Mel Spectrogram Research Articles

Exploring vocal biomarkers as non-invasive fine-tuning assays of cardiovascular health: heart failure model

Abstract Background Mobile health (mHealth) technologies offer a promising avenue for non-invasive heart failure monitoring through vocal biomarkers. The relationship between feature changes in anonymous and standardized voice recordings of heart failure patients and the NYHA scores of the same patients is assessed, aiming to identify vocal biomarkers as delicate indicators of chronic noncommunicable disease progression and/ or fluctuation. Methods In a cardiology outpatient setting, 55 chronic heart failure patients provided voice recordings via a mobile app, performing specific vocal tasks prospectively. We analyzed waveforms visually via Mel spectrograms and extracting features by audio processing, focusing on chroma centroids and tonnetz measurements across 147 clinical and laboratory parameters (Mean NYHA: 2.62, SD: 0.56). Applying Ordinary Least Squares (OLS) test, we assessed the relevance of spectral bandwidth mean (0.04), spectral bandwidth std (0.00), spectral roll-off std (0.011) between NYHA scores, given each p-score < 0.05. Results 147 voice recordings taken from 55 patients were analyzed to examine whether there were any correlations between changes in the voice recordings and NYHA scores. OLS test underscored the significance of spectral bandwidth mean (0.04), spectral bandwidth std (0.00), spectral roll-off std (0.011) between NYHA scores with p-value < 0.05. These findings show the potential role of multiple vocal features in reflecting heart failure progression and/or fluctuation. Analysis based on the clinical status progression from NYHA 2 to NYHA 3 over time showed notable changes in chroma centroids (mean = 0.006, std = 0.174, skew = 0.179, kurtosis = 0.205) and tonnetz (mean = 0.023, std = 0.131, skew = 0.023, kurtosis = 4.247). Conclusion This investigation highlights vocal biomarkers' potential in heart failure management, offering insights into non-invasive monitoring techniques and shows the importance of standardised recording procedures and patient engagement for data integrity. Future directions include quantifying vocal changes' correlation with clinical status and integrating additional parameters (e.g., edema, weight) to enhance predictive models for personalised care.Vocal features according to NYHA scores

Programmatic Pitch

Diffusion models have firmly established their excellence for image generation tasks, as evidenced by the success of renowned models such as DALL-E, Midjourney, and Stable Diffusion. This advanced development of diffusion models for visual content raises an interesting question: can diffusion models be adapted for audio generation tasks? In this study, we introduce a novel diffusion model architecture designed to generate mel spectrograms, visual representations of sound which can subsequently be converted into audible music. Given the exceptional capability of diffusion models to produce high- quality images, their application to mel spectrogram generation is particularly promising. Our proposed diffusion model deviates minimally from the conventional architectures employed for visual content, making this research especially useful for examining the potential for cross-domain application between image and audio generation. The proposed model has been trained on a dataset consisting of over 186 hours of Lofi audio, offering the model diverse samples for generalized learning. However, a combination of research limitations led to subpar results, paving the way for further studies to build on this one.

MelCochleaGram-DeepCNN: Sequentially Fused Spectrogram and the DeepCNN Classifiers-based Audio Spoof Detection System

Automatic Speaker Verification (ASV) systems are crucial in various fields, enabling speaker identification for authentication, fraud detection, and forensic applications. While the simplicity and effectiveness of speech biometrics are driving the demand for ASV systems, their increasing popularity raises concerns about vulnerability to speech attacks. To enhance the security of these systems, the work in this paper proposes a spectrogram-based solution that leverages the robustness of spectrograms in audio analysis and feature extraction. The proposed model consists of two main components: frontend and backend. In the frontend, it introduces a novel spectrogram MelCochleaGram (MCG) by fusing Mel Spectrogram and Cochleagram, sequentially. For the backend implementation, pre-trained deep learning models, including ResNet50, ResNet50V2, and InceptionV3, are employed using the Keras framework. These models are individually paired with MCG to detect deepfake and replay attacks. To validate the effectiveness of the proposed system, thorough experimentation is conducted on two datasets: the DEepfake CROss-lingual (DECRO) evaluation dataset and the Voice Spoofing Detection Corpus (VSDC). The proposed combination of MCG with ResNet50 has achieved an Equal Error Rate (EER) of 0.2%, and 1.2% for deepfake detection over DECRO English and Chinese datasets, respectively. Also, for replay attack detection, the proposed combination has produced an EER of 1.4%.

