Cicada species recognition based on acoustic signals using dynamic time warping-graph based GraphMix, graph convolution network

Sex classification is a major benchmark of previous work in learning on the structural connectome, a naturally occurring brain graph that has proven useful for studying cognitive function and impairment. While graph neural networks (GNNs), specifically graph convolutional networks (GCNs), have gained popularity lately for their effectiveness in learning on graph data, achieving strong performance in adult sex classification tasks, their application to pediatric populations remains unexplored. We seek to characterize the capacity for GNN models to learn connectomic patterns on pediatric data through an exploration of training techniques and architectural design choices. Two datasets comprising an adult BRIGHT dataset (N = 147 Hodgkin's lymphoma survivors and N = 162 age similar controls) and a pediatric Human Connectome Project in Development (HCP-D) dataset (N = 135 healthy subjects) were utilized. Two GNN models (GCN simple and GCN residual), a deep neural network (multi-layer perceptron), and two standard machine learning models (random forest and support vector machine) were trained. Architecture exploration experiments were conducted to evaluate the impact of network depth, pooling techniques, and skip connections on the ability of GNN models to capture connectomic patterns. Models were assessed across a range of metrics including accuracy, AUC score, and adversarial robustness. GNNs outperformed other models across both populations. Notably, adult GNN models achieved 85.1% accuracy in sex classification on unseen adult participants, consistent with prior studies. The extension of the adult models to the pediatric dataset and training on the smaller pediatric dataset were sub-optimal in their performance. Using adult data to augment pediatric models, the best GNN achieved comparable accuracy across unseen pediatric (83.0%) and adult (81.3%) participants. Adversarial sensitivity experiments showed that the simple GCN remained the most robust to perturbations, followed by the multi-layer perceptron and the residual GCN. These findings underscore the potential of GNNs in advancing our understanding of sex-specific neurological development and disorders and highlight the importance of data augmentation in overcoming challenges associated with small pediatric datasets. Further, they highlight relevant tradeoffs in the design landscape of connectomic GNNs. For example, while the simpler GNN model tested exhibits marginally worse accuracy and AUC scores in comparison to the more complex residual GNN, it demonstrates a higher degree of adversarial robustness.

Significance of analytic phase of speech signals in speaker verification

LightGCAN: A lightweight graph convolutional attention network for user preference modeling and personalized recommendation

Graph Neural Networks (GNNs) have become a critical tool for learning on structured data, particularly for their ability to capture feature dependencies within multivariate datasets. This study investigates the application of Graph Convolutional Networks (GCNs) to improve classification performance on such data. We constructed a fully connected graph using cosine similarity to compare our GCN approach against standard dimensionality reduction techniques like PCA and t-SNE. In our tests, the GCN model clearly surpassed these baselines in accuracy, precision, recall, and F1-score.But the method has its own trade-offs: dense graphs are computationally costly, there are chances of overfitting on smaller datasets and the resulting embeddings may be uninterpretable. We cannot make such a claim of generality at this point because this review has only limited itself to one multivariate data set. In future endeavour we would wish to compare GCNs to more powerful classifiers, such as Random Forests, Deep Neural Networks, with greater regard to efficiency in training and resistance to noise. To summarize, this paper confirms that GNNs are an ideal option when it comes to multivariate classification, although scalability and interpretability have to be resolved in order to make it applicable in the real-life context.

The n-octanol/buffer solution distribution coefficient at pH = 7.4 (log D7.4) is an indicator of lipophilicity, and it influences a wide variety of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties and druggability of compounds. In log D7.4 prediction, graph neural networks (GNNs) can uncover subtle structure-property relationships (SPRs) by automatically extracting features from molecular graphs that facilitate the learning of SPRs, but their performances are often limited by the small size of available datasets. Herein, we present a transfer learning strategy called pretraining on computational data and then fine-tuning on experimental data (PCFE) to fully exploit the predictive potential of GNNs. PCFE works by pretraining a GNN model on 1.71 million computational log D data (low-fidelity data) and then fine-tuning it on 19,155 experimental log D7.4 data (high-fidelity data). The experiments for three GNN architectures (graph convolutional network (GCN), graph attention network (GAT), and Attentive FP) demonstrated the effectiveness of PCFE in improving GNNs for log D7.4 predictions. Moreover, the optimal PCFE-trained GNN model (cx-Attentive FP, Rtest2 = 0.909) outperformed four excellent descriptor-based models (random forest (RF), gradient boosting (GB), support vector machine (SVM), and extreme gradient boosting (XGBoost)). The robustness of the cx-Attentive FP model was also confirmed by evaluating the models with different training data sizes and dataset splitting strategies. Therefore, we developed a webserver and defined the applicability domain for this model. The webserver (http://tools.scbdd.com/chemlogd/) provides free log D7.4 prediction services. In addition, the important descriptors for log D7.4 were detected by the Shapley additive explanations (SHAP) method, and the most relevant substructures of log D7.4 were identified by the attention mechanism. Finally, the matched molecular pair analysis (MMPA) was performed to summarize the contributions of common chemical substituents to log D7.4, including a variety of hydrocarbon groups, halogen groups, heteroatoms, and polar groups. In conclusion, we believe that the cx-Attentive FP model can serve as a reliable tool to predict log D7.4 and hope that pretraining on low-fidelity data can help GNNs make accurate predictions of other endpoints in drug discovery.

