Linear Predictive Coding Research Articles

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.

Feature Selection for Speaker Identification and Arabic Digits Recognition.(Dept.E)

This article introduces a comparison between three different processing techniques for the selection of speech features. These features can be used for speaker recognition or speech recognition. A comparison between the performance of a system based on the linear prediction code, a system based on the cepstrum and a system based on the short time energy is introduced feature selection is very effective for recognition accuracy. This work illustrates where each of these features are more efficient for speaker recognition or for speech recognition. The results show that the short time energy in time domain is very effective for epeech recognition where its accuracy is found to be 92%. In speaker identification, the accuracy of identification for the features depending on energy in each frame is found to be 60%. It may be recommended that the features based on the capstrum given accuracy of 94% and 96% for speech recognition and speaker identification respectively. The accuracy of linear prediction code features depend on cepstrum may be recommended for speaker identifier or speech recognition. A recognition system for spoken digits are given using the above features with neural networks. The neural network has been used as a tool in this comparison.

INDIVIDUAL IDENTIFICATION SYSTEM DESIGN THROUGH VOICE USING LINEAR PREDICTIVE CODING METHOD AND K-NEAREST NEIGHBOR

Humans have a variety of characteristics that are different from one another. Characteristics possessed by humans are genuine which can be used as a differentiator between one individual and another, one of which is sound. Voice recognition is called speech recognition. In this study, it was developed as an individual voice recognition system using a combination of the Linear Predictive Coding (LPC) method of feature extraction and K-Nearest Neighbor (K-NN) classification in the speech recognition process. Testing is done by testing changes in several parameters, namely the LPC order value, the number of frames, the K value, and different distance methods. The results of the parameter combination test showed a fairly good presentation of 73.56321839% with the combination parameter or LPC 8, the number of frames 480, the value of K 5, with the distance method used by Chebychev.

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.

Recognition of Moving Tracked and Wheeled Vehicles Based on Sound Analysis and Machine Learning Algorithms

The paper presents results of a preliminary study on verification of the possibility to establish simple methods to process acquired sound signals that were generated by a vehicle in motion; to determine its characteristic features for classification as a wheeled or tracked one. The analysis covered 220 signals acquired from real experiment and pre-processed with the use of power spectral density estimation (PSD) and linear prediction coding (LPC). The signal processing methods were used to generate features for which applicability in the classification process was assessed using a statistical method. The set of features was then optimised to reduce the dimensionality of data. Results of recognition obtained with the proposed non-iterative procedures for solving linearly separable problems were compared with results from standard methods, including SVM and k-NN. The developed features as well as selected methods of classification were proposed with respect to the possibility to implement them in low computational power computers for embedded applications.

Detection of Bryde's whale short pulse calls using time domain features with hidden Markov models

Passive acoustic monitoring (PAM) is generally usedto extract acoustic signals produced by cetaceans. However, the large data volume from the PAM process is better analyzed using an automated technique such as the hidden Markovmodels (HMM). In this paper, the HMM is used as a detection and classification technique due to its robustness and low time complexity. Nonetheless, certain parameters, such as the choice of features to be extracted from the signal, the frame duration, and the number of states affect the performance of the model. Theresults show that HMM exhibits best performances as the number of states increases with short frame duration. However, increasing the number of states creates more computational complexity in the model. The inshore Bryde's whales produce short pulse calls with distinct signal features, which are observable in the time-domain. Hence, a time-domain feature vector is utilized to reduce the complexity of the HMM. Simulation results also show that average power as a time-domain feature vector provides the best performance compared to other feature vectors for detecting the short pulse call of inshore Bryde's whales based on the HMM technique. More so, the extracted features such as the average power, mean, and zero-crossing rate, are combined to form a single 3-dimensional vector (PaMZ). The PaMZ-HMM shows improved performance and reduced complexity over existing feature extraction techniques such as Mel-scale frequency cepstral coefficients (MFCC) and linear predictive coding (LPC). Thus, making the PaMZ-HMM suitable for real-time detection.