Coal-gangue sound recognition using hybrid multi-branch CNN based on attention mechanism fusion in noisy environments

The coal-gangue recognition technology plays an important role in the intelligent realization of fully mechanized caving face and the improvement of coal quality. Although great progress has been made for the coal-gangue recognition in recent years, most of them have not taken into account the impact of the complex environment of top coal caving on recognition performance. Herein, a hybrid multi-branch convolutional neural network (HMBCNN) is proposed for coal-gangue recognition, which based on improved Mel Frequency Cepstral Coefficient (MFCC) as well as Mel spectrogram, and attention mechanism. Firstly, the MFCC and its smooth feature matrix are input into each branch of one-dimensional multi-branch convolutional neural network, and the spliced features are extracted adaptively through multi-head attention mechanism. Secondly, the Mel spectrogram and its first-order derivative are input into each branch of the two-dimensional multi-branch convolutional neural network respectively, and the effective time-frequency information is paid attention to through the soft attention mechanism. Finally, at the decision-making level, the two networks are fused to establish a model for feature fusion and classification, obtaining optimal fusion strategies for different features and networks. A database of sound pressure signals under different signal-to-noise ratios and equipment operations is constructed based on a large amount of data collected in the laboratory and on-site. Comparative experiments and discussions are conducted on this database with advanced algorithms and different neural network structures. The results show that the proposed method achieves higher recognition accuracy and better robustness in noisy environments.

Acoustic insights into the corn extrusion process for enhanced quality control

In industrial extrusion processes, a solid material is pressed through a die to obtain products of the desired shape and dimension. Fluctuations in the process parameters have a significant impact on the product quality. In food extrusion, the expansion noise at the die can serve as an indicator of the stability of the process. This study employs microphones to characterize the corn extrusion process, focusing on correlating acoustic emissions with predefined process parameters such as feed intake and water content. Experimental data from laboratory and industrial settings reveal distinct domain shifts, yet consistent findings confirm the distinguishability of various extrusion process parameters by analyzing acoustic emissions. Employing machine learning models, including support vector machines and convolutional neural networks, in conjunction with audio features such as log Mel spectrograms, yields promising accuracies above 90\% in discriminating between standard and non-standard process parameters. The proposed acoustic quality control approach has the potential to enhance the stability of extrusion processes and contributes to the development of automated monitoring systems in the field of food extrusion. This ensures consistent quality and reduced waste, ultimately leading to significant cost savings in production.

Impact of Sliding Window Variation and Neuronal Time Constants on Acoustic Anomaly Detection Using Recurrent Spiking Neural Networks in Automotive Environment

Acoustic perception of the automotive environment has the potential to advance driving potentials with enhanced safety. The challenge arises when these acoustic perception systems need to perform under resource and power constraints on edge devices. Neuromorphic computing has introduced spiking neural networks in the context of ultra-low power sensory edge devices. Spiking architectures leverage biological plausibility to achieve computational capabilities, accurate performance, and great compatibility with neuromorphic hardware. In this work, we explore the depths of spiking neurons and feature components with the acoustic scene analysis task for siren sounds. This research work aims to address the qualitative analysis of sliding windows’ variation on the feature extraction front of the preprocessing pipeline. Optimization of the parameters to exploit the feature extraction stage facilitates the advancement of the performance of the acoustics anomaly detection task. We exploit the parameters for mel spectrogram features and FFT calculations, prone to be suitable for computations in hardware. We conduct experiments with different window sizes and the overlapping ratio within the windows. We present our results for performance measures like accuracy and onset latency to provide an insight on the choice of optimal window. The non-trivial motivation of this research is to understand the effect of encoding behavior of spiking neurons with different windows. We further investigate the heterogeneous nature of membrane and synaptic time constants and their impact on the accuracy of anomaly detection. On a large scale audio dataset comprising of siren sounds and road traffic noises, we obtain accurate predictions of siren sounds using a recurrent spiking neural network. The baseline dataset comprising siren and noise sequences is enriched with a bird dataset to evaluate the model with unseen samples.

