333 results about "Cepstrum" patented technology

The present invention discloses a complete speech recognition system having a training button and a recognition button, and the whole system uses the application specific integrated circuit (ASIC) architecture for the design, and also uses the modular design to divide the speech processing into 4 modules: system control module, autocorrelation and linear predictive coefficient module, cepstrum module, and DTW recognition module. Each module forms an intellectual product (IP) component by itself. Each IP component can work with various products and application requirements for the design reuse to greatly shorten the time to market.

A method for controlling subscription services delivered to a user by an Internet Service Provider (ISP) coupled to an Automated Intelligent Network (AIN) telephone system with at least one central office switching system. An intelligent peripheral subsystem is connected to the central office switching system, via a call connection channel. The intelligent peripheral subsystem providing at least one auxiliary call processing capability via the call connection channel and provides a telephony speaker authentication method for selectively authorizing updates to user subscription services types provided by the ISP, wherein each of the subscription services types include one or more service options. The method for controlling subscription services including: a) prompting for a voice response; b) authenticating a user's voice response pattern by performing a speaker-dependent cepstrum matching algorithm with previously stored samples of the user's voice response, and if the user's voice response pattern is positively authenticated with previously stored samples, then performing the steps of: c) presenting a menu of user subscription types, each with available AIN service options; and d) responding to a user selection of at least one user subscription types, each with service option, by activating a service option selected by the user, wherein the service option is governed by said ISP by regulating one or more Uniform Resource Locator (URL) addresses received by a user subscriber device from said ISP over a telecommunication line.

The device and method of the invention receives a digital speech signal, which is processed by an Acoustic Processor to produce a Mel-Cepstrum Vector and Pitch. This is recalibrated and encoded. The encoded signal is transmitted over a narrow-band Channel, then decoded, split and recalibrated. From the split signals, one signal feeds a Statistical Processor which produces Recognized Text. Another signal feeds a Regenerator, which produces Regenerated Speech. The device and method according to the invention achieve simultaneously very perceptive Automatic Speech Recognition and high quality VoCoding, using Speech communicated or stored via a Channel with narrow-bandwidth; very perceptive Automatic Speech Recognition on a Client & Server system without a need to store or to communicate wide-bandwidth Speech signals; very perceptive Automatic Speech Recognition with Deferred Review and Editing without storage of wide-bandwidth Speech signals; better feedback in a system for Automatic Speech Recognition particularly for Deferred Automatic Speech Recognition; and good usability for unified Automatic Speech Recognition and VoCoding.

A computer-implemented method and apparatus for embedding hidden data in an audio signal. An audio signal is received in a base domain and then transformed into a non-base domain, such as cepstrum domain or LP residue domain. The statistical mean manipulation is employed on selected transform coefficients to embed hidden data. The introduced distortion is controlled by psychoacoustic model to ensure the imperceptibility of the embedded hidden data. Scrambling techniques can be plugged in to further increase the security of the data hiding system. The present new audio data hiding scheme provides transparent audio quality, sufficient embedding capacity, and high survivability over a wide range of common signal processing attacks.

Processing of plethysmographic signals via the cepstral domain is provided. In one embodiment, a cepstral domain plethysmographic signal processing method (200) includes the steps of obtaining (210) time domain plethysmographic signals, smoothing (220) the time domain plethysmographic signals, performing (230) a first-stage Fourier transformation of the time domain plethysmographic signals to frequency domain plethysmographic signals, computing (240) power spectrums from the frequency domain plethysmographic signals, scaling (250) the power spectrums with a logarithmic function, performing (260) a second-stage Fourier transformation on log-scaled spectrums to transform the power spectrums into cepstrums, and examining (270) the cepstrums to obtain information therefrom relating to a physiological condition of the patient such as the patient's pulse rate or SPO2 level.

The invention provides a double-microphone speech enhancer, which comprises a double-microphone array module, a delay compensation module, a cepstrum field dereverberation module, a speech enhancement processing module and an output module, wherein the cepstrum field dereverberation module has the effect of dereverberation. The invention also provides a speech enhancement method based on the double-microphone speech enhancer. The invention adopts the cepstrum field dereverberation module to carry out beam formation and low-pass filtering, and can effectively eliminate the affection of room reverberation, and meanwhile, by using a speech enhancement algorithm, background noise can be further suppressed.

