Search

Deep learning-based speech deception detection research relies on a large amount of labeled data. However, in the process of collecting speech deception detection data, the identification of truth and lies requires researchers to have a professional knowledge reserve, which greatly limits the number of annotated samples. Improving the accuracy of lie detection with insufficient annotation data is the focus of this study at this stage. In this paper, we propose a semi-supervised high-quality pseudo-label algorithm based on multi-constraint optimization (HQPL-MC) for speech deception detection. Firstly, the algorithm exploits the potential feature information of unlabeled data by using deep auto-encoder networks; secondly, it achieves entropy minimization with the help of the pseudo labeling technique to reduce the class overlap distribution of truth and deception data; finally, it improves the quality of pseudo labels by optimizing the unlabeled loss and reconstruction loss to further enhance the classification performance of the model when the labeled data is insufficient. We recorded an interview-style corpus by ourselves and used it in this paper for the experimental demonstration of the algorithm together with the Columbia/SRI/Colorado(CSC) corpus. The detection performance of the proposed algorithm is better than most state-of-the-art algorithms. • A new semi supervised speech deception detection algorithm. • An interview-type Chinese lie corpus is recorded for speech deception detection. • A data enhancement method suitable for acoustic features of speech lie detection. [ABSTRACT FROM AUTHOR]

Accurate processing and analysis of non-human primate (NHP) brain magnetic resonance imaging (MRI) serves an indispensable role in understanding brain evolution, development, aging, and diseases. Despite the accumulation of diverse NHP brain MRI datasets at various developmental stages and from various imaging sites/scanners, existing computational tools designed for human MRI typically perform poor on NHP data, due to huge differences in brain sizes, morphologies, and imaging appearances across species, sites, and ages, highlighting the imperative for NHP-specialized MRI processing tools. To address this issue, in this paper, we present a robust, generic, and fully automated computational pipeline, called non-human primates Brain Extraction and Segmentation Toolbox (nBEST), whose main functionality includes brain extraction, non-cerebrum removal, and tissue segmentation. Building on cutting-edge deep learning techniques by employing lifelong learning to flexibly integrate data from diverse NHP populations and innovatively constructing 3D U-NeXt architecture, nBEST can well handle structural NHP brain MR images from multi-species, multi-site, and multi-developmental-stage (from neonates to the elderly). We extensively validated nBEST based on, to our knowledge, the largest assemblage dataset in NHP brain studies, encompassing 1,469 scans with 11 species (e.g., rhesus macaques, cynomolgus macaques, chimpanzees, marmosets, squirrel monkeys, etc.) from 23 independent datasets. Compared to alternative tools, nBEST outperforms in precision, applicability, robustness, comprehensiveness, and generalizability, greatly benefiting downstream longitudinal, cross-sectional, and cross-species quantitative analyses. We have made nBEST an open-source toolbox (https://github.com/TaoZhong11/nBEST) and we are committed to its continual refinement through lifelong learning with incoming data to greatly contribute to the research field. • We proposed nBEST, a deep-learning toolbox for processing MR images of non-human primate brains. • nBEST leverages lifelong learning and 3D U-NeXt models, performing brain extraction, non-cerebrum removal, and tissue segmentation. • Validated with 1,400+ scans from 11 species, nBEST shows extensive applicabilit. • nBEST is available online with a user manual. [ABSTRACT FROM AUTHOR]