Clustering of Experimental Seismo-Acoustic Events Using Self-Organizing Map (SOM)

The analogue experiments that produce seismo-acoustic events are relevant for understanding the degassing processes of a volcanic system. The aim of this work is to design an unsupervised neural network for clustering experimental seismo-acoustic events in order to investigate the possible cause-effect relationships between the obtained signals and the processes. We focused on two tasks: 1) identify an appropriate strategy for parameterizing experimental seismo-acoustic events recorded during analogue experiments devoted to the study of degassing behavior at basaltic volcanoes; 2) define the set up of the selected neural network, the Self-Organizing Map (SOM), suitable for clustering the features extracted from the experimental events. The seismo-acoustic events were generated using an ad hoc experimental setup under different physical conditions of the analogue magma (variable viscosity), injected gas flux (variable flux velocity) and conduit surface (variable surface roughness). We tested the SOMs ability to group the experimental seismo-acoustic events generated under controlled conditions and conduit geometry of the analogue volcanic system. We used 616 seismo-acoustic events characterized by different analogue magma viscosity (10, 100, 1000 Pa s), gas flux (5, 10, 30, 60, 90, 120, 150, 180 × 10−3 l/s) and conduit roughness (i.e. different fractal dimension corresponding to 2, 2.18, 2.99). We parameterized the seismo-acoustic events in the frequency domain by applying the Linear Predictive Coding to both accelerometric and acoustic signals generated by the dynamics of various degassing regimes, and in the time domain, applying a waveform function. Then we applied the SOM algorithm to cluster the feature vectors extracted from the seismo-acoustic data through the parameterization phase, and identified four main clusters. The results were consistent with the experimental findings on the role of viscosity, flux velocity and conduit roughness on the degassing regime. The neural network is capable to separate events generated under different experimental conditions. This suggests that the SOM is appropriate for clustering natural events such as the seismo-acoustic transients accompanying Strombolian explosions and that the adopted parameterization strategy may be suitable to extract the significant features of the seismo-acoustic (and/or infrasound) signals linked to the physical conditions of the volcanic system.

Sistem Pembelajaran Hukum Baca Al-Qur’an Menggunakan Algoritma LPC dan KNN

Seorang muslim harus dapat membaca ayat-ayat Al-Quran dengan baik sesuai yang diajarkan oleh Rasulullah saw. Membaca Al-Quran sesuai ilmu tajwid hukumnya wajib bagi setiap orang muslim, apabila seseorang membaca Al-Quran dengan tidak memakai tajwid, hukumnya berdosa. Pengembangan Aplikasi Pembelajaran Tajwid Al-Qur’an ini bertujuan untuk membantu seorang muslim agar pandai membaca al-Qur’an yang baik dan benar. Surat yang di pakai dalam aplikasi ini adalah surat Al-Fatihah. Aplikasi Pembelajaran Tajwid Al-Qur’an menggunakan Bahasa pemrograman Python dengan metode Linear Predictive Coding (LPC) sebagai ekstraksi ciri suara dan metode K-Nearest Neigbor sebagai pencocokan denan data latih. Untuk pengujian pengucapan ayat ke-1 didapatkan akurasi data sebesar 83.3%, ayat ke-2 sebesar 86.7%, ayat ke-3 sebesar 85%, ayat ke-4 sebesar 80%, ayat ke-5 sebesar 88.3%, ayat ke-6 sebesar 93.3%

Mel Scale-Based Linear Prediction Approach to Reduce the Prediction Filter Order in CELP Paradigm

This paper proposes a novel method to reduce the order of prediction filter from 10 to 7 in Code Excited Linear Prediction (CELP) coding framework by the inclusion of psychoacoustic Mel scale into Linear Predictive Coding (Mel-LPC). Efficient quantization methods using 2-split Vector Quantization (VQ) for Mel-LPC obtained a reduction of 4 bits/frame and resulted in a total bit gain of 200 bps. A weighting scheme for the Euclidean distance measure gave a reduction of 6 bits/frame that adds up to a total bit gain of 300 bps. A lower Mel-LPC order of 3 has been employed for unvoiced frames by using the perceptual quality as selection criteria and an efficient VQ method using 5 bits is developed which brought down the average bit requirement to 11.5 bits/frame. To incorporate this into Mel-LPC-based CELP encoding scheme, a neural network-based voiced-unvoiced classification algorithm using 5 derived features as input has been constructed and this selection of filter order based on signal statistics provides the benefit of bit reduction by 625 and 325 bps, respectively, for 10th order LPC and 7th order Mel-LPC. In addition to all, the incorporation of Mel-LPC gives a better performance in the estimation of formants.