The invention discloses a voice enhancing method based on a multiresolution auditory cepstrum system and a deep convolutional neural network. The voice enhancing method comprises the following steps:firstly, establishing new characteristic parameters, namely multiresolution auditory cepstrum coefficient (MR-GFCC), capable of distinguishing voice from noise; secondly, establishing a self-adaptivemasking threshold on based on ideal soft masking (IRM) and ideal binary masking (IBM) according to noise variations; further training an established seven-layer neural network by using new extracted characteristic parameters and first/second derivatives thereof and the self-adaptive masking threshold as input and output of the deep convolutional neural network (DCNN); and finally enhancing noise-containing voice by using the self-adaptive masking threshold estimated by the DCNN. By adopting the method, the working mechanism of human ears is sufficiently utilized, voice characteristic parameters simulating a human ear auditory physiological model are disposed, and not only is a relatively great deal of voice information maintained, but also the extraction process is simple and feasible.

The invention discloses an identification method of fundamental frequency for detection of the force of the cable of a stayed-cable bridge, which gets a first fundamental frequency by an autopower spectrum module, a second fundamental frequency by a cepstrum module, and then determines whether the quotient of the following two values is less than or equal to the set threshold: 1. the absolute value of the difference of the first fundamental frequency and the second fundamental frequency; 2. a half of the sum of the first fundamental frequency and the second fundamental frequency. In this way, whether the fundamental frequency of the pull cable is a half of the first fundamental frequency and the second fundamental frequency is determined. By adopting the method, the accuracy and the precision of the fundamental frequencies got are significantly improved. In addition, as the vibration acceleration response time interval signal got by an acceleration sensor passes through a signal conditioning module for filtration and smooth processing firstly, the environmental noise in the vibration acceleration response time interval signal is effectively suppressed; the antijamming capability of the stayed-cable bridge is improved so that the fundamental frequency is identified more clearly and accurately.

The invention relates to a fault diagnosis method, in particular to a rolling bearing fault diagnosis method based on the vibration detection. The method comprises the following steps of firstly decomposing the rolling bearing data collected by an acceleration sensor into three layers of wavelet packets, solving the energy of a third layer of wavelet packet coefficient rebuilding signals, selecting a frequency band with centralized energy to rebuild approximate evaluation of an original signal according to the variation of energy values of each frequency bands of the third layer; and utilizing a cepstrum to further analyze the rebuilt signal, and comparing the rebuilt signal with a theoretically-computed fault characteristic frequency and an edge frequency characteristic. By combining multiple resolutions of the wavelet packet and the cepstrum, the periodic component on a power spectrum, a separated-side frequency-band signal and the characteristics which are slightly subjected to the transmission route can be well detected. Meanwhile, the method is strong in manipulability and practicability.

An adjustable K-factor-improvement (KFI) filter having a sparse kernel composed of non-zero weighting coefficients of substantially equal amplitudes is included in a receiver for digital television signals or the like. The receiver includes apparatus for measuring the channel impulse response (CIR) or cepstrum of the signal as received. The respective polarities of the non-zero weighting coefficients in the sparse kernel of the adjustable KFI filter are adjusted responsive to the measured CIR. The differential delay between each successive pair of non-zero weighting coefficients in the sparse kernel of the adjustable K-factor-improvement filter is adjusted responsive to the measured CIR. The adjustment is such that the KFI filter response has a principal component with substantially more energy than any of its echo components. The KFI filter response is applied as input signal to subsequent adaptive equalization filtering in the receiver.

A monitoring apparatus comprising a multichannel pressure sensing sensor for measuring a ballistocardiographic signal of a human body is disclosed. The monitoring apparatus also comprises means for selecting a time window for heart inter beat interval including two consecutive heart beats to be estimated, defining a spectrum for the ballistocardiographic signal averaging between at least two measurement channels of the multichannel pressure sensing sensor, a cepstrum from the logarithm of a spectrum, and a heart inter beat interval. The invention relates to a method for defining a heart inter beat interval, where a ballistocardiographic signal of a body is measured with a multichannel pressure sensing sensor, a time window for heart inter beat interval Including two consecutive heart beats to be estimated is selected, a spectrum for the ballistocardiographic signal averaging between at least two measurement channels of the multichannel pressure sensing sensor, a cepstrum from the logarithm of a spectrum, and a heart inter beat interval are defined.

The invention discloses a robust speech characteristic extraction method based on sparse decomposition and reconfiguration, relating to a robust speech characteristic extraction method with sparse decomposition and reconfiguration. The robust speech characteristic extraction method solves the problems that 1, the selection of an atomic dictionary has higher the time complexity and is difficult tomeet the sparsity after signal projection; 2, the sparse decomposition of signals has less consideration for time relativity of speech signals and noise signals; and 3, the signal reconfiguration ignores the prior probability of atoms and mutual transformation of all the atoms. The robust speech characteristic extraction method comprises the following detailed steps of: step 1, preprocessing; step 2, conducting discrete Fourier transform and solving a power spectrum; step 3, training and storing the atom dictionary; step 4, conducting sparse decomposition; step 5, reconfiguring the speech spectrum; step 6, adding a Mel triangular filter and taking the logarithm; and step 7, obtaining sparse splicing of Mel cepstrum coefficients and a Mel cepstrum to form the robust characteristic. The robust speech characteristic extraction method is used for the fields of multimedia information processing.