Feature extraction techniques for input representation to diagnose infant diseases have received significant attention recently. Mel Frequency Cepstral Coefficients (MFCC) is one of the most popular feature extraction techniques due to its representation method being very similar to the human auditory system. The MFCC method for feature extraction depends on several important parameter settings, namely the number of filter banks, and the number of coefficients used in the final representation. These settings affects the way the features are represented, and in turn, affects the performance of the classifier for diagnosis of the disease. In this paper, the Particle Swarm Optimization (PSO) algorithm was used to optimise the parameters of the MFCC feature extraction method for classifying infants with asphyxia. The extracted MFCC features were then used to train several MLP classifiers over different initialization values. The accuracy of these classifiers was then used to guide the PSO optimization. Our results show that the optimization of MFCC computation using PSO yielded 93.9% accuracy, an improvement of 1.45% over typical MFCC parameter settings using the same classifier.

This paper analyzes the distance-based objective measures for evaluation of Text-to-Speech (TTS) systems (which is generally used objective measures). In this paper, we discuss some aspects of evaluation of speech quality of synthesized speech. Some of the limitations and issues of subjective evaluation are discussed and importance of objective measures is presented. Traditional objective measure using Dynamic Time Warping (DTW) distance is used in this work. We have used magnitude and phase-based features as well as auditory features to check effectiveness of objective measures for predicting quality of TTS voice. In particular, Mel Frequency Cepstral Coefficients (MFCC) features and phase-based Modified Group Delay-based Cepstral Coefficients (MGDCC) alone have no good correlation with subjective scores. However, feature-level fusion of MFCC and MGDCC gives better correlation than all other feature sets. With this fusion, we obtained value of correlation coefficient, −0.3 and −0.32 for Blizzard Challenge databases 2010 and 2011, respectively. The results also show significance of phase-based features for objective measures when used along with magnitude-based features. The experimental results show that distance-based measures still do not work well with Blizzard Challenge databases and need more general objective measures for measuring quality of TTS voice.

In this paper, we propose a feature set by concatenating Mel-Frequency Cepstral Coefficients (MFCC) and Spectral Centroid Magnitude Coefficients (SCMC) features for Acoustic Scene Classification (ASC) using Deep Neural Networks (DNN). MFCC features are used to hold the acoustic characteristics such as spectral envelope of an acoustic scene in each frame. It also carries the sub-band average energy as a single dimension. SCMC features are used to hold the distribution of energy in a sub-band effectively. A test is carried out on Tampere University of Technology (TUT) Acoustic Scenes 2017 Dataset. The DNN architecture for utterance level classification has been used. The proposed system’s performance on a 4-fold cross-validation setup is 80.2% and it gives 5.4% relative improvement in performance when compared to the baseline system that uses log-Mel band energies with Multi-Layer Perceptron model.

Music style classification plays a fundamental role in music recommendation, retrieval, and organization systems. Traditional classification models primarily rely on audio features or symbolic representations, such as mel-frequency cepstral coefficients or Musical Instrument Digital Interface (MIDI) sequences. However, these models often ignore the rich structural and relational information inherent in musical compositions. This study proposes a novel graph neural network (GNN)-based framework for music style classification that represents each piece of music as a graph, capturing the relationships among notes, chords, and temporal transitions. By modeling these components as interconnected nodes, the GNN is able to learn stylistic features that extend beyond local patterns, such as harmonic progressions, motif repetitions, and inter-note dependencies. To enhance model performance, the framework incorporates a dual-graph architecture combining intra-piece and inter-piece structures, enabling the GNN to generalize across compositions while retaining individual stylistic identities. Experimental results on publicly available symbolic music datasets demonstrate that the proposed model outperforms traditional convolutional neural network (CNN) and recurrent neural network (RNN)-based models in classification accuracy and robustness across multiple musical genres. These findings highlight the potential of graph-based deep learning for extracting structural patterns critical to music understanding and classification.

