Linear Predictive Coding Coefficients Research Articles

Pilot based channel estimation improvement in orthogonal frequency-division multiplexing systems using linear predictive coding

Pilot based least square (LS) channel estimation is a commonly used channel estimation technique in orthogonal frequency-division multiplexing based systems due to its simplicity. However, LS estimation does not handle the noise effect and hence suffers from performance degradation. Since the channel coefficients are correlated in time and hence show a slower variation than the noise, it is possible to encode the channel using linear predictive coding (LPC) without the noise. In this work, the channel is estimated from the pilots using LS estimation and in a second step the channel’s LS estimated is encoded as LPC coefficients to produce an improved channel estimation. The estimation technique is simulated for space-time block coding (STBC) based orthogonal frequency-division multiplexing (OFDM) system and the bit error rate (BER) curves show improvement of the LPC estimation over the LS estimation of the channel.

Robust children’s speech recognition in zero resource condition

User applications such as voice-based web search, online learning, and video gaming require an effective speech recognition module to take user commands. Nowadays, even children are frequently using such tools, especially for online learning and gaming. This has increased the demand for developing a noise-robust automatic speech recognition (ASR) system that can effectively transcribe children’s data under varied ambient conditions. However, automatic recognition of children’s speech is extremely challenging due to the insufficiency of data from child speakers in the majority of the languages across the world. Consequently, in this zero-resource condition, we are forced to decode children’s speech on systems trained using adults’ data. However, the acoustic mismatch between adults’ and children’s speech, such as differences in pitch, formant frequencies, and speaking-rates, leads to highly degraded recognition performance. To enhance the recognition rate under zero-resource conditions, we have explored the role of formant and duration-modification-based out-of-domain data augmentation in this paper. For that purpose, the formant frequencies of the adults’ speech data are upscaled using warping of linear predictive coding coefficients. On pooling original and formant modified adults’ speech data into training, the mismatch in formant locations is reduced leading to better recognition performance. Further improvement in recognition rate can be achieved by simultaneously modifying the duration as well as the formant frequencies of the training data. This case of out-of-domain data augmentation has also been studied in this work and found to yield added gains. In addition to data augmentation, a noise- and pitch-robust front-end acoustic feature extraction approach exploiting higher-order spectral analysis (simple and cross-bispectrum) is also proposed in this paper. The proposed features are noise-robust due to the inherent immunity of the bispectrum towards additive noises. An added advantage of bispectrum is reduced pitch sensitivity as demonstrated in this work. This, in turn, helps alleviate the aforementioned pitch-induced acoustic mismatch. The experimental evaluations presented in this paper demonstrate that the use of proposed acoustic features, as well as the out-of-domain data augmentation techniques, are highly suited for zero-resource children’s speech recognition tasks under clean and noisy conditions.

Modeling and Reproducing Textile Sensor Noise: Implications for Textile-Compatible Signal Processing Algorithms.

Smart textiles provide an opportunity to simultaneously record various electrophysiological signals, e.g., ECG, from the human body in a non-invasive and continuous manner. Accurate processing of ECG signals recorded using textile sensors is challenging due to the very low signal-to-noise ratio (SNR). Signal processing algorithms that can extract ECG signals out of textile-based electrode recordings, despite low SNR are needed. Presently, there are no textile ECG datasets available to develop, test and validate these algorithms. In this paper we attempted to model textile ECG signals by adding the textile sensor noise to open access ECG signals. We employed the linear predictive coding method to model different features of this noise. By approximating the linear predictive coding residual signals using Kernel Density Estimation, an artificial textile ECG noise signal was generated by filtering the residual signal with the linear predictive coding coefficients. The synthetic textile sensor noise was added to the MIT-BIH Arrhythmia Database (MITDB), thus creating Textile-like ECG dataset consisting of 108 trials (30 min each). Furthermore, a Python code for generating textile-like ECG signals with variable SNR was also made available online. Finally, to provide a benchmark for the performance of R-peak detection algorithms on textile ECG, the five common R-peak detection algorithms: Pan & Tompkins, improved Pan & Tompkins (in Biosppy), Hamilton, Engelse, and Khamis, were tested on textile-like MITDB. This work provides an approach to generating noisy textile ECG signals, and facilitating the development, testing, and evaluation of signal processing algorithms for textile ECGs.

Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal.