A Multi-Feature Fusion Approach for Dialect Identification using 1D CNN

The phonological variety of Kurdish, a language with several dialects, poses a distinct problem in automatically identifying dialects. This study examines and evaluates several sound criteria for identifying Kurdish dialects: Badini, Hawrami, and Sorani. We deployed a dataset including 6,000 samples and utilized a mix of 1D convolutional neural networks (CNN) and fully connected layers to conduct the identification job. Our study aimed to assess the efficacy of different sound characteristics in accurately identifying dialects. We employed the Mel-frequency Cepstral Coefficients (MFCC) and other features such as the Mel spectrogram, spectral contrast, and polynomial features to extract the sound characteristics. We conducted training and testing of our models utilizing both individual characteristics and a composite of all features. Our analysis revealed that the identification task achieved excellent accuracy rates, suggesting a promising potential for success. We achieved 95.75% accuracy using MFCC combined with a Mel spectrogram. The accuracy improved by including contrast in the MFCC feature extraction process to 91.42%. Similarly, using poly_features resulted in an accuracy of 90.83%. Remarkably, accuracy reached a maximum of 96.5% when all the attributes were combined.

Baby Cry Sound Detection: A Comparison of Mel Spectrogram Image on Convolutional Neural Network Models

Baby cries contain patterns that indicate their needs, such as pain, hunger, discomfort, colic, or fatigue. This study explores the use of Convolutional Neural Network (CNN) architectures for classifying baby cries using Mel Spectrogram images. The primary objective of this research is to compare the effectiveness of various CNN architectures such as VGG-16, VGG-19, LeNet-5, AlexNet, ResNet-50, and ResNet-152 in detecting baby needs based on their cries. The datasets used include the Donate-a-Cry Corpus and Dunstan Baby Language. The results show that AlexNet achieved the best performance with an accuracy of 84.78% on the Donate-a-Cry Corpus dataset and 72.73% on the Dunstan Baby Language dataset. Other models like ResNet-50 and LeNet-5 also demonstrated good performance although their computational efficiency varied, while VGG-16 and VGG-19 exhibited lower performance. This research provides significant contributions to the understanding and application of CNN models for baby cry classification. Practical implications include the development of baby cry detection applications that can assist parents and healthcare provide.

Speech synthesis from three-axis accelerometer signals using conformer-based deep neural network

Silent speech interfaces (SSIs) have emerged as innovative non-acoustic communication methods, and our previous study demonstrated the significant potential of three-axis accelerometer-based SSIs to identify silently spoken words with high classification accuracy. The developed accelerometer-based SSI with only four accelerometers and a small training dataset outperformed a conventional surface electromyography (sEMG)-based SSI. In this study, motivated by the promising initial results, we investigated the feasibility of synthesizing spoken speech from three-axis accelerometer signals. This exploration aimed to assess the potential of accelerometer-based SSIs for practical silent communication applications. Nineteen healthy individuals participated in our experiments. Five accelerometers were attached to the face to acquire speech-related facial movements while the participants read 270 Korean sentences aloud. For the speech synthesis, we used a convolution-augmented Transformer (Conformer)-based deep neural network model to convert the accelerometer signals into a Mel spectrogram, from which an audio waveform was synthesized using HiFi-GAN. To evaluate the quality of the generated Mel spectrograms, ten-fold cross-validation was performed, and the Mel cepstral distortion (MCD) was chosen as the evaluation metric. As a result, an average MCD of 5.03 ± 0.65 was achieved using four optimized accelerometers based on our previous study. Furthermore, the quality of generated Mel spectrograms was significantly enhanced by adding one more accelerometer attached under the chin, achieving an average MCD of 4.86 ± 0.65 (p < 0.001, Wilcoxon signed-rank test). Although an objective comparison is difficult, these results surpass those obtained using conventional SSIs based on sEMG, electromagnetic articulography, and electropalatography with the fewest sensors and a similar or smaller number of sentences to train the model. Our proposed approach will contribute to the widespread adoption of accelerometer-based SSIs, leveraging the advantages of accelerometers like low power consumption, invulnerability to physiological artifacts, and high portability.