In recent years, precision agriculture, driven by scientific monitoring, precise management, and efficient use of agricultural resources, has become the direction for future agricultural development. The precise identification and assessment of phenotypes, which serve as external representations of a crop's growth, development, and genetic characteristics, are crucial for the realization of precision agriculture. Applications surrounding phenotypic indices also provide significant technical support for optimizing crop cultivation management and advancing smart agriculture, contributing to the efficient and high-quality development of precision agriculture.This paper focuses on lettuce and employs common nutritional stress conditions during growth as experimental settings. By collecting RGB images throughout the lettuce's complete growth cycle, we developed a deep learning-based computational model to tackle key issues in the lettuce's growth and precisely identify and assess phenotypic indices. We discovered that some phenotypic indices, including custom ones defined in this study, are representative of the lettuce's growth status. By dynamically monitoring the changes in phenotypic traits during growth, we quantitatively analyzed the accumulation and evolution of phenotypic indices across different growth stages. On this basis, a predictive model for lettuce growth and development was trained.The model incorporates MSE, SSIM, and perceptual loss, significantly enhancing the predictive accuracy of the lettuce growth images and phenotypic indices. The model trained with the reconstructed loss function outperforms the original model, with the SSIM and PSNR improving by 1.33% and 10.32%, respectively. The model also demonstrates high accuracy in predicting lettuce phenotypic indices, with an average error less than 0.55% for geometric indices and less than 1.7% for color and texture indices. Ultimately, it achieves intelligent monitoring and management throughout the lettuce's life cycle, providing technical support for high-quality and efficient lettuce production. • Accurate identification of 45 lettuce phenotypes was performed using images. • Analysis of phenotypes was conducted through dynamic approaches. • A prediction model was constructed using a reconstructed loss function approach. • Precise prediction of lettuce growth and phenotype was achieved. [ABSTRACT FROM AUTHOR]

China's coastal region is the major geographical unit for the future development of China's industrial sector. The transformation of basic structure to high-class development in China's coastal places is a significant tool for promoting the changes related to quality, power and efficiency in regional economic development. In the 21st century, environmental and energy issues have increased worldwide, and challenges related to environmental pollution, energy crises, and ecological imbalances have emerged. To climate change and energy utilization, the sustainable progress of clean energy is the new route of future energy development. Based on China's non-polluting energy growth process in the last ten years, this article explores China's clean/green energy policies and economic growth development plans. Clean energy utilization is crucial for sustainable development in the context of high-quality economic growth and climate change. However, the monetary evolution and carbon emission are not investigated whole from the clean energy aspects. Using Wind energy sources as the acceptable variable, this paper employs threshold regression and impulse functions to assess the energy consumption and economic growth on carbon emission in 30 Chinese provinces over the 2000 to 2020 period. The Deep Belief Network (DBN) model predicts wind energy utilization and efficiency. The results show that economic development and carbon emissions are connected. Further, growth influences promote the offset of carbon emissions. Green innovation alters the nexus of carbon emissions, and China's economy reduces carbon usage. It provides the decision-making policies for clean energy development. • China's Coastal region is the major geographical unit for the future development of China's industrial. • In high-quality economic growth and climate change, clean energy use is vital for sustainable development. • The utilization of wind energy and it's efficiency is predicted using Deep Belief Network (DBN) model. • Empirical results link economic growth with carbon emissions, showing growth promotes emissions offset. • Green innovation changes the economic growth-carbon link, aiding China's carbon reduction efforts. [ABSTRACT FROM AUTHOR]

• A novel approach for single channel speech enhancement is presented, using the colored spectrograms. • Using deep neural network for spectrogram denoising and regression neural network for translating the colors of denoised spectrograms to short time Fouier transform (STFT) magnitudes. • Output is comparable to the state-of-the-art baseline models at a much reduced computational cost. Speech enhancement concerns the processes required to remove unwanted background sounds from the target speech to improve its quality and intelligibility. In this paper, a novel approach for single-channel speech enhancement is presented using colored spectrograms. We propose the use of a deep neural network (DNN) architecture adapted from the pix2pix generative adversarial network (GAN) and train it over colored spectrograms of speech to denoise them. After denoising, the colors of spectrograms are translated to magnitudes of short-time Fourier transform (STFT) using a shallow regression neural network. These estimated STFT magnitudes are later combined with the noisy phases to obtain an enhanced speech. The results show an improvement of almost 0.84 points in the perceptual evaluation of speech quality (PESQ) and 1 % in the short-term objective intelligibility (STOI) over the unprocessed noisy data. The gain in quality and intelligibility over the unprocessed signal is almost equal to the gain achieved by the baseline methods used for comparison with the proposed model, but at a much reduced computational cost. The proposed solution offers a comparative PESQ score at almost 10 times reduced computational cost than a similar baseline model that has generated the highest PESQ score trained on grayscaled spectrograms, while it provides only a 1 % deficit in STOI at 28 times reduced computational cost when compared to another baseline system based on convolutional neural network-GAN (CNN-GAN) that produces the most intelligible speech. [ABSTRACT FROM AUTHOR]