Power-Weighted LPC Formant Estimation

A power-weighted formant frequency estimation procedure based on Linear Predictive Coding (LPC) is presented. It works by pre-emphasizing the dominant spectral components of an input signal, which allows a subsequent estimation step to extract formant frequencies with greater accuracy. The accuracy of traditional LPC formant estimation is improved by this new power-weighted formant estimator for different classes of synthetic signals and for speech. Power-weighted LPC significantly and reliably outperforms LPC and variants of LPC at the task of formant estimation using the VTR formants dataset, a database consisting of the Vocal Tract Resonance (VTR) frequency trajectories obtained by human experts for the first three formant frequencies. This performance gain is evident over a range of filter orders.

Speech enhancement and encoding by combining SS-VAD and LPC

In this paper, the encoding of noisy and enhanced speech data is demonstrated. To encode and enhance the speech data under an uncontrolled environment, the linear predictive coding (LPC) and spectral subtraction with voice activity detection (SS-VAD) methods are studied individually. The noisy speech data is obtained by considering the amalgamation of the clean speech signal and noise model and it is encoded using the LPC technique. The LPC uses a lossy compression procedure to encode the speech data which converts the data rate from 64 to 2.4 Kbps. Due to reverberations and degradations in noisy speech data, the quality of encoded noisy speech data is very less. Therefore, an algorithm is proposed to enhance and encode the speech data by combining SS-VAD and LPC under degraded conditions. In the first step, the encoding of noisy speech data is done using LPC and its performance is evaluated using signal-to-ratio. The noisy speech data is given as input to the SS-VAD algorithm and the output of SS-VAD is given as input to the LPC encoder is followed in the second step. In the LPC encoder, the coefficients are extracted from the input speech data to design all-pole filters. The cross correlation process is also done for differentiating the voiced and unvoiced samples at the analysis step. The pitch information and extracted coefficients are used in the synthesis step. The experiments are conducted for different types of noisy speech data which are degraded by musical noise, F16 noise, factory noise, and car noise. The experimental results show that there is a significant improvement in the quality of enhanced encoded speech data obtained by the proposed method compared to encoded noisy speech data. The schematic representation of outputs of LPC and proposed combined SS-VAD and LPC waveforms are also given in this work.

General Steganalysis Method of Compressed Speech Under Different Standards

Analysis-by-synthesis linear predictive coding (AbS-LPC) is widely used in a variety of low-bit-rate speech codecs. Most of the current steganalysis methods for AbS-LPC low-bit-rate compressed speech steganography are specifically designed for a specific coding standard or category of steganography methods, and thus lack generalization capability. In this paper, a general steganalysis method for detecting steganographies in low-bit-rate compressed speech under different standards is proposed. First, the code-element matrices corresponding to different coding standards are concatenated to obtain a synthetic code-element matrix, which will be mapped into an intermediate feature representation by utilizing the pre-trained dictionaries. Then, bidirectional long short-term memory is employed to capture long-term contextual correlations. Finally, a code-element affinity attention mechanism is used to capture the global inter-frame context, and a full connection structure is used to generate the prediction result. Experimental results show that the proposed method is effective and better than the comparison methods for detecting steganographies in cross-standard low-bit-rate compressed speech.

Using Formants to Extract Short Vowels from Arabic Words with (Consonant Vowel)<sup>3</sup> Structure

Arabic texts suffer from missing short vowels. Arabic Speech Recognition is not as good as English speech recognition due to the short vowels not being recognized. And the Arabic language is unlike the English language in characteristics such as the number of vowels. English has more than 24 vowels that are close to each other in pronunciation. The Arabic language only has three short vowels that are far from each other in utter and measurement, by elongating those short vowels, long vowels arose. Researchers said that the vowels could be recognized using formants. The formants’ measurements of Arabic vowels are far from each other too, so it is possible to recognize them so that Arabic Speech recognition can give more accurate results. The paper applies this idea to the corpus Phonemes of Arabic. It uses the Euclidian distance method to measure the distances between formant values to recognize Arabic from words with a CV3 structure, the Linear Predictive Coding method and MATLAB to develop the programs that will extract the formants and calculate the means of the short vowels by using the corpus to identify the short vowels within words in the corpus. The results showed that if highly qualified readers were chosen to read the Arabic text, then higher rates of recognition of the short vowels involved in words will be achieved. This paper revealed that some of the characteristics of a language can be utilized for vowel recognition or to enhance the existing methods for speech recognition.