Hybrid CNN-BiLSTM architecture with multiple attention mechanisms to enhance speech emotion recognition

During recent years, the concept of attention in deep learning has been increasingly used to boost the performance of Speech Emotion Recognition (SER) models. However, these models for SER exhibit shortcomings in jointly emphasizing the time-frequency and dynamic sequential variations, often under-utilizing the rich contextual emotion-related information. We propose a hybrid deep learning model for SER using Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory Networks (BiLSTM) with multiple attention mechanisms. Our model utilizes features from the speech waveform viz. Mel spectrograms and Mel Frequency Cepstral Coefficients (MFCC), along with their time derivatives as input to the CNN and BiLSTM modules, respectively. A Time–Frequency Attention (TFA) mechanism, optimally incorporated into CNN, helps to selectively focus on emotion-related energy–time–frequency variations in Mel spectrograms. Attention-based BiLSTM uses MFCC and its time derivatives to identify the positional information of emotion for addressing the dynamic sequential variations. Finally, we fuse the attention-learned features from the CNN and BiLSTM modules and feed them to a Deep Neural Network (DNN) for SER. The experiments were carried out using three different datasets: Emo-DB and IEMOCAP, which are public datasets, and Amritaemo_Arabic; a private dataset. The hybrid model exhibited superior performance on both the public and private datasets, generating an average SER accuracy of 94.62%, 67.85%, and 95.80% with Emo-DB, IEMOCAP, and Amritaemo_Arabic datasets, respectively, effectively outperforming several state-of-the-art models.

Recognition of Western Black-Crested Gibbon Call Signatures Based on SA_DenseNet-LSTM-Attention Network

As part of the ecosystem, the western black-crested gibbon (Nomascus concolor) is important for ecological sustainability. Calls are an important means of communication for gibbons, so accurately recognizing and categorizing gibbon calls is important for their population monitoring and conservation. Since a large amount of sound data will be generated in the process of acoustic monitoring, it will take a lot of time to recognize the gibbon calls manually, so this paper proposes a western black-crested gibbon call recognition network based on SA_DenseNet-LSTM-Attention. First, to address the lack of datasets, this paper explores 10 different data extension methods to process all the datasets, and then converts all the sound data into Mel spectrograms for model input. After the test, it is concluded that WaveGAN audio data augmentation method obtains the highest accuracy in improving the classification accuracy of all models in the paper. Then, the method of fusion of DenseNet-extracted features and LSTM-extracted temporal features using PCA principal component analysis is proposed to address the problem of the low accuracy of call recognition, and finally, the SA_DenseNet-LSTM-Attention western black-crested gibbon call recognition network proposed in this paper is used for recognition training. In order to verify the effectiveness of the feature fusion method proposed in this paper, we classified 13 different types of sounds and compared several different networks, and finally, the accuracy of the VGG16 model improved by 2.0%, the accuracy of the Xception model improved by 1.8%, the accuracy of the MobileNet model improved by 2.5%, and the accuracy of the DenseNet network model improved by 2.3%. Compared to other classical chirp recognition networks, our proposed network obtained the highest accuracy of 98.2%, and the convergence of our model is better than all the compared models. Our experiments have demonstrated that the deep learning-based call recognition method can provide better technical support for monitoring western black-crested gibbon populations.