Conventional automatic speaker verification systems can usually be decomposed into a front-end model such as time delay neural network (TDNN) for extracting speaker embeddings and a back-end model such as statistics-based probabilistic linear discriminant analysis (PLDA) or neural network-based neural PLDA (NPLDA) for similarity scoring. However, the sequential optimization of the front-end and back-end models may lead to a local minimum, which theoretically prevents the whole system from achieving the best optimization. Although some methods have been proposed for jointly optimizing the two models, such as the generalized end-to-end (GE2E) model and NPLDA E2E model, most of these methods have not fully investigated how to model the intra-relationship between multiple enrollment utterances. In this paper, we propose a new E2E joint method for speaker verification especially designed for the practical scenario of multiple enrollment utterances. To leverage the intra-relationship among multiple enrollment utterances, our model comes equipped with frame-level and utterance-level attention mechanisms. Additionally, focal loss is utilized to balance the importance of positive and negative samples within a mini-batch and focus on the difficult samples during the training process. We also utilize several data augmentation techniques, including conventional noise augmentation using MUSAN and RIRs datasets and a unique speaker embedding-level mixup strategy for better optimization. • Extend attention back-end to end-to-end for multi-enrollment speaker verification. • Introduce focal loss, suggest speaker embedding mixup for fine-tuning end-to-end model. • Analyze the effect of the number of enrollment utterances. • Analyze the embedding-level attention weights for speech genres. [ABSTRACT FROM AUTHOR]

Emotion detection from online textual information is gaining more attention due to its usefulness in understanding users' behaviors and their desires. This is driven by the large amounts of texts from different sources such as social media and shopping websites. Recent studies investigated the benefits of deep learning in the detection of emotions from textual conversations. In this paper, we study the performance of several deep learning and transformer-based models in the classification of emotions in English conversations. Further, we apply ensemble learning using a majority voting technique to improve the overall classification performance. We evaluated our proposed models on the SemEval 2019 Task 3 public dataset that categorizes emotions as Happy , Angry , Sad , and Others. The results show that our models can successfully distinguish the three main classes of emotions and separate them from Others in a highly imbalanced dataset. The transformer-based models achieved a micro-averaged F1-score of up to 75.55%, whereas the RNN-based models only reached 67.03%. Further, we show that the ensemble model significantly improves the overall performance and achieves a micro-averaged F1-score of 77.07%. • Emotion detection in textual conversations helps in sales, marketing, and psychology. • Recurrent neural networks and long-term dependency. • Convolutional neural networks • Transformer-based models. [ABSTRACT FROM AUTHOR]

In recent years, frequent occurrences of algal blooms due to environmental changes have posed significant threats to the environment and human health. This paper analyzes the reasons of algal bloom from the perspective of environmental factors such as nutrients, temperature, light, hydrodynamics factors and others. Various commonly used algal bloom monitoring methods are discussed, including traditional field monitoring methods, remote sensing techniques, molecular biology-based monitoring techniques, and sensor-based real-time monitoring techniques. The advantages and limitations of each method are summarized. Existing algal bloom prediction models, including traditional models and machine learning (ML) models, are introduced. Support Vector Machine (SVM), deep learning (DL), and other ML models are discussed in detail, along with their strengths and weaknesses. Finally, this paper provides an outlook on the future development of algal bloom warning techniques, proposing to combine various monitoring methods and prediction models to establish a multi-level and multi-perspective algal bloom monitoring system, further improving the accuracy and timeliness of early warning, and providing more effective safeguards for environmental protection and human health. • Reviewed the environmental factors of algal blooms. • Reviewed machine learning models for algal bloom early warning. • Reviewed the basic process of machine learning early warning. • Perspectived the future directions for algal bloom early warning. [ABSTRACT FROM AUTHOR]

