Bark Frequency Cepstral Coefficients Research Articles

Comparative study of respiratory sounds classification methods based on cepstral analysis and artificial neural networks

In this paper, we investigated and evaluated various machine learning-based approaches for automatically detecting wheezing sounds. We conducted a comprehensive comparison of these proposed systems, assessing their classification performance through metrics such as Sensitivity, Specificity, and Accuracy. The main approach to developing a machine learning-based system for classifying respiratory sounds involved the combination of a technique for extracting features from an unknown input sound with a classification method to determine its belonging class. The characterization techniques used in this study are based on the cepstral analysis, which was extensively employed in the automatic speech recognition field. While MFCC (Mel-Frequency Cepstral Coefficients) feature extraction methods are commonly used in respiratory sounds classification, our study introduces a novelty by employing GFCC (Gammatone-Frequency Cepstral Coefficients) and BFCC (Bark-Frequency Cepstral Coefficients) for this purpose. For the classification task, we employed two types of neural networks: the MLP (Multilayer Perceptron), a feedforward neural network, and a variant of the LSTM (Long Short-Term Memory) recurrent neural network called BiLSTM (Bidirectional LSTM). The proposed classification systems are evaluated using a database consisting of 497 wheezing segments and 915 normal respiratory segments, which are recorded from individuals diagnosticated with asthma and individuals without any respiratory issues, respectively. The highest classification performance was achieved by the BFCC-BiLSTM model, which demonstrated an exceptional accuracy rate of 99.8%.

End-to-end Multi-modal Low-resourced Speech Keywords Recognition Using Sequential Conv2D Nets

Advanced Neural Networks are widely used to recognize multi-modal conversational speech with significant improvements in accuracy automatically. Significantly, Convolutional Neural sheets have retreated cutting-edge performance in Automatic Voice Recognition (AVR) recently more appropriately in English; however, the Hindi language has not been explored and examined well on AVR systems. The work in this article has exposed a three-layered two-dimensional Sequential Convolutional neural architecture. The Sequential Conv2D is an end-to-end system that can instantaneously exploit speech signal spectral and temporal structures. The network has been trained and tested on different cepstral features such as Frequency and Time variant-Mel-Filters, Gamma-tone Filter Cepstral Quantities, Bark-Filter band Coefficients, and Spectrogram features of speech structures. The experiment was performed on two low-resourced speech command datasets; Hindi with 27,145 Speech Keywords developed by TIFR and 23,664 (1-s utterances) of English speech commands by Google TensorFlow and AIY English Speech Commands. The experimental outcome showed that the model achieves significant performance of Convolutional layers trained on spectrograms with 91.60% accuracy, compared to that achieved in other cepstral feature labels for English speech. However, the model achieved an accuracy of 69.65% for Hindi audio words in which bark-frequency cepstral coefficients features outperformed spectrogram features.

Using multi-audio feature fusion for android malware detection

Detecting mobile Android malware is still a challenge, despite the numerous research efforts. This paper presents a static detection approach that employs music information retrieval techniques. Detection based on a single, or a few, acoustic features suffer from reduction in classification accuracy, due to the use of limited ‘views’. In this paper, we propose a multi-audio feature-fusion approach, which merges audio features of heterogeneous views in order to detect Android malware. Sixty-three standard audio signal processing features and thirty-nine biologically inspired audio features were extracted, after converting the Android application package files into waveform audio files. The biologically inspired features were derived from Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), and Bark Frequency Cepstral Coefficients (BFCC). Experimental results show that the proposed audio-based malware detection features are effective and need to be further studied. Using the traditional eXtreme Gradient Boosting machine learning algorithm on the CICMaldroid 2020 dataset, the proposed approach achieved accuracy, recall, f1-score, and AUC scores of 98.96%, 99.65%, 99.30% and 98.14% respectively. An average-precision (AP) score of 100% was also achieved.

