33 results about "Spectral subtraction" patented technology

A sensorless method for machine tool chatter detection. A motor torque signal is analyzed in the time domain to determine whether a bit is currently cutting workpiece material. When not cutting material, an air-cut reference signal is stored for later use. When cutting material, the motor torque signal is converted to the frequency domain and filtered in a multi-step process. After removal of the air-cut reference signal via spectral subtraction, and removal of spindle harmonic components, additional filtering is performed to address aliasing and encoder error effects. The aliasing filtering removes artificial peaks in the frequency response spectrum resulting from interaction between sampling frequency and cutting frequency. The encoder error filtering removes frequency response peaks related to encoder design and interaction with motor speed. After filtering, indicator criteria are evaluated to detect chatter, and corrective action is taken when chatter is detected.

A sensorless method for machine tool chatter detection. When the machine tool spindle is running, a spindle motor torque signal is analyzed in the time domain to determine whether a bit is currently cutting a workpiece. When not cutting, an air-cut reference signal is stored for later use. When cutting, the spindle motor torque signal, along with positioning servo motor signals, are converted to the frequency domain and filtered. Filtering steps include removal of the air-cut reference signal via spectral subtraction, removal of spindle harmonic components, removal of artificial peaks due to aliasing effects, and removal of artificial peaks due to encoder error effects. After filtering, indicator criteria are evaluated to detect chatter, including a magnitude of the filtered torque signal for servo data and a magnitude ratio of the filtered torque signal to the air-cut reference signal for spindle data. Corrective action is taken when chatter is detected.

The invention relates to the technical field of agricultural travel services, and provides a dialect intelligent customer service and culture knowledge base system, the system comprises a perception layer, an analysis layer, a knowledge layer and an interaction layer four-dimensional architecture, the perception layer collects and preprocesses dialect voice, noise reduction is performed through spectral subtraction, and Mel frequency cepstrum coefficient features are extracted; the analysis layer identifies dialects based on a fine tuning Wav2Vec2.0 model, converts the dialects into mandarin through a Transform architecture, and completes intention identification and slot filling by using a BERT related model; the knowledge layer constructs a local culture knowledge graph containing non-abandoned, folk and other entities, and supports dynamic updating; and the interaction layer is combined with multiple rounds of dialogue management to generate multiform responses, and can be connected with an external service system. The system also optimizes a feedback module iterative model and knowledge. The system can cover more than ten dialects, realizes dialect interaction, culture interpretation and service conversion closed loop, and assists rural culture revitalizing and rural cultural travel service upgrading.

The invention discloses a weak fault sound source monitoring and early warning method based on deep learning and an acoustic array, and belongs to the technical field of equipment state monitoring and fault diagnosis. In order to solve the problem of early fault detection caused by easy submergence of weak fault voiceprint signals, incomplete feature extraction and scarcity of fault samples in a strong noise environment, the method comprises the following steps: collecting multichannel signals through an acoustic array, establishing a dynamic noise baseline by adopting a Gaussian mixture model, and performing noise suppression in combination with a spectral subtraction method; extracting a composite feature vector containing time domain, frequency domain and time-frequency domain features; and carrying out fault identification by using the pre-trained and fine-tuned transfer learning model, and finally outputting an early warning according to an identification result. The method is suitable for online monitoring and early warning of early weak faults of industrial equipment.

The invention discloses an AI-driven vehicle-mounted sound field real-time modeling and voice separation method, and relates to the technical field of voice signal processing. A main control unit comprising a time sequence synchronizer, a resource scheduler and a health monitor is constructed. 3D sound field modeling is carried out by adopting a lightweight STCN + bidirectional LSTM network, adaptive updating of the model is realized through EWC incremental learning, and a CNN-LSTM noise classification network and targeted suppression algorithms such as ANF / spectral subtraction are developed. The voice separation module adopts an improved Conv-TasNet architecture, 3D spatial constraint and a multi-task loss function are fused, and low delay is realized under INT8 quantization and pipeline processing. The system dynamically optimizes parameters through a real-time regulation and control unit, supports scene self-adaption, finally achieves a separation effect in a mixed noise scene, reduces the delay of the whole system, and effectively improves the definition and stability of vehicle-mounted voice interaction.