The aim of the study was to inspect the acoustic properties and sleep characteristics of a preapneic snoring sound. The feasibility of forecasting upcoming respiratory events by snoring sound was also investigated. Participants with habitual snoring or a heavy breathing sound during sleep were recruited consecutively. Polysomnography was conducted, and snoring-related breathing sound was recorded simultaneously. Acoustic features and sleep features were extracted from 30-second samples, and a machine learning algorithm was used to establish 2 prediction models. A total of 74 eligible participants were included. Model 1, tested by 5-fold cross-validation, achieved an accuracy of 0.92 and an area under the curve of 0.94 for respiratory event prediction. Model 2, with acoustic features and sleep information tested by Leave-One-Out cross-validation, had an accuracy of 0.78 and an area under the curve of 0.80. Sleep position was found to be the most important among all sleep features contributing to the performance of the 2 models. Preapneic sound presented unique acoustic characteristics, and snoring-related breathing sound could be deployed as a real-time apneic event predictor. The models, combined with sleep information, serve as a promising tool for an early warning system to forecast apneic events. Wang B, Yi X, Gao J, etal. Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal. J Clin Sleep Med. 2021;17(9):1777-1784.

Speaker Recognition Systems in the Last Decade – A Survey

Speaker Recognition Defined by the process of recognizing a person by his\her voice through specific features that extract from his\her voice signal. An Automatic Speaker recognition (ASP) is a biometric authentication system. In the last decade, many advances in the speaker recognition field have been attained, along with many techniques in feature extraction and modeling phases. In this paper, we present an overview of the most recent works in ASP technology. The study makes an effort to discuss several modeling ASP techniques like Gaussian Mixture Model GMM, Vector Quantization (VQ), and Clustering Algorithms. Also, several feature extraction techniques like Linear Predictive Coding (LPC) and Mel frequency cepstral coefficients (MFCC) are examined. Finally, as a result of this study, we found MFCC and GMM methods could be considered as the most successful techniques in the field of speaker recognition so far.

Automatic Evaluation of Heart Condition According to the Sounds Emitted and Implementing Six Classification Methods.

The main cause of death in Mexico and the world is heart disease, and it will continue to lead the death rate in the next decade according to data from the World Health Organization (WHO) and the National Institute of Statistics and Geography (INEGI). Therefore, the objective of this work is to implement, compare and evaluate machine learning algorithms that are capable of classifying normal and abnormal heart sounds. Three different sounds were analyzed in this study; normal heart sounds, heart murmur sounds and extra systolic sounds, which were labeled as healthy sounds (normal sounds) and unhealthy sounds (murmur and extra systolic sounds). From these sounds, fifty-two features were calculated to create a numerical dataset; thirty-six statistical features, eight Linear Predictive Coding (LPC) coefficients and eight Cepstral Frequency-Mel Coefficients (MFCC). From this dataset two more were created; one normalized and one standardized. These datasets were analyzed with six classifiers: k-Nearest Neighbors, Naive Bayes, Decision Trees, Logistic Regression, Support Vector Machine and Artificial Neural Networks, all of them were evaluated with six metrics: accuracy, specificity, sensitivity, ROC curve, precision and F1-score, respectively. The performances of all the models were statistically significant, but the models that performed best for this problem were logistic regression for the standardized data set, with a specificity of 0.7500 and a ROC curve of 0.8405, logistic regression for the normalized data set, with a specificity of 0.7083 and a ROC curve of 0.8407, and Support Vector Machine with a lineal kernel for the non-normalized data; with a specificity of 0.6842 and a ROC curve of 0.7703. Both of these metrics are of utmost importance in evaluating the performance of computer-assisted diagnostic systems.

Speech Recognition Using Elman Artificial Neural Network and Linear Predictive Coding

Background: Today, the automatic intelligent system requirement has caused an increasing consideration on the interactive modern techniques between human being and machine. These techniques generally consist of two types: audio and visual methods. Meanwhile, the need for developing the algorithms that enable the human speech recognition by machine is of high importance and frequently studied by the researchers. Objective: Using artificial intelligence methods has led to better results in human speech recognition, but the basic problem is the lack of an appropriate strategy to select the recognition data among the huge amount of speech information that practically makes it impossible for the available algorithms to work. Method: In this article, to solve the problem, the linear predictive coding coefficients extraction method is used to sum up the data related to the English digits pronunciation. After extracting the database, it is utilized to an Elman neural network to recognize the relation between the linear coding coefficients of an audio file with the pronounced digit. Results: The results show that this method has a good performance compared to other methods. According to the experiments, the obtained results of network training (99% recognition accuracy) indicate that the network still has better performance than RBF despite many errors. Conclusion: The results of the experiments showed that the Elman memory neural network has had an acceptable performance in recognizing the speech signal compared to the other algorithms. The use of the linear predictive coding coefficients along with the Elman neural network has led to higher recognition accuracy and improved the speech recognition system.