BarkDroid: Android Malware Detection Using Bark Frequency Cepstral Coefficients

Since their inaugural releases in 2007, Google’s Android and Apple’s iOS have grown to dominate the mobile OS market share. Currently, they jointly possess over 99% of the global market share with Android being the leading mobile Operating System of choice worldwide, controlling close to 70% of the market share. Mobile devices have enabled the exponential growth of a plethora of mobile applications that play key roles in enabling many use cases that are pivotal in our daily lives. On the other hand, access to a large pool of potential end users is available to both legitimate and nefarious applications, thus making mobile devices a burgeoning target of malicious applications. Current malware detection solutions rely on tedious, time-consuming, knowledge-based, and manual processes to identify malware. This paper presents BarkDroid, a novel Android malware detection technique that uses the low-level Bark Frequency Cepstral Coefficients audio features to detect malware. The results obtained outperform results obtained using other features on the same datasets. BarkDroid achieved 97.9% accuracy, 98.5% precision, an F1 score of 98.6%, and shorter execution times.

Spectral features and optimal Hierarchical attention networks for pulmonary abnormality detection from the respiratory sound signals

The most important concern in the medical field is to consider the analysis of data and perform accurate diagnosis. However, the analysis of pulmonary abnormalities may depend on the diagnostic experience and the medical skills of the physicians, and is a time-consuming practice. In order to solve such issues, an efficient Water Cycle Swarm Optimizer-based Hierarchical Attention Network (WCSO-based HAN) is developed for detecting the pulmonary abnormalities from the respiratory sound signals. However, the developed optimization technique named WCSO is devised by incorporating the Water Cycle Algorithm (WCA) with Competitive Swarm Optimizer (CSO). Here, the pre-processing is performed using the Hanning window and Spectral gating-based noise reduction method in order to remove the falsifications or noises from the signal. Thereafter, the process of feature extraction is carried out to extract the significant features, such as Bark frequency Cepstral coefficient (BFCC) and the short-term features, such as spectral flux and spectral centroid. Once the significant features are extracted, classification is performed using HAN where the training procedure of HAN is carried out using WCSO. Furthermore, the developed WCSO-based HAN obtained efficient performance using True Positive Rate (TPR), True Negative Rate (TNR) and accuracy with the values of 0.943, 0.913, and 0.923 using dataset 1, respectively. All test results are validated with the k-fold cross validation method in order to make an assessment of the generalizability of these results.

Voice Analysis and Classification System Based on Perturbation Parameters and Cepstral Presentation in Psychoacoustic Scales

The paper describes an approach to design a system for analyzing and classification of a voice signal based on perturbation parameters and cepstral representation. Two variants of the cepstral representation of the voice signal are considered: based on mel-frequency cepstral coefficients (MFCC) and based on bark-frequency cepstral coefficients (BFCC). The work used a generally accepted approach to calculating the MFCC based on the time-frequency analysis by the method of discrete Fourier transform (DFT) with summation of energy in subbands. This method approximates the frequency resolution of human hearing, but has a fixed temporal resolution. As an alternative, a variant of the cepstral representation based on the BFCC has been proposed. When calculating the BFCC, a warped DFT-modulated filter bank was used, which approximates the frequency and temporal resolution of hearing. The aim of the work was to compare the effectiveness of the use of features based on the MFCC and BFCC for the designing systems for the analysis and classification of the voice signal. The results of the experiment showed that in the case when using acoustic features based on the MFCC, it is possible to obtain a voice classification system with an average recall of 80.6 %, and in the case when using features based on the BFCC, this metric is 83.7 %. With the addition of the set of MFCC features with perturbation parameters of the voice, the average recall of the classification increased to 94.1 %, with a similar addition to the set of BFCC features, the average recall of the classification increased up to 96.7 %.

Speech stress recognition using semi-eager learning

Homo-sapiens suffer from psychogenic pain due to current day lifestyle. According to psychologists, stress is the most destructive form of psychalgia and it is a vicious companion for this species. Immoderate levels of stress may lead to the death of many individuals. Normally, the presence of stress gives rise to certain emotions which can be detected to predict stress levels of a person. This paper proposes the development of mechanized and efficient Speech Emotion Recognition (SER) for stress level analysis. The paper investigates the performance of perceptual based speech features like Revised Perceptual Linear Prediction Coefficients, Bark Frequency Cepstral Coefficients, Perceptual Linear Predictive Cepstrum, Gammatone Frequency Cepstral coefficient, Mel Frequency Cepstral Coefficient, Gammatone Wavelet Cepstral Coefficient and Inverted Mel Frequency Cepstral Coefficients on SER. The novelty of this work involves application of a SemiEager (SemiE) learning algorithm for evaluating auditory cues. SemiE offers advantages over eager and lazy based learning by reducing the computational cost. Stress level recognition being the main objective, the Speech Under Simulated and Actual Stress (SUSAS) benchmark database is used for performance analysis. A comparative analysis is presented to demonstrate the improvement in the SED performance. An overall accuracy of 90.66% recognition of stress related emotions is achieved.