HMM-based phoneme speech recognition system for the control and command of industrial robots

In recent years, the integration of human-robot interaction with speech recognition has gained a lot of pace in the manufacturing industries. Conventional methods to control the robots include semi-autonomous, fully-autonomous, and wired methods. Operating through a teaching pendant or a joystick is easy to implement but is not effective when the robot is deployed to perform complex repetitive tasks. Speech and touch are natural ways of communicating for humans and speech recognition, being the best option, is a heavily researched technology. In this study, we aim at developing a stable and robust speech recognition system to allow humans to communicate with machines (roboticarm) in a seamless manner. This paper investigates the potential of the linear predictive coding technique to develop a stable and robust HMM-based phoneme speech recognition system for applications in robotics. Our system is divided into three segments: a microphone array, a voice module, and a robotic arm with three degrees of freedom (DOF). To validate our approach, we performed experiments with simple and complex sentences for various robotic activities such as manipulating a cube and pick and place tasks. Moreover, we also analyzed the test results to rectify problems including accuracy and recognition score.

Infant Crying Classification by Using Genetic Algorithm and Artificial Neural Network

Cry as the only way of communication of babies with the surrounding environment can be happened for many reasons such as diseases, suffocation, hunger, cold and heat feeling, pain and etc. So, the analysis and detection of its source are very important for parents and health care providers. So the present study designed with the aim to test the performance of neural networks in the identification of the source of babies crying. The present study combines the genetic algorithm and artificial neural network with (Linear Predictive Coding) LPC and MFCC (Mel-Frequency Cepstral Coefficients) to classify the babies crying. The results of this study indicate the superiority of the proposed method compared to the other previous methods. This method could achieve the highest accuracy in the classification of newborns crying among the previous studies. Developing methods for classification audio signal analysis are promising and can be effectively applied in different areas such as babies crying.

Variation of Formant Frequency with Nepalese Vowels

The regions of speech spectrum in which the frequency corresponds to relatively large amplitude are known as formants. For any vocalic sounds, number of formants may occur in the frequency range 0 to 4000 Hz. The formant frequencies of speech sounds are directly depending up on the shape and size of vocal tract. The aim of study was to study the variation of formant frequency with Nepalese vowels. Ten Nepalese vowels word in initial position /VC/ as spoken three times by 10 male and 10 female Nepali speakers were recorded in system in the free field of partially acoustically treated room. PRRAT software is used to digitize and analyze the data. Linear predictive coding (LPC) spectra were obtained for each of vowels and formant frequencies were measured. By plotting curve between formant frequencies and vowels, explain their variation.

Comparison of Khasi speech representations with different spectral features and hidden Markov states

In this paper, we present a comparison of the Khasi speech representations with four different spectral features and novel extension towards the development of Khasi speech corpora. These four features include linear predictive coding (LPC), linear prediction cepstrum coefficient (LPCC), perceptual linear prediction (PLP), and Mel frequency cepstral coefficient (MFCC). The 10-h speech data was used for training and 3-h data for testing. For each spectral feature, different hidden Markov model (HMM) based recognizers with variations in HMM states and different Gaussian mixture models (GMMs) were built. The performance was evaluated by using the word error rate (WER). The experimental results showed that MFCC provides a better representation for Khasi speech compared with the other three spectral features.

Kurdish Spoken Letter Recognition based on k-NN and SVM Model

Automatic recognition of spoken letters is one of the most challenging tasks in the area of speech recognition system. In this paper, different machine learning approaches are used to classify the Kurdish alphabets such as SVM and k-NN where both approaches are fed by two different features, Linear Predictive Coding (LPC) and Mel Frequency Cepstral Coefficients (MFCCs). Moreover, the features are combined together to learn the classifiers. The experiments are evaluated on the dataset that are collected by the authors as there as not standard Kurdish dataset. The dataset consists of 2720 samples as a total. The results show that the MFCC features outperforms the LPC features as the MFCCs have more relative information of vocal track. Furthermore, fusion of the features (MFCC and LPC) is not capable to improve the classification rate significantly.

Qualitative Analysis of PLP in LSTM for Bangla Speech Recognition

The performance of various acoustic feature extraction methods has been compared in this work using Long Short-Term Memory (LSTM) neural network in a Bangla speech recognition system. The acoustic features are a series of vectors that represents the speech signals. They can be classified in either words or sub word units such as phonemes. In this work, at first linear predictive coding (LPC) is used as acoustic vector extraction technique. LPC has been chosen due to its widespread popularity. Then other vector extraction techniques like Mel frequency cepstral coefficients (MFCC) and perceptual linear prediction (PLP) have also been used. These two methods closely resemble the human auditory system. These feature vectors are then trained using the LSTM neural network. Then the obtained models of different phonemes are compared with different statistical tools namely Bhattacharyya Distance and Mahalanobis Distance to investigate the nature of those acoustic features.