Feature Vector Of Signal Research Articles

Detection of Ultrasonic closer flaws using Nonlinear signal processing

The ultrasonic flaw detection is an important problem in the nondestructive evaluation (NDE) of materials. In order to successfully detect and classify flaw echoes from high scattering grain echoes, an efficient and robust method is required. In this paper, a method using split-spectrum processing (SSP) combined with a neural network (NN) has been developed and applied on the ultrasonic signals to perform the detection of closer echoes. SSP can display signal diversity and is therefore able to provide the signal feature vectors for signal classification. The neural network (NN) performs highly complex nonlinear mapping by which signals can be classified according to their feature vectors. Therefore, the combination of SSP and NN (SSP-NN) presents a powerful technique for ultrasonic NDE. The SSP is achieved by using Gaussian bandpass filters. Then, an adaptive three layer neural network using a backpropagation learning process is applied to perform the classification processing of frequency diverse data. The SSP-NN method has been tested using both simulated and experimental ultrasonic signals, and the results show that SSP-NN has good sensitivity in the detection of ultrasonic closer flaws echoes drowned in the noise.

A New Feature Vector Using Selected Line Spectra for Pulsar Signal Bispectrum Characteristic Analysis and Recognition

Average pulse profiles of pulsar signals are analyzed using the bispectrum technique. The result shows that there are nonlinear phase couplings between the two frequency axes of the bispectrum charts, which indicate nonlinear factors in the generation and propagation of pulsar signals. Bispectra can be used as feature vectors of pulsar signals because of their being translation invariant. A one-dimension selected line spectrum algorithm for extracting pulsar signal characteristic is proposed. Compared with selected bispectra, the proposed selected line spectra have the maximum interclass separability measurements from the point of view of the whole one-dimension feature vector. Recognition experiments on several pulsar signals received at several frequency bands are carried out. The result shows that the selected line spectrum algorithm is suitable for extracting pulsar signal characteristics and has a good classification performance.

Method and apparatus for removing noise from feature vectors

A method and computer-readable medium are provided for identifying clean signal feature vectors from noisy signal feature vectors. The method is based on variational inference techniques. One aspect of the invention includes using an iterative approach to identify the clean signal feature vector. Another aspect of the invention includes using the variance of a set of noise feature vectors and/or channel distortion feature vectors when identifying the clean signal feature vectors. Further aspects of the invention use mixtures of distributions of noise feature vectors and/or channel distortion feature vectors when identifying the clean signal feature vectors. Additional aspects of the invention include using a variance for the noisy signal feature vector conditioned on fixed values of noise, channel transfer function, and clean speech, when identifying the clean signal feature vector.

Method of noise reduction using correction and scaling vectors with partitioning of the acoustic space in the domain of noisy speech

A method and apparatus are provided for reducing noise in a training signal and/or test signal. The noise reduction technique uses a stereo signal formed of two channel signals, each channel containing the same pattern signal. One of the channel signals is “clean” and the other includes additive noise. Using feature vectors from these channel signals, a collection of noise correction and scaling vectors is determined. When a feature vector of a noisy pattern signal is later received, it is multiplied by the best scaling vector for that feature vector and the best correction vector is added to the product to produce a noise reduced feature vector. Under one embodiment, the best scaling and correction vectors are identified by choosing an optimal mixture component for the noisy feature vector. The optimal mixture component being selected based on a distribution of noisy channel feature vectors associated with each mixture component.

A new feature vector using selected bispectra for signal classification with application in radar target recognition

Radially integrated bispectra (RIB), axially integrated bispectra (AIB), and circularly integrated bispectra (CIB) were used as feature vectors of signals, but many bispectra on integration paths may be redundant, and some bispectra are even baneful for signal classification. To avoid these problems, this paper proposes using selected bispectra with the maximum interclass separability as feature vectors of signals. In radar target recognition, range profiles are suitable feature vectors, but they have two main shortcomings: sensitivity to time shift and aspect dependence. Since the selected bispectra of range profiles are translation invariant and can avoid redundant and baneful bispectra as features, they are thus especially suitable for radar target recognition, which is shown by experiments.

Speech coding apparatus and method using classification rules

A speech coding apparatus and method uses classification rules to code an utterance while consuming fewer computing resources. The value of at least one feature of an utterance is measured during each of a series of successive time intervals to produce a series of feature vector signals representing the feature values. The classification rules comprise at least first and second sets of classification rules. The first set of classification rules map each feature vector signal from a set of all possible feature vector signals to exactly one of at least two disjoint subsets of feature vector signals. The second set of classification rules map each feature vector signal in a subset of feature vector signals to exactly one of at least two different classes of prototype vector signals. Each class contains a plurality of prototype vector signals. According to the classification rules, a first feature vector signal is mapped to a first class of prototype vector signals. The closeness of the feature value of the first feature vector signal is compared to the parameter values of only the prototype vector signals in the first class of prototype vector signals to obtain prototype match scores for the first feature vector signal and each prototype vector signal in the first class. At least the identification value of at least the prototype vector signal having the best prototype match score is output as a coded utterance representation signal of the first feature vector signal.

