6 results about "Perceptual weighting" patented technology

The application provides a voice call real-time transcription system and method, and relates to the technical field of computers.The system comprises a network element module for acquiring corresponding audio data when detecting a call request of a user terminal; a voice stream sending engine for performing hierarchical compression on the audio data based on a preset perceptual weighting vector quantization algorithm to obtain audio compression data, and performing format conversion processing on the audio compression data to obtain temporary audio data; a voice engine for performing feature extraction on the temporary audio data to obtain multimodal feature data, and processing the multimodal feature data based on a preset voice recognition model to obtain text information; and an analysis optimization module for obtaining corresponding real-time transcription text data based on a preset large model and according to the text information and a preset vocabulary library.The application comprehensively represents voice information by utilizing multimodal feature data, so that the voice recognition model can more accurately convert voice into text.

The invention relates to the technical field of industrial product quality detection and equipment fault diagnosis, in particular to a multi-mode abnormal sound detection system based on deep learning and a detection method thereof. The system comprises an audio signal acquisition module, an audio preprocessing module, a time domain feature extraction module, a frequency domain feature extraction module, a multi-granularity pooling module, a feature fusion module, a context sensing weighting module and an abnormal sound judgment module. The method has the beneficial effects that the defect that the prior art only depends on a single frequency domain feature and ignores time domain transient abnormal information is overcome by constructing a bimodal input mechanism of the time domain waveform and the frequency domain spectrogram, and complete representation of abnormal sound signals in a time-frequency joint space is realized.

The invention discloses a space active noise control and sound field optimization method for privacy office furniture, and the method comprises the steps: separating a mixed acoustic signal through employing a collection microphone array, and obtaining an environment noise reference signal and a user voice target signal; based on the environment noise reference signal, introducing a perception weighting adaptive filtering algorithm of a psychological acoustic model, and generating a first group of control signals for offsetting the environment noise; based on a user voice target signal, solving an optimization problem with multiple constraints, and generating a second group of control signals for constructing a light and dark privacy sound field; based on a collaborative strategy of model prediction control, a dynamic prediction model is established, the weight of noise reduction and privacy protection in a cost function is adjusted according to a voice activity detection result, an optimal control sequence of hardware physical constraint is solved, and a secondary sound source array is uniformly driven. According to the scheme of the invention, through an integrated cooperative control framework, the optimal balance between noise reduction and privacy is realized, and the subjective noise reduction experience and the robustness of the system in a dynamic environment are improved.

The invention discloses an audio sampling rate conversion method based on multi-rate signal processing and a related device, and the method comprises the steps: carrying out the self-adaptive multi-resolution time-frequency representation, perception weighting factor generation and weighted spectrum reconstruction of an original audio signal to be converted, and obtaining the weighted time-frequency representation; frequency sub-band division and sub-band independent resampling are carried out on the weighted time-frequency representation and the target sampling rate according to the Bark scale, and a resampling sub-band frequency spectrum is obtained; and performing sub-band synthesis on the re-sampling sub-band frequency spectrum to obtain a target frequency spectrum of a target sampling rate, performing inverse short-time Fourier transform on the target frequency spectrum to reconstruct a time domain audio signal, and obtaining a converted audio signal with the target sampling rate. According to the method, through weighted time-frequency representation and frequency sub-band division and independent resampling according with human ear hearing characteristics, the tone quality performance of audio sampling rate conversion is remarkably improved, and the perception quality of human ears on converted audio is optimized on the premise of ensuring signal integrity.

The invention discloses a speech enhancement method and system based on spectral decomposition. The method comprises the following steps: acquiring an amplitude spectrum and a phase spectrum of noisy speech through short-time Fourier transform; constructing a harmonic extraction model combining basis tracking and an auditory masking effect, and adaptively separating structured harmonic components through a non-convex optimization problem; performing sparse decomposition on the residual frequency spectrum by using an over-complete dictionary formed by Gabor atoms and Dirac atoms, and extracting transient detail components; synthesizing an enhanced amplitude spectrum by adopting a sensing weighted fusion strategy based on signal-to-noise ratio dynamic adjustment; and reconstructing a phase spectrum through a U-Net neural network and outputting a time domain signal. The method provided by the invention solves the problems of significant music noise, phase distortion and insufficient transient feature retention in the traditional method, and significantly improves the voice signal-to-noise ratio and perception quality in a complex noise environment.