Speaker verification from mixture of speech and non-speech audio signals via using pole distribution of piecewise linear predictive coding coefficients

This paper examines a method of speaker verification from mixture of speech and non-speech audio signals via using pole distribution of speech signals. The poles of speech signal derived from the all-pole speech production model are obtained via a neural net called bagging CAN2 (competitive associative net 2) for learning efficient piecewise linear approximation of nonlinear functions. We show an analysis that poles of the mixture of two audio signals are expected to show three typical phenomena. Namely, with the change of the weight of the mixture, there will be (1) a sudden change of the number of poles, (2) a gradual change of the number of poles, and (3) novel poles not in the original signals. By means of experiments, we show that there are poles exhibiting those phenomena, and they are considered to affect the performance on speaker verification. As a performance measure of speaker verification, recall shows large decrease with the change of speech signal from unmixed to mixed, especially for the mixture with violin signal as well as with speech signal. Furthermore, precision has larger value than recall for the same dataset of mixture of audio signals. Finally, we show the usefulness of the present method in further researches.

Speech to Text Processing for Interactive Agent of Virtual Tour Navigation

The development of science and technology is one way to replace the method of human interaction with computers, one of which is to provide voice input. Conversion of sound into text form with the Backpropagation method can be understood and realized through feature extraction, including the use of Linear Predictive Coding (LPC). Linear Predictive Coding is one way to represent the signal in obtaining the features of each sound pattern. In brief, the way this speech recognition system worked was by inputting human voice through a microphone (analog signal) which then sampled with a sampling speed of 8000 Hz so that it became a digital signal with the assistance of sound card on the computer. The digital signal from the sample then entered the initial process using LPC, so that several LPC coefficients were obtained. The LPC outputs were then trained using the Backpropagation learning method. The results of the learning were classified with a word and stored in a database afterwards. The results of the test were in the form of an introduction program that able display the voice plots. the results of speech recognition with voice recognition percentage of respondents in the database iss 80% of the 100 data in the test in Real Time

Word recognition from speech signal using linear predictive coding and spectrum analysis

This paper presents a technique for isolated word recognition from speech signal using Spectrum Analysis and Linear Predictive Coding (LPC). In the present study, only those words have been analyzed which are commonly used during a telephonic conversations by criminals. Since each word is characterized by unique frequency spectrum signature, thus, spectrum analysis of a speech signal has been done using certain statistical parameters. These parameters help in recognizing a particular word from a speech signal, as there is a unique value of a feature for each word, which helps in distinguishing one word from the other. Second method used is based on LPC coefficients. Analysis of features extracted using LPC coefficients help in identification of a specific word from the input speech signal. Finally, a combination of best features from these two methods has been used and a hybrid technique is proposed. An accuracy of 94% has been achieved for sample size of 400 speech words.

Genetic Algorithm for Combined Speaker and Speech Recognition using Deep Neural Networks

Huge growth is observed in the speech and speaker recognition field due to many artificial intelligence algorithms being applied. Speech is used to convey messages via the language being spoken, emotions, gender and speaker identity. Many real applications in healthcare are based upon speech and speaker recognition, e.g. a voice-controlled wheelchair helps control the chair. In this paper, we use a genetic algorithm (GA) for combined speaker and speech recognition, relying on optimized Mel Frequency Cepstral Coefficient (MFCC) speech features, and classification is performed using a Deep Neural Network (DNN). In the first phase, feature extraction using MFCC is executed. Then, feature optimization is performed using GA. In the second phase training is conducted using DNN. Evaluation and validation of the proposed work model is done by setting a real environment, and efficiency is calculated on the basis of such parameters as accuracy, precision rate, recall rate, sensitivity, and specificity. Also, this paper presents an evaluation of such feature extraction methods as linear predictive coding coefficient (LPCC), perceptual linear prediction (PLP), mel frequency cepstral coefficients (MFCC) and relative spectra filtering (RASTA), with all of them used for combined speaker and speech recognition systems. A comparison of different methods based on existing techniques for both clean and noisy environments is made as well.

A Review on Emotion Recognition Algorithms using Speech Analysis

In recent years, there is a growing interest in speech emotion recognition (SER) by analyzing input speech. SER can be considered as simply pattern recognition task which includes features extraction, classifier, and speech emotion database. The objective of this paper is to provide a comprehensive review on various literature available on SER. Several audio features are available, including linear predictive coding coefficients (LPCC), Mel-frequency cepstral coefficients (MFCC), and Teager energy based features. While for classifier, many algorithms are available including hidden Markov model (HMM), Gaussian mixture model (GMM), vector quantization (VQ), artificial neural networks (ANN), and deep neural networks (DNN). In this paper, we also reviewed various speech emotion database. Finally, recent related works on SER using DNN will be discussed.