The invention relates to the technical field of artificial intelligence, and discloses a BCM module cooperative control method based on voice instruction recognition in a vehicle-mounted high-noise environment, and the method comprises the following steps: collecting original voice instruction data and vehicle state parameter data in the vehicle-mounted high-noise environment; performing voice signal preprocessing in a noise environment based on the original voice instruction data to generate de-noised voice instruction data; according to the method, the engine noise and the wind noise steady-state background noise are filtered out through multi-level noise suppression processing combining adaptive filtering and spectral subtraction, residual noise elimination is carried out for sudden impact noise, and the definition of voice signals is improved. Meanwhile, through a voice activity detection algorithm, a detection threshold is dynamically adjusted according to vehicle state parameters, an effective voice segment and a noise segment can be separated, the accuracy of voice feature extraction in a complex time-varying noise environment is ensured, and thus the robustness and reliability of voice instruction recognition are improved.

The application discloses a consumer complaint response method and system based on AI assistance and language understanding, which splits the complaint response process into two core sub-problems of multi-modal consumer complaint data processing and feature fusion and demand attribution and response generation. In multi-modal consumer complaint data processing and feature fusion, first, regular expressions are used to denoise text, spectral subtraction is used to denoise voice, and Gaussian filtering and adaptive histogram equalization are used to denoise images; then, modal features are extracted, text is used as the core of cross-modal fusion, and entity and relationship are extracted to construct a multi-modal semantic knowledge graph. In demand attribution and response generation, Graph Transformer is used in combination with the graph and domain prior knowledge to output primary and secondary demands; a static complaint graph is constructed, an attribution path is mined through BFS and is verified through multi-modal verification; and an "emotion-demand-attribution-prevention" structure is used to optimize text and adjust the format by using LLM, and an individualized complaint response is output.

The application relates to the technical field of artificial intelligence, and discloses a BCM module cooperative control method based on voice instruction recognition in a vehicle high-noise environment, which comprises the following steps: collecting original voice instruction data and vehicle state parameter data in the vehicle high-noise environment; performing voice signal preprocessing in the noise environment based on the original voice instruction data to generate denoised voice instruction data; through multi-level noise suppression processing combining adaptive filtering and spectral subtraction, engine noise, wind noise and steady-state background noise are filtered out, and residual noise is eliminated for sudden impact noise, so that the intelligibility of the voice signal is improved. Meanwhile, through a voice activity detection algorithm, and by dynamically adjusting the detection threshold according to the vehicle state parameters, effective voice segments and noise segments can be separated, the accuracy of voice feature extraction in a complex time-varying noise environment is ensured, and the robustness and reliability of the voice instruction recognition are improved.

The invention relates to the technical field of voice enhancement, in particular to an audio noise reduction method and system for a Bluetooth headset, and the method comprises the steps: analyzing the feature condition of noise influence in a mobile scene, including the feature change condition of a signal obtained by a microphone under the condition of pedestrian voice noise interference; according to the method, the spectral subtraction factor of the spectral subtraction method is adjusted in a targeted manner by integrating the characteristic difference conditions of the audios obtained by the reference microphone and the main microphone when the audios are moved to different scenes, so that the filtering error occurring during the audio noise reduction of the Bluetooth headset in the moving scene is avoided, and the audio noise reduction level in the call process of the Bluetooth headset is further improved.

The invention discloses a distributed reconnaissance tool, relates to the technical field of voice interception, and aims to solve the problems of limited multi-node access capability, poor anti-interference performance and insufficient multi-target interception continuity of an existing reconnaissance system. The tool comprises a micro audio node network and a base station unit, a recording module, a wireless transmission module and an encryption module are arranged in the miniature audio node, local recording and remote transmission are supported, and the miniature audio node has the characteristics of water resistance and low power consumption; the base station unit adopts an orthogonal graph division multiple access technology, at most 32 micro audio nodes can be accessed, four paths of voice can be monitored in real time, the audio quality is optimized through a spectral subtraction voice enhancement algorithm, and WIFI / Ethernet connection and time synchronization and combination of multi-node recording files are also supported. According to the invention, approaching interception and multi-target centralized deployment and control of the moving target are realized, the stability, expansibility and practicability of the interception system are improved, and the method is suitable for scenes such as public security technical investigation and the like.

The invention provides a real-time speech enhancement method and system based on dual-stage spectral subtraction and dual-mask fusion, and relates to the technical field of speech signal processing, and the method comprises the steps: respectively carrying out the framing, windowing and short-time Fourier transform of a left channel mixed signal and a right channel noise reference signal, obtaining a complex frequency spectrum and an amplitude spectrum of the left channel signal and an amplitude spectrum of the right channel noise reference signal; and performing noise estimation by adopting a first noise multiplication factor based on the amplitude spectrum of the right channel noise reference signal to obtain a noise estimation spectrum, and performing constraint spectrum subtraction on the amplitude spectrum of the left channel signal to obtain voice amplitude estimation of a first stage. According to the method, effective suppression of TTS noise and real-time speech enhancement are realized through framing windowing and frequency domain conversion in combination with over-estimation spectrum subtraction and double-mask fusion through two-stage gain application and time domain reconstruction.