Exploring the front fricative contrast in Greek: A study of acoustic variability based on cepstral coefficients

In the current study, we explore the factors underlying the well-known difficulty in acoustic classification of front nonsibilant fricatives (Maniwa, Jongman & Wade 2009, McMurray & Jongman 2011) by applying a novel classification method to the production of Greek speakers. The Greek fricative inventory [f v θ ð s z ç ʝ x ɣ] includes voiced and voiceless segments from five distinct places of articulation. Our corpus contains all of the Greek fricatives produced by 29 monolingual speakers, but our focus is on the distinction between the front nonsibilant fricatives [f v θ ð]. For comparison, we also discuss the other places of articulation where relevant. We apply a relatively novel classification method based on cepstral coefficients, previously successful in categorizing English obstruent bursts (Bunnell, Polikoff & McNicholas 2004), English vowels (Ferragne & Pellegrino 2010), Romanian fricatives (Spinu & Lilley 2016), and Russian fricatives (Spinu, Kochetov & Lilley 2018). For this study, fricative boundaries were automatically aligned using Hidden Markov Models (HMMs) and then manually checked. Six Bark-frequency cepstral coefficients (c0–c5) were extracted from 20-millisecond Hann windows. HMMs were used to divide the fricatives and adjacent vowels into three regions of internally minimized variance. A multinomial logistic regression analysis then used the mean cepstral coefficients from each region as predictors for classification by consonant identity. Our method yields highly successful classification rates, exceeding the performance of previous methods. We discuss these results in light of the differences of the phonemic distributions of fricatives between English and Greek.

Real-Time Speech Enhancement Algorithm Based on Attention LSTM

Because traditional single-channel speech enhancement algorithms are sensitive to the environment and perform poorly, a speech enhancement algorithm based on attention-gated long short-term memory (LSTM) is proposed. To simulate human auditory perceptual characteristics, the algorithm divides the frequency band according to the Bark scale. Based on these bands, bark frequency cepstral coefficients (BFCCs), their derivative features and pitch-based features are extracted. Furthermore, considering that different noises have different influence on the clean speech, the attention mechanism is applied to screen out the information less polluted by noise, which is helpful to reconstruct the clean speech. To adaptively reallocate the power ratio of the speech and noise during the construction of the ratio mask, the ideal ratio mask (IRM) with the inter-channel correlation (ICC) is adopted as the learning target. In addition, to improve the performance of the network, the algorithm introduces a multiobjective learning strategy to jointly optimize the networks by using a voice activity detector (VAD). Subjective and objective experiments show that the proposed algorithm outperforms other baseline algorithms. In real-time experiment, the proposed algorithm maintains high real-time performance and fast convergence speed.

Infant cry language analysis and recognition: an experimental approach

Recently, lots of research has been directed towards natural language processing. However, the baby &#x02BC s cry, which serves as the primary means of communication for infants, has not yet been extensively explored, because it is not a language that can be easily understood. Since cry signals carry information about a babies &#x02BC wellbeing and can be understood by experienced parents and experts to an extent, recognition and analysis of an infant &#x02BC s cry is not only possible, but also has profound medical and societal applications. In this paper, we obtain and analyze audio features of infant cry signals in time and frequency domains. Based on the related features, we can classify given cry signals to specific cry meanings for cry language recognition. Features extracted from audio feature space include linear predictive coding &#x0028 LPC &#x0029, linear predictive cepstral coefficients &#x0028 LPCC &#x0029, Bark frequency cepstral coefficients &#x0028 BFCC &#x0029, and Mel frequency cepstral coefficients &#x0028 MFCC &#x0029. Compressed sensing technique was used for classification and practical data were used to design and verify the proposed approaches. Experiments show that the proposed infant cry recognition approaches offer accurate and promising results.