Investigation of Combined use of MFCC and LPC Features in Speech Recognition Systems

Statement of the automatic speech recognition problem, the assignment of speech recognition and the application fields are shown in the paper. At the same time as Azerbaijan speech, the establishment principles of speech recognition system and the problems arising in the system are investigated. The computing algorithms of speech features, being the main part of speech recognition system, are analyzed. From this point of view, the determination algorithms of Mel Frequency Cepstral Coefficients (MFCC) and Linear Predictive Coding (LPC) coefficients expressing the basic speech features are developed. Combined use of cepstrals of MFCC and LPC in speech recognition system is suggested to improve the reliability of speech recognition system. To this end, the recognition system is divided into MFCC and LPC-based recognition subsystems. The training and recognition processes are realized in both subsystems separately, and recognition system gets the decision being the same results of each subsystems. This results in decrease of error rate during recognition. The training and recognition processes are realized by artificial neural networks in the automatic speech recognition system. The neural networks are trained by the conjugate gradient method. In the paper the problems observed by the number of speech features at training the neural networks of MFCC and LPC-based speech recognition subsystems are investigated. The variety of results of neural networks trained from different initial points in training process is analyzed. Methodology of combined use of neural networks trained from different initial points in speech recognition system is suggested to improve the reliability of recognition system and increase the recognition quality, and obtained practical results are shown.

An intelligent system for estimating frog community calling activity and species richness

Over the past decade, dramatic declines in frog populations have been noticed worldwide. To examine this decline, monitoring frogs is becoming increasingly important. Compared to traditional field survey methods, recent advances in acoustic sensor technology have greatly extended spatial and temporal scales for monitoring animal populations. In this paper, we examine the problem of monitoring frog populations by analysing acoustic sensor data, where the population is reflected by community calling activity and species richness. Specifically, a novel acoustic event detection (AED) algorithm is first proposed to filter out those recordings without frog calls. Then, multi-label learning is used to classify each individual recording with six acoustic features: linear predictive coding coefficients, Mel-frequency cepstral coefficients, linear-frequency cepstral coefficients, acoustic complexity index, acoustic diversity index, and acoustic evenness index. Next, frog community calling activity and species richness are estimated by accumulating the results of AED and multi-label learning, respectively. Finally, ordinary least squares regression (OLS) is conducted to reveal the relationship between frog populations (frog calling activity and species richness) and weather variables (maximum temperature and rainfall). Experimental results demonstrate that our proposed intelligent system can significantly facilitate the effort to estimate frog community calling activity and species richness with comparable accuracies. The statistical results of OLS indicate that rainfall pattern has a lagged impact on frog community calling activity (significant in the first day after rainy day) and species richness (significant in the fourth day after rainy day). Temperature is shown to affect species richness but is less likely to change calling activity.

Fast Discrimination of Local Earthquakes Using a Neural Approach

ABSTRACT In this article, we describe a neural network method for the fast discrimination between local earthquakes and regional and teleseismic earthquakes using seismic records from a single station. Neural networks are data‐driven nonlinear classifiers that learn from experience and can model real‐world complex relationships. For the discrimination task, we implement a two‐layer feed‐forward multilayer perceptron (MLP). MLP is a supervised technique that accomplishes the learning process using a preclassified dataset for the training phase. The dataset includes 70 teleseisms, 79 regional earthquakes, and 103 local earthquakes. The seismic events are recorded at a single station, equipped with a short‐period sensor. We parameterize the seismograms in the frequency domain, using the linear predictive coding (LPC). This technique is mostly used in audio signal processing for efficiently encoding frequency features of digital signals in a compressed form. The obtained spectral features, or LPC coefficients, are the input to the neural model. We carry out several tests by shortening from 4 to 1 s the time‐window duration used for the LPC analysis. The proposed algorithm achieves a correct classification of 98.5% and 97.7% in discriminating local versus regional and local versus teleseismic earthquakes, respectively, on a 1‐s time window. These results indicate that our discrimination algorithm can be profitably exploited in automatic analyses of seismic data that require fast responses, such as seismological monitoring systems and earthquake early warning systems.