The invention relates to the field of float glass production, in particular to a method and a device for identifying glass fragmentation sound in an annealing kiln. According to the method, a plurality of acoustic sensors which are arranged on a longitudinal steel beam on the non-transmission side of the annealing kiln and can tolerate the high temperature of 100 DEG C or above are used for collecting field environment sound signals; sequentially executing time domain preprocessing, improved spectral subtraction noise suppression, wavelet packet analysis and scale energy feature extraction to obtain a normalized feature vector; and finally, carrying out model training and real-time identification based on a hidden Markov model, and outputting whether the sound is glass fragmentation sound or not and a specific fragmentation type. The invention further provides a device for implementing the method, manual guarding can be replaced, accurate recognition and type judgment of glass fragmentation of the annealing kiln are achieved, the labor cost is reduced, manual monitoring defects are avoided, the fragmentation interval can be rapidly positioned, the device is adaptive to the high-temperature and high-noise scene of the annealing kiln, and the yield loss and the equipment production halt risk are reduced.

This invention relates to a method for highlighting spike discharge data of intracranial electroencephalogram (EEG) signals. The method involves collecting background noise data from the patient's brain without neuronal discharges, preprocessing the background noise data, automatically selecting the optimal order of an autoregressive (AR) model using the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), estimating the AR model coefficients using the Yul-Walker equation, and constructing a background noise model. The intracranial EEG signals to be processed are then subjected to high-pass filtering. A short-time Fourier transform (STFT) and window-based frame-by-frame processing strategy are used to subtract the spectrum of the signal from the noise. By adjusting the parameters of the spectral subtraction, noise removal and preservation of neuronal signal features are achieved.

The invention relates to a non-contact fault detection method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a motor audio signal for a to-be-tested motor; performing noise suppression processing on the motor audio signal, and extracting to obtain motor audio feature information; the noise suppression processing comprises the steps of dynamically adjusting a noise threshold by utilizing self-adaptive frequency spectrum subtraction, and highlighting the characteristic frequency of the motor through harmonic enhancement processing; and based on the motor audio feature information, utilizing a pre-trained motor fault detection model to obtain a fault classification result for the to-be-detected motor. The reliability of motor fault detection can be effectively improved.

This application relates to the field of language processing technology, specifically to a brain-computer interface-based auditory stimulation enhancement and reconstruction system. The system includes: a signal acquisition module for acquiring background noise and auditory signal data, obtaining the background noise and auditory response spectra; a background noise analysis module for constructing background noise interference intensity based on the differences between various physiological electrical signals and the background noise spectrum; an over-subtraction factor adjustment module for adjusting the over-subtraction factor based on the background noise interference intensity and the overlap between strong interference physiological electrical signals and the auditory response spectrum; a spectral lower limit parameter adjustment module for determining the optimal spectral lower limit parameter by analyzing the noise performance balance under each spectral lower limit parameter after spectral subtraction; an over-subtraction factor correction module for correcting the over-subtraction factor using the optimal spectral lower limit parameter; and a signal reconstruction module for reconstructing the auditory signal sequence obtained through the spectral method. This improves the denoising effect of music noise while simultaneously reducing the influence of other noises on the auditory signal, resulting in better auditory stimulation enhancement.

The application discloses a photoacoustic signal enhancement method and device based on adaptive multi-band spectral subtraction and Wiener filtering, and belongs to the technical field of speech signal enhancement. The application divides a signal into sub-bands according to Mel scale, determines a subtraction factor and a lower limit factor by a monotone decreasing function linkage according to real-time signal-to-noise ratio of each sub-band, and makes the two factors negatively correlated with the signal-to-noise ratio, so that the denoising strength and the spectral bottom filling depth are automatically adapted; the weighted moving average of the power spectrum of adjacent sub-bands is carried out to smooth isolated spectral peaks and spectral valleys left by spectral subtraction; a residual amplitude limiting is introduced before Wiener filtering, the maximum noise residual threshold is determined based on adjacent frame statistics and limiting, and Wiener filtering is carried out by taking the data after limiting as clean signal estimation; the noise spectrum is recursively updated by a forgetting factor which is dynamically adjusted according to the signal-to-noise ratio, and is only executed in the speech inactive section. The application has an output signal-to-noise ratio improvement of more than 50% when the input is 0dB, can stably enhance without damage under high signal-to-noise ratio, and is suitable for photoacoustic speech acquisition and enhancement scenes.