A Hybrid Parallel Computing Architecture Based on CNN and Transformer for Music Genre Classification

Music genre classification (MGC) is the basis for the efficient organization, retrieval, and recommendation of music resources, so it has important research value. Convolutional neural networks (CNNs) have been widely used in MGC and achieved excellent results. However, CNNs cannot model global features well due to the influence of the local receptive field; these global features are crucial for classifying music signals with temporal properties. Transformers can capture long-range dependencies within an image thanks to adopting the self-attention mechanism. Nevertheless, there are still performance and computational cost gaps between Transformers and existing CNNs. In this paper, we propose a hybrid architecture (CNN-TE) based on CNN and Transformer encoder for MGC. Specifically, we convert the audio signals into mel spectrograms and feed them into a hybrid model for training. Our model employs a CNN to initially capture low-level and localized features from the spectrogram. Subsequently, these features are processed by a Transformer encoder, which models them globally to extract high-level and abstract semantic information. This refined information is then classified using a multi-layer perceptron. Our experiments demonstrate that this approach surpasses many existing CNN architectures when tested on the GTZAN and FMA datasets. Notably, it achieves these results with fewer parameters and a faster inference speed.

A Semi-Supervised Lie Detection Algorithm Based on Integrating Multiple Speech Emotional Features

When people tell lies, they often exhibit tension and emotional fluctuations, reflecting a complex psychological state. However, the scarcity of labeled data in datasets and the complexity of deception information pose significant challenges in extracting effective lie features, which severely restrict the accuracy of lie detection systems. To address this, this paper proposes a semi-supervised lie detection algorithm based on integrating multiple speech emotional features. Firstly, Long Short-Term Memory (LSTM) and Auto Encoder (AE) network process log Mel spectrogram features and acoustic statistical features, respectively, to capture the contextual links between similar features. Secondly, the joint attention model is used to learn the complementary relationship among different features to obtain feature representations with richer details. Lastly, the model combines the unsupervised loss Local Maximum Mean Discrepancy (LMMD) and supervised loss Jefferys multi-loss optimization to enhance the classification performance. Experimental results show that the algorithm proposed in this paper achieves better performance.

Deep transfer learning-based bird species classification using mel spectrogram images.

The classification of bird species is of significant importance in the field of ornithology, as it plays an important role in assessing and monitoring environmental dynamics, including habitat modifications, migratory behaviors, levels of pollution, and disease occurrences. Traditional methods of bird classification, such as visual identification, were time-intensive and required a high level of expertise. However, audio-based bird species classification is a promising approach that can be used to automate bird species identification. This study aims to establish an audio-based bird species classification system for 264 Eastern African bird species employing modified deep transfer learning. In particular, the pre-trained EfficientNet technique was utilized for the investigation. The study adapts the fine-tune model to learn the pertinent patterns from mel spectrogram images specific to this bird species classification task. The fine-tuned EfficientNet model combined with a type of Recurrent Neural Networks (RNNs) namely Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). RNNs are employed to capture the temporal dependencies in audio signals, thereby enhancing bird species classification accuracy. The dataset utilized in this work contains nearly 17,000 bird sound recordings across a diverse range of species. The experiment was conducted with several combinations of EfficientNet and RNNs, and EfficientNet-B7 with GRU surpasses other experimental models with an accuracy of 84.03% and a macro-average precision score of 0.8342.