This paper addresses the critical environmental issue of effectively managing construction and demolition waste (CDW), which has seen a global surge due to rapid urbanization. With the advent of deep learning-based computer vision, this study focuses on improving intelligent identification of valuable recyclables from cluttered and heterogeneous CDW streams in material recovery facilities (MRFs) by optimally leveraging both visual and spatial features (depth). A high-quality CDW RGB-D dataset was curated to capture MRF stream complexities often overlooked in prior studies, and comprises over 3500 images for each modality and more than 160,000 dense object instances of diverse CDW materials with high resource value. In contrast to former studies which directly concatenate RGB and depth features, this study introduces a new depth fusion strategy that utilizes computationally efficient convolutional operations at the end of the conventional waste segmentation architecture to effectively fuse colour and depth information. This avoids cross-modal interference and maximizes the use of distinct information present in the two different modalities. Despite the high clutter and diversity of waste objects, the proposed RGB-DL architecture achieves a 13% increase in segmentation accuracy and a 36% reduction in inference time when compared to the direct concatenation of features. The findings of this study emphasize the benefit of effectively incorporating geometrical features to complement visual cues. This approach helps to deal with the cluttered and varied nature of CDW streams, enhancing automated waste recognition accuracy to improve resource recovery in MRFs. This, in turn, promotes intelligent solid waste management for efficiently managing environmental concerns. [Display omitted] • Features a high-quality CDW RGB-D dataset curated to capture MRF stream complexities. • Direct feature fusion results in large feature maps and loss of distinct characteristics. • Advanced downstream fusion mitigates cross-modal interference. • Proposed RGB-D L fusion strategy improves accuracy without incurring high computational cost. • Most significant improvements are observed in small object segmentation. [ABSTRACT FROM AUTHOR]

Accurately predicting carbon trading prices using deep learning models can help enterprises understand the operational mechanisms and regulations of the carbon market. This is crucial for expanding the industries covered by the carbon market and ensuring its stable and healthy development. To ensure the accuracy and reliability of the predictions in practical applications, it is important to evaluate the model's robustness. In this paper, we built models with different parameters to predict carbon trading prices, and proposed models with high accuracy and robustness. The accuracy of the models was assessed using traditional survey indicators. The robustness of the CNN-LSTM model was compared to that of the LSTM model using Z-scores. The CNN-LSTM model with the best prediction performance was compared to a single LSTM model, resulting in a 9% reduction in MSE and a 0.0133 shortening of the Z-score range. Furthermore, the CNN-LSTM model achieved a level of accuracy comparable to other popular models such as CEEMDAN, Boosting, and GRU. It also demonstrated a training speed improvement of at least 40% compared to the aforementioned methods. These results suggest that the CNN-LSTM enhances model resilience. Moreover, the practicality of using Z-score to evaluate model robustness is confirmed. • Deep learning by combined CNN-LSTM networks for carbon price forecasting. • Hyperparameter tuning of deep learning models for improving forecast accuracy. • CNN-LSTM models outperform single CNN models and single LSTM models. • Performance metric of deep learning for abrupt changes in carbon price variation. [ABSTRACT FROM AUTHOR]