An elevator abnormal sound positioning method based on local and global attention models belongs to the field of elevator detection technology, deep learning and sound source localization, and comprises the following steps: step 1, using a microphone array to collect multi-channel sound signals of an elevator in the operation process, carrying out direct current removal preprocessing on the sound signals to obtain preprocessed sound signals, and storing the preprocessed sound signals in a database; complex frequency spectrum calculation and spectral subtraction denoising are carried out on the preprocessed sound signals, and a power spectrum is calculated; 2, performing feature extraction on the sound signal: extracting a logarithmic Mel spectrum feature and a phase transformation generalized cross-correlation feature of the sound signal, and splicing the two features to obtain an input feature of the model; and step 3, inputting the input features into the GLAN model to obtain an abnormal sound detection condition and an estimation result of sound source localization. The method has high positioning precision and stability.

This invention relates to the field of noise reduction technology, specifically to an AI-based intelligent noise reduction method for laser-modulated speech, comprising the following steps: Analog-to-digital conversion: A high-speed, high-precision analog-to-digital conversion module is used to convert analog data into digital signals, and noise reduction is performed only on human voices according to the usage scenario; Digital filtering: Bandpass filtering technology is used to filter out all out-of-band signals; AI intelligent processing: Spectral subtraction is used to eliminate background noise. By constructing a collaborative processing link of "high-precision analog-to-digital / digital-to-analog conversion—64th-order narrow transition band FIR filtering—dynamic spectral subtraction based on AI model library", for slow-changing and stable specific background noise such as mechanical vibration thermal noise of the laser itself and ambient optical path scattering interference, a 10-millisecond non-overlapping time slice and a joint decision mechanism of three parameters (mean, variance, and entropy) of Mel frequency cepstral coefficients are used to achieve accurate dynamic tracking of noise targets and adaptive stripping of speech signals.

This invention discloses a real-time piano timbre simulation method and system based on machine learning, relating to the field of audio signal processing technology. The method includes: data acquisition and multi-dimensional annotation, acquiring multiple types of piano audio, covering techniques and seven dynamic levels, and simultaneously acquiring information such as key presses and techniques; audio preprocessing, including pre-emphasis compensation for high frequencies, Hanning window framing, Fourier transform to frequency domain, spectral subtraction for noise reduction and normalization; multi-dimensional feature extraction, extracting static features such as MFCC and spectral parameters, dynamic features such as first- and second-order differences, and overtone structures; two-stage model training, using stacked autoencoders for dimensionality reduction; real-time parsing, filtering and converting acquired performance data into parameter sequences; timbre synthesis, where the model generates a spectrum and performs an inverse Fourier transform into a waveform; and dynamic optimization, receiving user feedback. This invention solves the problems of traditional simulation methods; the two-stage model enhances timbre coherence, dynamic control achieves low latency, and multi-scenario adaptation and feedback optimization meet specific needs.

The invention relates to a multi-channel voice signal noise reduction method and device. The method comprises the following steps: acquiring a multi-channel vibration signal and a pure noise signal acquired by a distributed optical fiber acoustic sensing system; performing framing processing on the multi-channel vibration signal to obtain a frequency domain complex spectrum of each frame of each channel; determining a spectral entropy and a low-frequency signal-to-noise ratio according to the pure noise signal, and performing adaptive adjustment on an over-reduction coefficient according to the spectral entropy and the low-frequency signal-to-noise ratio to obtain a target over-reduction coefficient; performing spectral subtraction operation on the first amplitude spectrum according to a target over-reduction coefficient, and performing phase correction on the first phase spectrum based on the time delay of each channel to obtain a single-channel complex spectrum of each frame, thereby effectively suppressing non-stationary noise interference and keeping signal phase consistency through self-adaptive adjustment of the over-reduction coefficient and combination of multi-channel phase correction; and performing phase optimization and superposition reduction on the single-channel complex spectrum to obtain a time domain signal after noise reduction and reconstruction, thereby improving the feature fidelity of the vibration signal through phase optimization and superposition reduction.