Using Transfer Learning to Realize Low Resource Dungan Language Speech Synthesis

This article presents a transfer-learning-based method to improve the synthesized speech quality of the low-resource Dungan language. This improvement is accomplished by fine-tuning a pre-trained Mandarin acoustic model to a Dungan language acoustic model using a limited Dungan corpus within the Tacotron2+WaveRNN framework. Our method begins with developing a transformer-based Dungan text analyzer capable of generating unit sequences with embedded prosodic information from Dungan sentences. These unit sequences, along with the speech features, provide &lt;unit sequence with prosodic labels, Mel spectrograms&gt; pairs as the input of Tacotron2 to train the acoustic model. Concurrently, we pre-trained a Tacotron2-based Mandarin acoustic model using a large-scale Mandarin corpus. The model is then fine-tuned with a small-scale Dungan speech corpus to derive a Dungan acoustic model that autonomously learns the alignment and mapping of the units to the spectrograms. The resulting spectrograms are converted into waveforms via the WaveRNN vocoder, facilitating the synthesis of high-quality Mandarin or Dungan speech. Both subjective and objective experiments suggest that the proposed transfer learning-based Dungan speech synthesis achieves superior scores compared to models trained only with the Dungan corpus and other methods. Consequently, our method offers a strategy to achieve speech synthesis for low-resource languages by adding prosodic information and leveraging a similar, high-resource language corpus through transfer learning.

Reshaping Bioacoustics Event Detection: Leveraging Few-Shot Learning (FSL) with Transductive Inference and Data Augmentation.

Bioacoustic event detection is a demanding endeavor involving recognizing and classifying the sounds animals make in their natural habitats. Traditional supervised learning requires a large amount of labeled data, which are hard to come by in bioacoustics. This paper presents a few-shot learning (FSL) method incorporating transductive inference and data augmentation to address the issues of too few labeled events and small volumes of recordings. Here, transductive inference iteratively alters class prototypes and feature extractors to seize essential patterns, whereas data augmentation applies SpecAugment on Mel spectrogram features to augment training data. The proposed approach is evaluated by using the Detecting and Classifying Acoustic Scenes and Events (DCASE) 2022 and 2021 datasets. Extensive experimental results demonstrate that all components of the proposed method achieve significant F-score improvements of 27% and 10%, for the DCASE-2022 and DCASE-2021 datasets, respectively, compared to recent advanced approaches. Moreover, our method is helpful in FSL tasks because it effectively adapts to sounds from various animal species, recordings, and durations.

Detection and Classification of Obstructive Sleep Apnea Using Audio Spectrogram Analysis

Sleep disorders are steadily increasing in the population and can significantly affect daily life. Low-cost and noninvasive systems that can assist the diagnostic process will become increasingly widespread in the coming years. This work aims to investigate and compare the performance of machine learning-based classifiers for the identification of obstructive sleep apnea–hypopnea (OSAH) events, including apnea/non-apnea status classification, apnea–hypopnea index (AHI) prediction, and AHI severity classification. The dataset considered contains recordings from 192 patients. It is derived from a recently released dataset which contains, amongst others, audio signals recorded with an ambient microphone placed ∼1 m above the studied subjects and apnea/hypopnea accurate events annotations performed by specialized medical doctors. We employ mel spectrogram images extracted from the environmental audio signals as input of a machine-learning-based classifier for apnea/hypopnea events classification. The proposed approach involves a stacked model which utilizes a combination of a pretrained VGG-like audio classification (VGGish) network and a bidirectional long short-term memory (bi-LSTM) network. Performance analysis was conducted using a 5-fold cross-validation approach, leaving out patients used for training and validation of the models in the testing step. Comparative evaluations with recently presented methods from the literature demonstrate the advantages of the proposed approach. The proposed architecture can be considered a useful tool for supporting OSAHS diagnoses by means of low-cost devices such as smartphones.

Exploring the potential of combining Mel spectrograms with neural networks optimized by the modified crayfish optimization algorithm for acoustic speed violation identification

Enforcing vehicle speed limits is paramount for road safety. This paper pioneers an innovative approach by synergizing signal processing and Convolutional Neural Networks (CNNs) to detect speeding violations, addressing a critical aspect of traffic management. While traditional methods have shown efficacy, the potential synergy of signal processing and AI techniques remains largely unexplored. We bridge this gap by harnessing Mel spectrograms extracted from vehicle recordings, representing intricate audio features. These spectrograms serve as inputs to a tailored CNN architecture, meticulously designed for pattern recognition in speeding-related audio cues. An altered variant of the crayfish optimization algorithm (COA) was employed to tune the CNN model. Our methodology aims to discriminate between normal driving sounds and instances of speed limit breaches. Notably absent from previous literature, our fusion method yields promising initial results, demonstrating its potential to accurately identify speeding violations. This contribution not only enhances traffic safety and management but also provides a pioneering framework for integrating signal processing and AI techniques in innovative ways, with implications extending to broader audio analysis domains.