The construction industry generates a substantial volume of solid waste, often destinated for landfills, causing significant environmental pollution. Waste recycling is decisive in managing waste yet challenging due to labor-intensive sorting processes and the diverse forms of waste. Deep learning (DL) models have made remarkable strides in automating domestic waste recognition and sorting. However, the application of DL models to recognize the waste derived from construction, renovation, and demolition (CRD) activities remains limited due to the context-specific studies conducted in previous research. This paper aims to realistically capture the complexity of waste streams in the CRD context. The study encompasses collecting and annotating CRD waste images in real-world, uncontrolled environments. It then evaluates the performance of state-of-the-art DL models for automatically recognizing CRD waste in-the-wild. Several pre-trained networks are utilized to perform effectual feature extraction and transfer learning during DL model training. The results demonstrated that DL models, whether integrated with larger or lightweight backbone networks can recognize the composition of CRD waste streams in-the-wild which is useful for automated waste sorting. The outcome of the study emphasized the applicability of DL models in recognizing and sorting solid waste across various industrial domains, thereby contributing to resource recovery and encouraging environmental management efforts. • Automating solid waste recognition using deep learning-based models. • Segmentation of construction, renovation, and demolition waste in-the-wild. • Training deep learning-based segmentation models for effective environmental management. [ABSTRACT FROM AUTHOR]

Deep learning methods exhibited significant advantages in mapping highly nonlinear relationships with acceptable computational speed, and have been widely used to predict water quality. However, various model selection and construction methods resulted in differences in prediction accuracy and performance. Hence, a unified deep learning framework for water quality prediction was established in the paper, including data processing module, feature enhancement module, and data prediction module. In the established model, the data processing module based on wavelet transform method was applied to decomposing complex nonlinear meteorology, hydrology, and water quality data into multiple frequency domain signals for extracting self characteristics of data cyclic and fluctuations. The feature enhancement module based on Informer Encoder was used to enhance feature encoding of time series data in different frequency domains to discover global time dependent features of variables. Finally, the data prediction module based on the stacked bidirectional long and short term memory network (SBiLSTM) method was employed to strengthen the local correlation of feature sequences and predict the water quality. The established model framework was applied in Lijiang River in Guilin, China. The maximum relative errors between the predicted and observed values for dissolved oxygen (DO), chemical oxygen demand (COD Mn) were 12.4% and 20.7%, suggesting a satisfactory prediction performance of the established model. The validation results showed that the established model was superior to all other models in terms of prediction accuracy with RMSE values 0.329, 0.121, MAE values 0.217, 0.057, SMAPE values 0.022, 0.063 for DO and COD Mn , respectively. Ablation tests confirmed the necessity and rationality of each module for the established model framework. The established method provided a unified deep learning framework for water quality prediction. [Display omitted] • A deep learning model coupling with data feature extraction and enhancement methods was developed • ESWT module was applied to extract the self characteristics of data • Enhancement module was adopted to enhance the global and local feature of data • The established model improves the accuracy of water quality prediction [ABSTRACT FROM AUTHOR]

Distributed deep learning frameworks facilitate large deep learning workloads. These frameworks support sharing one GPU device among multiple jobs to improve resource utilization. Modern deep learning training jobs consume a large amount of GPU memory. Despite that, sharing GPU memory among jobs is still possible because a training job has iterative steps that its memory usage fluctuates over time. However, resource sharing also introduces the risk of job performance degradation. Co-located jobs sharing a GPU device may suffer from different levels of interference, mainly caused by memory oversharing. How to improve resource utilization while maintaining good job performance is a novel challenge for job placement strategies. This paper studies the job placement problem. We propose an opportunistic memory sharing model to describe the time-varying job memory requirements. Based on this model, we introduce an Opportunistic Job Placement Problem (OJPP) for shared GPU clusters that seek job placement configurations using a minimum number of GPU devices and guarantee user-defined performance requirements at the same time. We propose a greedy algorithm and a heuristic algorithm with computational complexities of O (n log ⁡ n) and O (n 2 log ⁡ n) , respectively, to solve the problem. We also propose an online adjustment algorithm with the computational complexity of O (n log ⁡ n) to perform updates to job placement configurations in runtime. A machine-learning-based interference prediction method is used to prepare accurate interference estimations. Extensive experiments are conducted on a GPU cluster to verify the correctness and effectiveness of our algorithms. Compared with standalone training jobs on dedicated clusters, the proposed approach reduces resource consumption by 46% in a shared cluster, while guaranteeing over 92.97% of the job performance, in terms of average job completion time. • Introduce a stochastic model to describe memory oversharing of deep learning jobs on a shared GPU device. • Introduce a novel interference-aware Opportunistic Job Placement Problem for shared distributed deep learning clusters. • Propose algorithms to handle both offline job placement and online adjustment problems. • Illustrate extensive experimental results to verify the correctness and effectiveness of the approaches. [ABSTRACT FROM AUTHOR]

