working surface; based on the sampling height of the target working face, the target normal sound sample, the target fault sound sample and the target environment interference sound sample, performing fine tuning on the universal audio recognition model to obtain a target audio recognition model matched with the target working face; and based on the target audio recognition model, recognizing the to-be-detected sound of the target working surface, and obtaining an abnormal sound recognition result of the scraper. The abnormal sound of the scraper conveyor can be accurately recognized, real-time and accurate support is provided for equipment troubleshooting, and the coal mine production efficiency is improved.

The invention relates to the technical field of artificial intelligence, in particular to a low-complexity environmental sound recognition method and system based on course temperature self-distillation, and the method comprises the steps: constructing a course temperature self-distillation model based on a lightweight backbone network, and constructing a teacher model and a student model based on the backbone network; a learning parameter is distributed for each training sample, a course temperature parameter is obtained through re-parameterization processing, a total loss function containing teacher loss and student loss is constructed, and a backbone network parameter, a student branch parameter and the course temperature parameter are jointly optimized through a gradient descent algorithm based on the total loss function; after training is completed, all student branches and course temperature parameters are removed, a backbone network and a final classifier are reserved, and an input sample is processed through the backbone network and the final classifier to obtain a recognition result; according to the invention, the recognition precision and efficiency of the low-complexity environment sound recognition system can be improved.

The application relates to the technical field of sound recognition, and provides a low-resource sound event detection method, device and equipment and a storage medium, wherein the method comprises the following steps: acquiring sound to be detected; inputting the sound to be detected into a trained sound group category neural network model to obtain sound group category information; inputting the sound to be detected into an encoder of a pre-trained sound event category judgment model to obtain fine-grained feature information, and splicing and fusing the group category information and the fine-grained feature information to obtain fusion feature information; inputting the fusion feature information into a decoder of the sound event category judgment model, and decoding the fusion feature information based on an attention mechanism and in combination with a pre-obtained group category representation matrix to obtain a sound event judgment result. The application forms large-class group sound group category information containing rich information by using the sound to be detected, and realizes auxiliary discrimination based on large-class sound event results through a self-attention mechanism.