Techniques are disclosed for a low-power and low-complexity speech onset detector (SOD) that uses a fractional-band filter structure and spectral subtraction technique to derive sub-band energy profiles to detect the onset of speech in the presence of noise. The SOD derives the sub-band energy profiles by filtering and down-sampling a full-band input audio signal using the fractional-bandwidth filter structure, which may be a low-pass filter with a cut-off frequency that is a fraction of the full bandwidth of the input signal. The SOD flexibly estimates the average noise energy across frames and the current frame speech energy in each sub-band to track noise and speech energy levels across the frames for each of the sub-bands to determine one or more band thresholds used to detect active speech. The sub-band energy profiles leverage any separation in frequency between noise and speech to detect the onset of speech in a target signal.

Techniques are disclosed for a low-power and low-complexity speech onset detector (SOD) that uses a fractional-band filter structure and spectral subtraction technique to derive sub-band energy profiles to detect the onset of speech in the presence of noise. The SOD derives the sub-band energy profiles by filtering and down-sampling a full-band input audio signal using the fractional-bandwidth filter structure, which may be a low-pass filter with a cut-off frequency that is a fraction of the full bandwidth of the input signal. The SOD flexibly estimates the average noise energy across frames and the current frame speech energy in each sub-band to track noise and speech energy levels across the frames for each of the sub-bands to determine one or more band thresholds used to detect active speech. The sub-band energy profiles leverage any separation in frequency between noise and speech to detect the onset of speech in a target signal.

The application discloses a kind of non-contact human respiratory rate measurement methods based on video and frequency modulation continuous wave radar information fusion, comprising:1 respectively processes video and radar bimodal data to obtain pixel motion trajectory and distance angle chart time sequence;2 video measurement part uses spectral subtraction and principal component analysis technique to carry out pretreatment, radar measurement part uses static clutter removal and average filtering technique to carry out pretreatment, two kinds of modal all use empirical mode decomposition technique to carry out single modal measurement;3 feature level fusion, after bimodal signal using multivariate singular spectrum analysis extraction shared respiratory signal is pretreated;4 decision level fusion, according to the signal-to-noise ratio weighted frequency domain estimation value summation of feature level fusion result and single modal measurement result obtains final measurement result.The application can measure respiration under a variety of spontaneous motion scene, measurement result is compared with single modal method and has significant improvement, can effectively expand the application range of video and radar fusion measurement.

A sensorless method for machine tool chatter detection. When the machine tool spindle is running, a spindle motor torque signal is analyzed in the time domain to determine whether a bit is currently cutting a workpiece. When not cutting, an air-cut reference signal is stored for later use. When cutting, the spindle motor torque signal, along with positioning servo motor signals, are converted to the frequency domain and filtered. Filtering steps include removal of the air-cut reference signal via spectral subtraction, removal of spindle harmonic components, removal of artificial peaks due to aliasing effects, and removal of artificial peaks due to encoder error effects. After filtering, indicator criteria are evaluated to detect chatter, including a magnitude of the filtered torque signal for servo data and a magnitude ratio of the filtered torque signal to the air-cut reference signal for spindle data. Corrective action is taken when chatter is detected.

The invention discloses a wireless communication noise reduction earphone and a noise reduction method thereof, and relates to the technical field of earmuff type noise reduction earphones. The earphone framework takes a main control circuit and a wireless communication circuit as a core and is supplemented by voice enhancement, active noise reduction, interception, power management and an external interface circuit, the main control circuit overall plans operation logic and cooperates with multiple modules, and the wireless communication circuit supports multi-person simultaneous conference in the same group and multi-person simultaneous voice receiving, so that wireless multi-party communication independent of external equipment is realized. According to the noise reduction method, a composite active noise reduction technology is adopted, voice enhancement and an impulse noise protection mechanism are combined, voice and noise signals are separated through frequency spectrum subtraction, and noise reduction and environment perception are balanced in cooperation with an environment monitoring function. The problems that a traditional earphone depends on external equipment for communication, noise reduction and safety perception are contradictory in a complex environment and the like are solved, a collaborative operation scene is adapted, and voice definition and use convenience in a noisy environment are improved.