• We feature a WMH comparison paper focused on TrUE-Net compared to established segmentation tools and semi-manual tracing. • Each segmentation tool is compared to both semi-manual tracing and age at both the global and regional level. • This emphasizes the strength of TrUE-Net for evaluating biological signals and its utility for large or small datasets. White matter hyperintensities (WMH) are nearly ubiquitous in the aging brain, and their topography and overall burden are associated with cognitive decline. Given their numerosity, accurate methods to automatically segment WMH are needed. Recent developments, including the availability of challenge data sets and improved deep learning algorithms, have led to a new promising deep-learning based automated segmentation model called TrUE-Net, which has yet to undergo rigorous independent validation. Here, we compare TrUE-Net to six established automated WMH segmentation tools, including a semi-manual method. We evaluated the techniques at both global and regional level to compare their ability to detect the established relationship between WMH burden and age. We found that TrUE-Net was highly reliable at identifying WMH regions with low false positive rates, when compared to semi-manual segmentation as the reference standard. TrUE-Net performed similarly or favorably when compared to the other automated techniques. Moreover, TrUE-Net was able to detect relationships between WMH and age to a similar degree as the reference standard semi-manual segmentation at both the global and regional level. These results support the use of TrUE-Net for identifying WMH at the global or regional level, including in large, combined datasets. [ABSTRACT FROM AUTHOR]

• A novel physiology-based driven patient specific DL model for EEG inverse problem in epilepsy. • Realistic simulated intracerebral electrical activity with patient's head model for the model training. • Simultaneous extraction of spatial feature and temporal dependency of HR-EEG signals using a well-tailored DL-Model. • Higher performance in terms of epileptic source localization and time course reconstruction for both simulated and real epileptic HR-EEG signals. Identifying the location, the spatial extent and the electrical activity of distributed brain sources in the context of epilepsy through ElectroEncephaloGraphy (EEG) recordings is a challenging task because of the highly ill-posed nature of the underlying Electrophysiological Source Imaging (ESI) problem. To guarantee a unique solution, most existing ESI methods pay more attention to solve this inverse problem by imposing physiological constraints. This paper proposes an efficient ESI approach based on simulation-driven deep learning. Epileptic High-resolution 256-channels scalp EEG (Hr-EEG) signals are simulated in a realistic manner to train the proposed patient-specific model. More particularly, a computational neural mass model developed in our team is used to generate the temporal dynamics of the activity of each dipole while the forward problem is solved using a patient-specific three-shell realistic head model and the boundary element method. A Temporal Convolutional Network (TCN) is considered in the proposed model to capture local spatial patterns. To enable the model to observe the EEG signals from different scale levels, the multi-scale strategy is leveraged to capture the overall features and fine-grain features by adjusting the convolutional kernel size. Then, the Long Short-Term Memory (LSTM) is used to extract temporal dependencies among the computed spatial features. The performance of the proposed method is evaluated through three different scenarios of realistic synthetic interictal Hr-EEG data as well as on real interictal Hr-EEG data acquired in three patients with drug-resistant partial epilepsy, during their presurgical evaluation. A performance comparison study is also conducted with two other deep learning-based methods and four classical ESI techniques. The proposed model achieved a Dipole Localization Error (DLE) of 1.39 and Normalized Hamming Distance (NHD) of 0.28 in the case of one patch with SNR of 10 dB. In the case of two uncorrelated patches with an SNR of 10 dB, obtained DLE and NHD were respectively 1.50 and 0.28. Even in the more challenging scenario of two correlated patches with an SNR of 10 dB, the proposed approach still achieved a DLE of 3.74 and an NHD of 0.43. The results obtained on simulated data demonstrate that the proposed method outperforms the existing methods for different signal-to-noise and source configurations. The good behavior of the proposed method is also confirmed on real interictal EEG data. The robustness with respect to noise makes it a promising and alternative tool to localize epileptic brain areas and to reconstruct their electrical activities from EEG signals. [ABSTRACT FROM AUTHOR]