Heart Sound Diagnose System with BFCC, MFCC, and Backpropagation Neural Network

human heart produce 2 different sound which are lub-dub. Abnormal heart sound would produce additional sound such as whoosing, roaring, rumbling or turbulence fliud noise between the normal heart sounds. In general, diagnosing heart abnormalities is relying on doctors’ experience by hearing heart sound through stethoscope or using ECG. This research is using heart sound recording from The Pascal Classifying Heart Sound, Dataset B[1] as learning and testing data. Diagnosing heart sound with BFCC (Bark Frequency Cepstral Coefficients), MFCC (Mel Frequency Cepstral Coefficients), Modified BFCC, and Modified MFCC as feature extraction method and Backpropagation Neural Network as learning method. Heart sound recognition from The Pascal Classifying Heart Sound, Dataset Bwith BFCC is up to 79.167%, MFCC is up to 87.5%, Modified BFCC is up to 70.83%, and Modified MFCC is up to 95.83%.

Enhanced speech emotion detection using deep neural networks

This paper focusses on investigation of the effective performance of perceptual based speech features on emotion detection. Mel frequency cepstral coefficients (MFCC’s), perceptual linear predictive cepstrum (PLPC), Mel frequency perceptual linear prediction cepstrum (MFPLPC), bark frequency cepstral coefficients (BFCC), revised perceptual linear prediction coefficient’s (RPLP) and inverted Mel frequency cepstral coefficients (IMFCC) are the perception features considered. The algorithm using these auditory cues is evaluated with deep neural networks (DNN). The novelty of the work involves analysis of the perceptual features to identify predominant features that contain significant emotional information about the speaker. The validity of the algorithm is analysed on publicly available Berlin database with seven emotions in 1-dimensional space termed categorical and 2-dimensional continuous space consisting of emotions in valence and arousal dimensions. Comparative analysis reveals that considerable improvement in the performance of emotion recognition is obtained using DNN with the identified combination of perceptual features.

Voice Verification System Based on Bark-frequency Cepstral Coefficient

Data verification systems evolve towards a more natural system using biometric media. In daily interactions, human use voice as a tool to communicate with others. Voice charactheristic is also used as a tool to identify subjects who are speaking. The problem is that background noise and signal characteristics of each person which is unique, cause speaker classification process becomes more complex. To identify the speaker, we need to understand the speech signal feature extraction process. We developed the technology to extract voice characteristics of each speaker based on spectral analysis. This research is useful for the development of biometric-based security application. At first, the voice signal will be separated by a pause signal using voice activity detection. Then the voice characteristic will be extracted using a bark-frequency cepstral coefficient. Set of cepstral will be classified according to the speaker, using artificial neural network. The accuracy reached about 82% in voice recognition process with 10 speakers, meanwhile, the highest accuracy was 93% with only 1 speaker.

Enhancement of a text-independent speaker verification system by using feature combination and parallel structure classifiers

Speaker verification (SV) systems involve mainly two individual stages: feature extraction and classification. In this paper, we explore these two modules with the aim of improving the performance of a speaker verification system under noisy conditions. On the one hand, the choice of the most appropriate acoustic features is a crucial factor for performing robust speaker verification. The acoustic parameters used in the proposed system are: Mel Frequency Cepstral Coefficients, their first and second derivatives (Deltas and Delta–Deltas), Bark Frequency Cepstral Coefficients, Perceptual Linear Predictive, and Relative Spectral Transform Perceptual Linear Predictive. In this paper, a complete comparison of different combinations of the previous features is discussed. On the other hand, the major weakness of a conventional support vector machine (SVM) classifier is the use of generic traditional kernel functions to compute the distances among data points. However, the kernel function of an SVM has great influence on its performance. In this work, we propose the combination of two SVM-based classifiers with different kernel functions: linear kernel and Gaussian radial basis function kernel with a logistic regression classifier. The combination is carried out by means of a parallel structure approach, in which different voting rules to take the final decision are considered. Results show that significant improvement in the performance of the SV system is achieved by using the combined features with the combined classifiers either with clean speech or in the presence of noise. Finally, to enhance the system more in noisy environments, the inclusion of the multiband noise removal technique as a preprocessing stage is proposed.