An Error Mitigation Technique for Erasure Channels Based on a Wavelet Representation of the Speech Excitation Signal

The importance of packet-based speech transmissions has grown since it offers cheaper and efficient communications. However, frame erasures are a common hurdle in these networks and concealment techniques are necessary to ensure a minimum quality of service. In this paper, we propose a mitigation technique focused on the reconstruction of the linear prediction coding (LPC) coefficients and the excitation signal of the lost frame by using a replacement technique. These replacements are obtained by means of a minimum mean square error estimation based on a source model of the speech parameters (LPC coefficients and the excitation signal). As this approach critically relies on the quantization and representation of the excitation signal, we explore the Haar wavelet transform as a novel approach to represent the excitation signal for error mitigation. Thus, this paper describes how optimal codebook and estimates can be computed in a Haar transformed domain. As a result, the excitation signal of a frame can be decomposed in several partitions where each one is independently reconstructed. Objective and subjective tests are conducted in order to assess the quality of the concealed speech signal resulting from our proposal. Both evaluations confirm noticeable improvements over the default mitigation method included in the two tested standard codecs, adaptive multirate, and Internet low bitrate codec.

Neural Network Based Detection of Drowsiness with Eyes Open using AR Modelling

ABSTRACTThis paper proposes a method of neural network based drowsiness detection with eyes open using power spectrum analysis and auto-regressive modelling. After the electroencephalogram measurements are complete, alertness, transient, and drowsy periods are classified according to alpha spectrum changes and alpha-blocking phenomena. Although the subject's eyes are open, alpha spectrum changes such as drowsiness patterns are detected. Consequently, drowsiness detection with eyes open is applied into the proposed system. The neural network based proposed method shows that LPC (linear predictive coding) coefficients are the proper feature vectors and average classification rate is about 92%.

Singer identification using perceptual features and cepstral coefficients of an audio signal from Indian video songs

Singer identification is a difficult topic in music information retrieval because background instrumental music is included with singing voice which reduces performance of a system. One of the main disadvantages of the existing system is vocals and instrumental are separated manually and only vocals are used to build training model. The research presented in this paper automatically recognize a singer without separating instrumental and singing sounds using audio features like timbre coefficients, pitch class, mel frequency cepstral coefficients (MFCC), linear predictive coding (LPC) coefficients, and loudness of an audio signal from Indian video songs (IVS). Initially, various IVS of distinct playback singers (PS) are collected. After that, 53 audio features (12 dimensional timbre audio feature vectors, 12 pitch classes, 13 MFCC coefficients, 13 LPC coefficients, and 3 loudness feature vector of an audio signal) are extracted from each segment. Dimension of extracted audio features is reduced using principal component analysis (PCA) method. Playback singer model (PSM) is trained using multiclass classification algorithms like back propagation, AdaBoost.M2, k-nearest neighbor (KNN) algorithm, naive Bayes classifier (NBC), and Gaussian mixture model (GMM). The proposed approach is tested on various combinations of dataset and different combinations of audio feature vectors with various Indian male and female PS’s songs.

Aspects of Melisma Synthesis

The problem of restoration of the comparatively long fragments of songs called melisma was proposed to be cast in a framework of a signal synthesis. The paper investigates several possibilities to synthesize melisma employing original, approximated and modeled parameters of melisma. Several synthesis ways are explored: employing linear prediction coding (LPC) coefficients and original glottal signal, and LPC coefficients, modeled glottal signal, gain and pitch. New method for synthesis of melisma employing fragment of original glottal signal and original LPC coefficients, gain and pitch is proposed. In order to cope with the variability of speech signals simple but effective procedure based on the cross-correlation test is proposed. Ill. 4, bibl. 12 (in English; summaries in Lithuanian, English, Russian).

A system for heart sounds classification.

The future of quick and efficient disease diagnosis lays in the development of reliable non-invasive methods. As for the cardiac diseases – one of the major causes of death around the globe – a concept of an electronic stethoscope equipped with an automatic heart tone identification system appears to be the best solution. Thanks to the advancement in technology, the quality of phonocardiography signals is no longer an issue. However, appropriate algorithms for auto-diagnosis systems of heart diseases that could be capable of distinguishing most of known pathological states have not been yet developed. The main issue is non-stationary character of phonocardiography signals as well as a wide range of distinguishable pathological heart sounds. In this paper a new heart sound classification technique, which might find use in medical diagnostic systems, is presented. It is shown that by combining Linear Predictive Coding coefficients, used for future extraction, with a classifier built upon combining Support Vector Machine and Modified Cuckoo Search algorithm, an improvement in performance of the diagnostic system, in terms of accuracy, complexity and range of distinguishable heart sounds, can be made. The developed system achieved accuracy above 93% for all considered cases including simultaneous identification of twelve different heart sound classes. The respective system is compared with four different major classification methods, proving its reliability.