N4-acetylcytidine (ac4C) is a highly conserved RNA modification that plays a crucial role in various biological processes. Accurately identifying ac4C sites is of paramount importance for gaining a deeper understanding of their regulatory mechanisms. Nevertheless, the existing experimental techniques for ac4C site identification are characterized by limitations in terms of cost-effectiveness, while the performance of current computational methods in accurately identifying ac4C sites requires further enhancement. In this paper, we present MetaAc4C, an advanced deep learning model that leverages pre-trained bidirectional encoder representations from transformers (BERT). The model is based on a bi-directional long short-term memory network (BLSTM) architecture, incorporating attention mechanism and residual connection. To address the issue of data imbalance, we adapt generative adversarial networks to generate synthetic feature samples. On the independent test set, MetaAc4C surpasses the current state-of-the-art ac4C prediction model, exhibiting improvements in terms of ACC, MCC, and AUROC by 2.36%, 4.76%, and 3.11%, respectively, on the unbalanced dataset. When evaluated on the balanced dataset, MetaAc4C achieves improvements in ACC, MCC, and AUROC by 2.6%, 5.11%, and 1.01%, respectively. Notably, our approach of utilizing WGAN-GP augmented training RNA samples demonstrates even superior performance compared to the SMOTE oversampling method. • We provide a new computing framework, termed MetaAc4C, to automatically capture local and long-range information from protein sequences using BLSTM. The attention mechanism and residual connection are employed to effectively capture the critical information from protein sequences. • MetaAc4C uses BERT module in the embedding layer to take the RNA sequence information as a sentence and extract the potential semantic information hidden in the RNA sequence, effectively improving the accuracy of model prediction • In order to solve the problem of data imbalance, we use generative adversarial network (WGAN-GP) to generate synthetic feature samples, and prove that it has higher performance than traditional feature enhancement methods. [ABSTRACT FROM AUTHOR]

Art therapy has been an essential form of psychotherapy to facilitate psychological well-being, which has been promoted and transformed by recent technological advances into digital art therapy. However, the potential of digital technologies has not been fully leveraged; especially, applying AI technologies in digital art therapy is still under-explored. In this paper, we propose an AI-infused art-making system, DeepThInk, to investigate the potential of introducing a human-AI co-creative process into art therapy, by collaborating with five experienced registered art therapists over ten months. DeepThInk offers a range of tools which can lower the expertise threshold for art-making while improving users' creativity and expressivity. We gathered the insights of DeepThInk through expert reviews and a two-part user evaluation with both synchronous and asynchronous therapy setups. This longitudinal iterative design process helped us derive and contextualize design principles of human-AI co-creation for art therapy, shedding light on future design in relevant domains. • A longitudinal iterative design process with five professional art therapists. • A novel AI-infused digital art-making system DeepThInk. • Results of an evaluation that assists the understanding of AI as a material in art therapy. [ABSTRACT FROM AUTHOR]