Combining Transformer, Convolutional Neural Network, and Long Short-Term Memory Architectures: A Novel Ensemble Learning Technique That Leverages Multi-Acoustic Features for Speech Emotion Recognition in Distance Education Classrooms

Speech emotion recognition (SER) is a technology that can be applied to distance education to analyze speech patterns and evaluate speakers’ emotional states in real time. It provides valuable insights and can be used to enhance students’ learning experiences by enabling the assessment of their instructors’ emotional stability, a factor that significantly impacts the effectiveness of information delivery. Students demonstrate different engagement levels during learning activities, and assessing this engagement is important for controlling the learning process and improving e-learning systems. An important aspect that may influence student engagement is their instructors’ emotional state. Accordingly, this study used deep learning techniques to create an automated system for recognizing instructors’ emotions in their speech when delivering distance learning. This methodology entailed integrating transformer, convolutional neural network, and long short-term memory architectures into an ensemble to enhance the SER. Feature extraction from audio data used Mel-frequency cepstral coefficients; chroma; a Mel spectrogram; the zero-crossing rate; spectral contrast, centroid, bandwidth, and roll-off; and the root-mean square, with subsequent optimization processes such as adding noise, conducting time stretching, and shifting the audio data. Several transformer blocks were incorporated, and a multi-head self-attention mechanism was employed to identify the relationships between the input sequence segments. The preprocessing and data augmentation methodologies significantly enhanced the precision of the results, with accuracy rates of 96.3%, 99.86%, 96.5%, and 85.3% for the Ryerson Audio–Visual Database of Emotional Speech and Song, Berlin Database of Emotional Speech, Surrey Audio–Visual Expressed Emotion, and Interactive Emotional Dyadic Motion Capture datasets, respectively. Furthermore, it achieved 83% accuracy on another dataset created for this study, the Saudi Higher-Education Instructor Emotions dataset. The results demonstrate the considerable accuracy of this model in detecting emotions in speech data across different languages and datasets.

Auscultation-Based Pulmonary Disease Detection through Parallel Transformation and Deep Learning.

Respiratory diseases are among the leading causes of death, with many individuals in a population frequently affected by various types of pulmonary disorders. Early diagnosis and patient monitoring (traditionally involving lung auscultation) are essential for the effective management of respiratory diseases. However, the interpretation of lung sounds is a subjective and labor-intensive process that demands considerable medical expertise, and there is a good chance of misclassification. To address this problem, we propose a hybrid deep learning technique that incorporates signal processing techniques. Parallel transformation is applied to adventitious respiratory sounds, transforming lung sound signals into two distinct time-frequency scalograms: the continuous wavelet transform and the mel spectrogram. Furthermore, parallel convolutional autoencoders are employed to extract features from scalograms, and the resulting latent space features are fused into a hybrid feature pool. Finally, leveraging a long short-term memory model, a feature from the latent space is used as input for classifying various types of respiratory diseases. Our work is evaluated using the ICBHI-2017 lung sound dataset. The experimental findings indicate that our proposed method achieves promising predictive performance, with average values for accuracy, sensitivity, specificity, and F1-score of 94.16%, 89.56%, 99.10%, and 89.56%, respectively, for eight-class respiratory diseases; 79.61%, 78.55%, 92.49%, and 78.67%, respectively, for four-class diseases; and 85.61%, 83.44%, 83.44%, and 84.21%, respectively, for binary-class (normal vs. abnormal) lung sounds.