The invention relates to a speaker recognition method for filtering the emotional tone by using pitch envelop. In the test for speaker recognition, the mutually corresponding cepstrum features and pitch frequency which are firstly extracted from a segment of tone; the gender information is obtained by testing on the gender model which is trained in advance according to the cepstrum features; the thresholds adopted in the method for filtering the emotional tone are determined by gender information; the pitch envelope is picked out according to the thresholds, and then the cepstrum features are filtered according to the serial number of each frame in pitch envelope, thus acquiring the processed cepstrum features; finally, the GMM system test is carried out on the processed cepstrum features.The beneficial effects of the invention are as follows: the inconvenience to the system which needs providing the emotional tone of the speaker in the training or the emotion information of the speech in the test in a traditional method is eliminated, and the recognition performance is increased by 8% compared with traditional ASR system.

Disclosed is a blind restoration method for the motion blurred image; the steps are as follows: (1) the image is converted through the cepstrum method to figure out the blur extent and the blur direction of the blurred image; (2) the blur extent and the blur direction of the blurred image figured out in step (1), and the total variation (TV) method are adopted to process the restoration towards the blurred image. The method based on the total variation (TV) includes: the fixed-point iteration used as the outer-loop and the conjugate gradient method used as the inner-loop are adopted for loop iteration to obtain the restored image. The blind restoration method has the advantages of strong self-adaptation, strong anti-noise ability and good robustness; the blind restoration method has validity and practicality according to the processing effects of the simulation picture and the photographed picture.

The invention discloses an end-to-end speech emotion recognition method and system. The method comprises the steps: extracting the phoneme features of speech data; extracting cepstrum features of thespeech data; aligning the phoneme vector sequence and the cepstrum feature by taking a file as a unit, taking the phoneme vector sequence and the cepstrum feature as input, and performing end-to-end speech emotion recognition model training by utilizing a deep neural network; when the model is deployed, carrying out resampling and effective speech segment detection on any input speech data. By using the feature extraction process and the recognition model, end-to-end recognition can be performed on the speech data, the efficiency is higher, and the prediction is more accurate.

The invention discloses an isolated word speech recognition method based on an HRSF (Half Raised Sine Function) and an improved DTW (Dynamic Time Warping) algorithm. The isolated word speech recognition method comprises the following steps that (1), a received analog voice signal is preprocessed; preprocessing comprises pre-filtering, sampling, quantification, pre-emphasis, windowing, short-time energy analysis, short-time average zero crossing rate analysis and end-point detection; (2), a power spectrum X(n) of a frame signal is obtained by FFT (Fast Fourier Transform) and is converted into a power spectrum under a Mel frequency; an MFCC (Mel Frequency Cepstrum Coefficient) parameter is calculated; the calculated MFCC parameter is subjected to HRSF cepstrum raising after a first order difference and a second order difference are calculated; and (3), the improved DTW algorithm is adopted to match test templates with reference templates; and the reference template with the maximum matching score serves as an identification result. According to the isolated word speech recognition method, the identification of a single Chinese character is achieved through the improved DTW algorithm, and the identification rate and the identification speed of the single Chinese character are increased.

The invention relates to a music voice tone changing method for stabilizing tone quality, and the method comprises the steps: exporting a spectrum envelope through employing a voice signal, which can be divided into a glottis stimulation component and a channel stimulation response component, and the cepstrum sequence of the voice signal; separating the stimulation component of the voice signal through employing the spectrum envelope; carrying out the processing of the stimulation components of the voice signal through a tone changing algorithm, and changing the pitch of the voice signal; finally enabling the stimulation components to be synthesized again after the spectrum envelope and the pitch are changed, and obtaining a music voice signal with the changed pitch and the stable tone quality. The method provided by the invention is simple, is flexible in implementation, and is higher in practicality.

The present invention discloses a gas pipeline leakage detection and identification method based on optical fiber sensing data excavation. The method comprises: employing distributed optical fiber sound waves/a vibration sensor to pick up leakage sound waves/vibration signals propagated along a pipeline, performing Mel cepstrum, AR model feature extraction and feature selection of the collected leakage sound waves/vibration signals of each space point, and establishing an association rule of the selected feature attributes and a type of a leakage event through an improved feature rule excavation method and positive and negative sample excavation to perform real-time online intelligent detection, identification and classification of a gas pipeline leakage event and solve a gas pipeline online leakage detection problem under a complex noise environment. The gas pipeline leakage detection and identification method based on optical fiber sensing data excavation can detect and identify simple pipeline leakage signals, and can detect and identify leakage signals mixed with different interference sources.