To reduce the impact of internal conduction noise introduced from within the subject's body during exertion on the acquisition of respiratory sounds, and to suppress the generation of friction noise that easily mixes with biological sounds during exertion. [Solution] A biosound sensor system comprising a holding means 1 that can be attached to the head of a subject and has a main input sensor 2 and a reference input sensor 3 installed facing inward on the left ear hook portion 4, and a biosound signal processing means 10 that reconstructs the respiratory sound waveform of the subject. The biosound signal processing means 10 applies a bandpass filter to the received main input and reference input signals to separate vascular sounds and respiratory sounds, applies STFT and HPSS to the extracted high-frequency main input and high-frequency reference input, and processes the obtained main input amplitude spectrogram and reference input amplitude spectrogram, etc. with a spectral subtraction Wiener filter (SSWF) and ISTFT to reconstruct a respiratory sound waveform with internal conduction noise reduced from the main input.

The invention discloses a piano tone real-time simulation method and system based on machine learning, and relates to the technical field of audio signal processing, and the method comprises the steps: data collection and multi-dimensional marking, collection of multiple types of piano audios, skill coverage and seven levels of strength, and synchronous collection of information such as keys and skill; performing audio preprocessing, pre-emphasis high frequency compensation, Hanning window framing, Fourier transform to frequency domain, spectral subtraction denoising and normalization; multi-dimensional feature extraction: extracting static features such as MFCC and spectrum parameters, dynamic features such as first-order and second-order differences and an overtone structure; carrying out two-stage model training, and carrying out stacking auto-encoder dimensionality reduction; analyzing and acquiring playing data in real time, filtering and converting into a parameter sequence; synthesizing timbre, generating a frequency spectrum by a model, and performing inverse Fourier transform to form a waveform; and dynamically optimizing and receiving user scores. According to the invention, the traditional simulation problem is solved; the dual-stage model enhances tone coherence, and dynamic control realizes low delay, multi-scene adaptation and feedback optimization fitting requirements.

The invention provides a fish ingestion intensity classification method based on fusion of multiple acoustic features. The method comprises the following steps: S1, collecting an original acoustic signal of a target fish school; s2, preprocessing the original acoustic signal, including re-sampling and spectral subtraction denoising; s3, extracting three acoustic feature maps from the de-noised signal in parallel, wherein the three acoustic feature maps are a Mel spectrogram, a GFCC map and an RMS envelope diagram respectively; s4, normalizing the three feature maps, and mapping the normalized three feature maps to a three-color channel of the RGB image to generate a fused image; and S5, inputting the fused image into a lightweight convolutional neural network, and outputting fish ingestion intensity classification results including four grades of strong, medium, weak and no through a multi-scale feature extraction module and a space attention mechanism. According to the method, the Mel frequency spectrum, the GFCC and the RMS envelope three-channel acoustic features and the lightweight network are fused, the ingestion intensity recognition capability in the underwater noise environment is remarkably enhanced, efficient real-time monitoring and feedback control are achieved, and the method is adaptive to an intelligent feeding system.

The invention discloses a noise suppression method and device for a cable partial discharge signal, electronic equipment and a storage medium, and belongs to the field of power equipment detection.The method comprises the steps that time-frequency transformation is conducted on an initial partial discharge signal to be denoised, and a corresponding first complex number time-frequency matrix is obtained; a signal segment with the minimum residual error is selected from the initial partial discharge signals to serve as a background noise signal, and the power spectrum density corresponding to the background noise signal is calculated; calculating a corresponding current spectral subtraction factor and a current spectral bottom coefficient, and performing spectral subtraction denoising processing on the first complex time-frequency matrix according to the power spectral density, the current spectral subtraction factor and the current spectral bottom coefficient to obtain a denoised first complex time-frequency matrix; and performing time-frequency inverse transformation on the denoised first complex time-frequency matrix to obtain a denoised partial discharge signal, therefore, by implementing the method and the device, the problems that modal decomposition parameters depend on manual setting, the calculation efficiency is low and the subjectivity is strong in the prior art can be solved.

The application relates to the technical field of hearing aids, in particular to a digital hearing aid howling suppression method and system, which comprises the following steps: determining an energy distribution characteristic value; determining the noise possibility of each to-be-processed signal based on the distribution of all high-energy values and derived values of each to-be-processed signal and a preset number of to-be-processed signals before the to-be-processed signal in a frequency domain and the rate at which each peak value in each to-be-processed signal drops to the adjacent next valley value, and determining an over-reduction index in combination with the energy distribution characteristic value; and suppressing howling noise in a speech signal by using a spectral subtraction method based on the over-reduction index. The application dynamically analyzes the frequency domain energy distribution and the time domain oscillation characteristics, adaptively adjusts the over-reduction index of the spectral subtraction method, solves the problem of poor adaptability of a traditional howling suppression method, and improves the howling suppression effect of a digital hearing aid in a complex acoustic environment.