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 identification refers to the process of recognizing human voice using artificial intelligence techniques. Speaker identification technologies are widely applied in voice authentication, security and surveillance, electronic voice eavesdropping, and identity verification. In the speaker identification process, extracting discriminative and salient features from speaker utterances is an important task to accurately identify speakers. Various features for speaker identification have been recently proposed by researchers. Most studies on speaker identification have utilized short-time features, such as perceptual linear predictive (PLP) coefficients and Mel frequency cepstral coefficients (MFCC), due to their capability to capture the repetitive nature and efficiency of signals. Various studies have shown the effectiveness of MFCC features in correctly identifying speakers. However, the performances of these features degrade on complex speech datasets, and therefore, these features fail to accurately identify speaker characteristics. To address this problem, this study proposes a novel fusion of MFCC and time-based features (MFCCT), which combines the effectiveness of MFCC and time-domain features to improve the accuracy of text-independent speaker identification (SI) systems. The extracted MFCCT features were fed as input to a deep neural network (DNN) to construct the speaker identification model. Results showed that the proposed MFCCT features coupled with DNN outperformed existing baseline MFCC and time-domain features on the LibriSpeech dataset. In addition, DNN obtained better classification results compared with five machine learning algorithms that were recently utilized in speaker recognition. Moreover, this study evaluated the effectiveness of one-level and two-level classification methods for speaker identification. The experimental results showed that two-level classification presented better results than one-level classification. The proposed features and classification model for identifying a speaker can be widely applied to different types of speaker datasets.

Audio forensics is the application of science and scientific methods in handling digital evidence in the form of audio. In this regard, the audio supports the disclosure of various criminal cases and reveals the necessary information needed in the trial process. So far, research related to audio forensics is more on human voices that are recorded directly, either by using a voice recorder or voice recordings on smartphones, which are available on Google Play services or iOS Store. This study compares the analysis of live voices (human voices) with artificial voices on Google Voice and other artificial voices. This study implements the audio forensic analysis, which involves pitch, formant, and spectrogram as the parameters. Besides, it also analyses the data by using feature extraction using the Mel Frequency Cepstral Coefficient (MFCC) method, the Dynamic Time Warping (DTW) method, and applying the K-Nearest Neighbor (KNN) algorithm. The previously made live voice recording and artificial voice are then cut into words. Then, it tests the chunk from the voice recording. The testing of audio forensic techniques with the Praat application obtained similar words between live and artificial voices and provided 40,74% accuracy of information. While the testing by using the MFCC, DTW, KNN methods with the built systems by using Matlab, obtained similar word information between live voice and artificial voice with an accuracy of 33.33%.

Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity of building shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural networks (DCNNs) has made accurate pixel-level classification tasks possible. Yet one central issue remains: the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to their progressive down-sampling. Hence, we introduce a generic framework to overcome the issue, integrating the graph convolutional network (GCN) and deep structured feature embedding (DSFE) into an end-to-end workflow. Furthermore, instead of using a classic graph convolutional neural network, we propose a gated graph convolutional network, which enables the refinement of weak and coarse semantic predictions to generate sharp borders and fine-grained pixel-level classification. Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks. Our proposed framework with the new GCN architecture outperforms state-of-the-art approaches. Although our main task in this work is building footprint extraction, the proposed method can be generally applied to other binary or multi-label segmentation tasks.

This paper presents the automatic genre classification of Indian Tamil music and western music using timbral features and fractional Fourier transform (FrFT) based Mel frequency cepstral coefficient (MFCC) features. The classifier model for the proposed system has been built using K-nearest neighbours and support vector machine (SVM) classifiers. In this work, the performance of various features extracted from music excerpts have been analyzed, to identify the appropriate feature descriptors for the two major genres of Indian Tamil music, namely classical music (Carnatic based devotional hymn compositions) and folk music. The results have shown that the feature combination of spectral roll off, spectral flux, spectral skewness and spectral kurtosis, combined with fractional MFCC features, outperforms all other feature combinations, to yield a higher classification accuracy of 96.05 %, as compared to the accuracy of 84.21 % with conventional MFCC. It has also been observed, that the FrFT based MFCC, with timbral features and SVM, efficiently classifies the two western genres of rock and classical music, from the GTZAN dataset, with fewer features and a higher classification accuracy of 96.25 %, as compared to the classification accuracy of 80 % with conventional MFCC.

In this paper, we present an efficient parallel implementation of Mel-frequency Cepstral Coefficient (MFCC)-based feature extraction and describe the optimizations required for effective throughput on Graphics Processing Units (GPU) processors. We demonstrate that the feature extraction process in automatic speech recognition is well suited for GPUs and a substantial reduction in computation time can be obtained by performing feature extraction on these platforms. Using a single Nvidia GTX580 GPU our proposed approach is shown to be approximately 90x faster than a sequential CPU implementation, enabling feature extraction to be performed at under 0.01% real-time. This is significantly faster than prior reported results implemented on GPUs, DSPs and FPGAs. Furthermore we demonstrate that multiple MFCC features can be generated for a set of predefined Vocal-Tract-Length-Normalization (VTLN) alpha parameters with little degradation in throughput. Using the approach described in this paper MFCC features were extracted in 0.05% and 0.09% realtime, for 11 and 21 VTLN parameters respectively. (4 pages)