Comparative Analysis of LPCC, MFCC and BFCC for the Recognition of Hindi Words using Artificial Neural Networks

Most important way of communication among humans is language and primary medium used for the said is speech. The speech recognizers make use of a parametric form of a signal to obtain the most important distinguishable features of speech signal for recognition purpose. In this paper, Linear Prediction Cepstral Coefficient (LPCC), Mel Frequency Cepstral Coefficient (MFCC) and Bark frequency Cepstral coefficient (BFCC) feature extraction techniques for recognition of Hindi Isolated, Paired and Hybrid words have been studied and the corresponding recognition rates are compared. Artifical Neural Network is used as back end processor. The experimental results show that the better recognition rate is obtained for MFCC as compared to LPCC and BFCC for all the three types of words. General terms Speech Recognition, Recognition rate, Bit-wise, Zero crossing rate.

A FRAMEWORK FOR MULTILINGUAL TEXT- INDEPENDENT SPEAKER IDENTIFICATION SYSTEM

This article evaluates the performance of Extreme Learning Machine (ELM) and Gaussian Mixture Model (GMM) in the context of text independent Multi lingual speaker identification for recorded and synthesized speeches. The type and number of filters in the filter bank, number of samples in each frame of the speech signal and fusion of model scores play a vital role in speaker identification accuracy and are analyzed in this article. Extreme Learning Machine uses a single hidden layer feed forward neural network for multilingual speaker identification. The individual Gaussian components of GMM best represent speaker-dependent spectral shapes that are effective in speaker identity. Both the modeling techniques make use of Linear Predictive Residual Cepstral Coefficient (LPRCC), Mel Frequency Cepstral Coefficient (MFCC), Modified Mel Frequency Cepstral Coefficient (MMFCC) and Bark Frequency Cepstral Coefficient (BFCC) features to represent the speaker specific attributes of speech signals. Experimental results show that GMM outperforms ELM with speaker identification accuracy of 97.5% with frame size of 256 and frame shift of half of frame size and filter bank size of 40.

Investigation of distance effect on Gaussian Mixture Models in Speaker Identification

This paper investigate the effect of distance on the Gaussian Mixture Models (GMM) for text dependent speaker identification. Three stages are used for three different distances from the microphone (1m, 2m, and 3m). The set of feature extraction used here include Mel frequency cepstral coefficient (MFCC), Bark frequency cepstral coefficient (BFCC) and linear predictive cepstral coefficient (LPCC). These features are obtained from 20 speakers (10 adults and 10 children) ;all spoke five Arabic words in 5 seconds. The set of classification includes two types GMM and multilayer perceptron neural network (MLP). Total results show that MFCC has the best performance in feature extraction, and GMM has better recognition than MLP as total recognition in GMM is 93.15% and recognition in MLP is 88.06%.The results show also that the recognition rate decreases from 93.15% to 80.82% as the distance is increased from 1m to 3m.

Automated Speaker Recognition for Home Service Robots Using Genetic Algorithm and Dempster–Shafer Fusion Technique

An automated speaker recognition system for home service robots is proposed in this paper. In an uncontrolled environment, a speech classifier should be adaptive to different users and robust to noisy environments. It is usually observed that specific features and classifiers are more appropriate to parts of the problem domain than others; therefore, we propose a self-optimizing approach in which multiple feature extraction and classification techniques are simultaneously considered. The system uses a genetic algorithm to simultaneously select features and classifier, and the results from multiple classifiers are then combined using the Dempster-Shafer theory. The set of feature extractors used here includes linear-prediction coefficients, linear-prediction cepstral coefficients, mel-frequency cepstral coefficients, and bark-frequency cepstral coefficients, and the set of classifiers includes the Gaussian mixture model, support vector machines, C4.5 decision tree, k nearest neighbors, and multilayer perceptron neural network. The WEVER-R2 home service robot is used in a typical Korean home environment to collect speech signals for evaluating the performance of the proposed system for gender and age classification. Classification results show that the performance of the proposed method consistently outperforms the individual classifiers.