A voice recognition system comprises an analyzer for converting an input voice signal to an input pattern including cepstrum, a reference pattern for storing reference patterns, an elongation/contraction estimating unit for outputting an elongation/contraction parameter in frequency axis direction by using the input pattern and the reference patterns, and a recognizing unit for calculating the distances between the converted input pattern from the converter and the reference patterns and outputting the reference pattern corresponding to the shortest distance as result of recognition. The elongation/contraction unit estimates an elongation/contraction parameter by using cepstrum included in the input pattern. The elongation/contraction unit does not have various values in advance for determining the elongation/contraction parameter, nor is it necessary for the elongation/contraction unit have to execute distance calculation for various values.

The invention discloses an audio-reverberation inhibiting device and an inhibiting method thereof. The device includes a reverberation-time blind estimation module, a later-period reverberation power spectrum estimation module, a spectral-subtraction module and a complex-cepstrum-domain filtering module. A reverberation voice estimates a reverberation time through the reverberation-time blind estimation module. The later-period reverberation power spectrum estimation module establishes a reverberation statistical model through the estimated reverberation time and carries out analysis processing on the reverberation voice so that a later-period reverberation power spectrum is obtained. The spectral-subtraction module includes a gain function structure and a spectral-subtraction implementation module and a spectral-subtraction gain function is constructed firstly through use of a reverberation-voice power spectrum and a later-period reverberation power spectrum. Then the spectral-subtraction gain function and the reverberation voice are input into the spectral-subtraction implementation module so that an earlier-period voice is obtained. Finally, the earlier-period voice is input into the complex-cepstrum-domain filtering module so that a reverberation-removed voice is obtained. The audio-reverberation inhibiting device and the inhibiting method thereof is low in calculation complexity, convenient to handle in a real-time manner and capable of inhibiting audio reverberation obviously and improving voice quality efficiently.

The invention discloses a blurred image detection method fusing frequency spectrum information and cepstrum information, belongs to the technical field of image processing, and particularly relates to the detection technology of various blurred images. According to the blurred image detection method, first, an energy frequency spectrum distribution feature and a singularity cepstrum value histogram feature of an image are calculated, and serve as blur features of the image; second, a support vector machine classifier is selected for differentiating sharp image features from the blur image features, and collected images with demarcated blur categories is used for training corresponding parameters of the support vector machine classifier; finally, the trained support vector machine classifier is used for detecting whether an image to be detected is a blurred image. The blurred image detection method has the advantage that as a non-reference blurred image detection method, the blurred image detection method needs no reference image, thereby being wide in application range; meanwhile, the defined blur features have specific physical significance, and therefore the sharp image and the blurred image can be differentiated accurately.

The invention discloses a speech enhancement method based on Gaussian mixture model (GMM) noise estimation, wherein the GMM is used for estimating background noise and a spectral subtraction coefficient, spectral subtraction is conducted on noisy speech, and pure speech is recovered. Firstly, the noisy speech is preprocessed so as to obtain the amplitude and phase of the noisy speech, the amplitude is used for noise estimation and spectral subtraction, and the phase is used for recovering a time-domain signal; then, the GMM is used for estimating noise parameters and pure speech cepstrum characteristics from the noisy speech in real time, and the spectral subtraction coefficient is calculated according to the estimated pure speech cepstrum characteristics; finally, spectral subtraction is conducted on the frequency spectrum of the noisy speech, the time-domain signal is recovered, and enhanced speech is obtained according to an overlap-add method. According to the speech enhancement method, the capability of the speech enhancement algorithm to track non-stationary noise can be improved remarkably.

The invention provides a bi-ear time delay estimating method based on frequency division and improved generalized cross correlation in reverberation environment, and relates to the field of sound source positioning. A Gammatone filter is used to effectively simulate characteristics of a basal membrane of a human ear, voice signals are subjected to frequency division processing, and two-ear cross-correlation delay is estimated under a reverberation environment. Compared with a generalized cross correlation delay estimating method, the method can estimate time delay more accurately. The sound source positioning system has better robustness. A Gammatone filter is used to conduct frequency dividing processing for bi-ear signals, and each sub-band signal is subjected to inverse transformation to a time domain after reverberation processing of cepstrum and pre-filtering. Each sub-band signal of left and right ears are subjected to generalized cross correlation operation, an improved phase transformation weight function is employed in a generalized cross correlation algorithm to obtain cross correlation value of each sub-band for summing operation, and the bi-ear time difference corresponding to maximal cross correlation value is obtained.