Speech coding apparatus and method for generating acoustic feature vector component values by combining values of the same features for multiple time intervals

A speech coding apparatus and method measures the values of at least first and second different features of an utterance during each of a series of successive time intervals. For each time interval, a feature vector signal has a first component value equal to a first weighted combination of the values of only one feature of the utterance for at least two time intervals. The feature vector signal has a second component value equal to a second weighted combination, different from the first weighted combination, of the values of only one feature of the utterance for at least two time intervals. The resulting feature vector signals for a series of successive time intervals form a coded representation of the utterance. In one embodiment, a first weighted mixture signal has a value equal to a first weighted mixture of the values of the features of the utterance during a single time interval. A second weighted mixture signal has a value equal to a second weighted mixture, different from the first weighted mixture, of the values of the features of the utterance during a single time interval. The first component value of each feature vector signal is equal to a first weighted combination of the values of only the first weighted mixture signals for at least two time intervals, and the second component value of each feature vector signal is equal to a second weighted combination, different from the first weighted combination, of the values of only the second weighted mixture for at least two time intervals.

PD classification by a modular neural network based on task decomposition

The use of modular neural network (MNN) for the recognition of partial discharge (PD) sources has been investigated. Three phase related quantities, the PD pulse counts, the average and maximum discharge magnitudes form the feature vector of a discharge signal. The MNN consists of 5 sub-networks with identical structure and a maximum selector. Each subnetwork is assigned the task to recognize a particular PD source. Compared with a single neural network which is trained to recognize all PD sources, the MNN has a higher training ability, faster rate of convergence and better recognition rate.

Speech coding apparatus having acoustic prototype vectors generated by tying to elementary models and clustering around reference vectors

A speech coding apparatus in which measured acoustic feature vectors are each represented by the best matched prototype vector. The prototype vectors are generated by storing a model of a training script comprising a series of elementary models. The value of at least one feature of a training utterance of the training script is measured over each of a series of successive time intervals to produce a series of training feature vectors. A first set of training feature vectors corresponding to a first elementary model in the training script is identified. The feature value of each training feature vector signal in the first set is compared to the parameter value of a first reference vector signal to obtain a first closeness score, and is compared to the parameter value of a second reference vector to obtain a second closeness score for each training feature vector. For each training feature vector in the first set, the first closeness score is compared with the second closeness score to obtain a reference match score. A first subset contains those training feature vectors in the first set having reference match scores better than a threshold Q, and a second subset contains those having reference match scores less than the threshold Q. One or more partition values are generated for a first prototype vector frown the first subset of training feature vectors, and one or more additional partition values are generated for the first prototype vector from the second subset of training feature vectors.

Speech recognition apparatus having a speech coder outputting acoustic prototype ranks

A speech coding and speech recognition apparatus. The value of at least one feature of an utterance is measured over each of a series of successive time intervals to produce a series of feature vector signals. The closeness of the feature value of each feature vector signal to the parameter value of each of a set of prototype vector signals is determined to obtain prototype match scores for each vector signal and each prototype vector signal. For each feature vector signal, first-rank and second-rank scores are associated with the prototype vector signals having the best and second best prototype match scores, respectively. For each feature vector signal, at least the identification value and the rank score of the first-ranked and second-ranked prototype vector signals are output as a coded utterance representation signal of the feature vector signal, to produce a series of coded utterance representation signals. For each of a plurality of speech units, a probabilistic model has a plurality of model outputs, and output probabilities for each model output. Each model output comprises the identification value of a prototype vector and a rank score. For each speech unit, a match score comprises an estimate of the probability that the probabilistic model of the speech unit would output a series of model outputs matching a reference series comprising the identification value and rank score of at least one prototype vector from each coded utterance representation signal in the series of coded utterance representation signals.

Linear predictive speech coding arrangement

A speech analyzer is adapted to produce speech parameter signals from a Pth order autocorrelation analysis of a speech pattern in a digital signal processor. The analyzer includes a plurality of memories of predetermined arrangement to store feature vector signals used in the analysis, a single set of coded signals for controlling the analysis, and a memory address processor for addressing the feature vector signal memories. In each iteration of the analysis, at least one speech parameter signal is produced by the digital signal processor responsive to the same set of control signals and the feature vector memory addressing signals.

Speech recognition apparatus and method

In this speech recognition system the array formed by a timewise sequence of speech signal feature vectors includes digital data at each time slot representing both presence/absence and consistency of occurence.

Musical tone origin identification by pattern matching

A method of determining the origin of a musical tone by pattern matching has been developed. Multidimensional feature vectors characterizing tone types were generated from the fit of an auto-regressive (linear prediction) model of flute, guitar, marimba, and piano tones. Identification templates (or reference vectors) for each musical instrument type were constructed from these feature vectors. Ultimately, identification was performed by minimizing the least-mean-squares distance of an unknown signal's feature vector to the previously constructed identification templates.