• A novel voice conversion technique for body-conducted unvoiced speech is proposed based on Taylor-Boltzmann Machines. The proposed algorithm was the integration of Taylor Series with Boltzmann machine Deep Neural Networks. • A body conductive microphone referred as the non audible murmur (NAM) microphone is used to capture the non-audible murmur from the neck part behind the ear. • The classifier was trained with the features likes "pitch chroma, spectral centroid, and spectral skewness" that are derived from the incoming body conducted low voice verbal communication signal. • In the initial training phase, a Taylor series approximation DNN model is trained from a collection of stereo data which encompasses the NAM speech of same phonemes represented as log-power spectral features. • Moreover, in the recognition phase, a well trained Taylor-DNN model that is based on Boltzmann Machine intakes the speech features and generates the "log-power-spectra features" and it aids in recognizing the speech waveform. • The paper may gain high interest from the readers and experts of Speech processing, Voice Conversion Techniques, body-conducted unvoiced speech. Communication becomes effectual while the verbal communication signal reaches the destination with profound characteristics. An application based on human voice attracts the researcher's attention. It leads the researcher to proceed towards the speech conversion for low voice humans having murmured voices as their attitude. The researchers introduced a technique for improving the body-conducted unvoiced speech for silent speech communication using Taylor-Boltzmann machine-trained optimized Deep Neural Network (DNN). The projected model includes two main stages: the training stage as well as recognition stage. In the training stage, the following functionalities are undergone: (i) pre-processing, (ii) feature extraction, and (iii) deep learning-based speech enhancement. Initially, the collected input Non-Audible Murmur (NAM) speech signal is subjected to the pre-processing stage, wherein the improved wiener filtering is employed for suppressing the noise in the input signal. From the pre-processed speech signal, the most relevant characteristics such as "spectral skewness, spectral chroma, spectral centroid and improved Mel Frequency Cepstral Coefficients (MFCC)" are extracted, and they are fused together. Then, using these fused features, the Taylor series with optimized DNN and Boltzmann Machine (Taylor-DNN-BM) model is trained. The final enhanced speech is acquired from the Taylor- optimized DNN-BM. The recognition phase encapsulates the feature extraction and deep learning-based speech enhancement stage. The input speech data enters into the feature extraction phase, wherein the characteristics such as "spectral skewness, spectral chroma, spectral centroid and improved (MFCC)" are retrieved. After that, these features are fused and fed as input to the Taylor-optimized DNN-BM model. From Taylor- optimized DNN-BM, the enhanced speech signal is acquired. In DNN, the weight function is fine-tuned using the newly projected Self Improved Flower Pollination Algorithm (SI-FPA) algorithm. This SI-FPA model is the conceptual improvement of the Flower Pollination Algorithm (FPA). Finally, the projected model is compared with the existing models to validate its efficiency in terms of speech enhancement. [ABSTRACT FROM AUTHOR]

This paper discusses how automatic speech recognition systems are and could be designed, in order to best exploit the discriminative information encoded in human speech. This contrasts with many recent machine learning approaches that apply general recognition architectures to signals to identify, with little concern for the nature of the input. The implicit assumption has often been that training can automatically discover the useful properties that exist in signals, with minimal manual intervention. These approaches may be suitable for some tasks such as image recognition, where the diversity of visual input is vast; e.g., an image may be any (natural or synthetic) scene that a camera views. We first examine what makes speech special, i.e., a natural signal from a complex tube, driven by a source that is quasi-periodic and/or noisy, aiming to communicate a wide variety of information, using the different vocal systems of human speakers. Then, we view how pertinent features are extracted from speech via efficient means, related to the objectives of communication. We see how to reliably and efficiently identify the different units of oral language. We learn from the history of attempts to do ASR, e.g., why they succeeded and how improved methods exploited the increasing availability of data and computer power (in particular, deep neural networks). Finally, we suggest ways to render ASR both more accurate and efficient. This work is aimed at both newcomers to ASR and experts, in terms of presenting issues broadly, but without mathematical or algorithmic details, which are readily found in the references. [ABSTRACT FROM AUTHOR]