scholarly journals Static–dynamic features and hybrid deep learning models based spoof detection system for ASV

2021 ◽  
Author(s):  
Aakshi Mittal ◽  
Mohit Dua
Keyword(s):  
Deep Learning ◽  
Speech Synthesis ◽  
Short Term Memory ◽  
Detection System ◽  
Performance Comparison ◽  
Voice Conversion ◽  
Learning Models ◽  
Dynamic Features ◽  
User Identification ◽  
Detection Systems

AbstractDetection of spoof is essential for improving the performance of current scenario of Automatic Speaker Verification (ASV) systems. Empowerment to both frontend and backend parts can build the robust ASV systems. First, this paper discuses performance comparison of static and static–dynamic Constant Q Cepstral Coefficients (CQCC) frontend features by using Long Short Term Memory (LSTM) with Time Distributed Wrappers model at the backend. Second, it performs comparative analysis of ASV systems built using three deep learning models LSTM with Time Distributed Wrappers, LSTM and Convolutional Neural Network at backend and using static–dynamic CQCC features at frontend. Third, it discusses implementation of two spoof detection systems for ASV by using same static–dynamic CQCC features at frontend and different combination of deep learning models at backend. Out of these two, the first one is a voting protocol based two-level spoof detection system that uses CNN, LSTM model at first level and LSTM with Time Distributed Wrappers model at second level. The second one is a two-level spoof detection system with user identification and verification protocol, which uses LSTM model for user identification at first level and LSTM with Time Distributed Wrappers for verification at the second level. For implementing the proposed work, a variation in ASVspoof 2019 dataset has been used to introduce all types of spoofing attacks such as Speech Synthesis (SS), Voice Conversion (VC) and replay in single set of dataset. The results show that, at frontend, static–dynamic CQCC feature outperform static CQCC features and at the backend, hybrid combination of deep learning models increases accuracy of spoof detection systems.

scholarly journals Discriminative Multi-Stream Postfilters Based on Deep Learning for Enhancing Statistical Parametric Speech Synthesis

Biomimetics ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 12
Author(s):  
Marvin Coto-Jiménez
Keyword(s):  
Deep Learning ◽  
Hidden Markov Models ◽  
Speech Synthesis ◽  
Short Term Memory ◽  
Markov Models ◽  
Hidden Markov ◽  
Voice Conversion ◽  
Statistical Parametric Speech Synthesis ◽  
Parametric Speech Synthesis

Statistical parametric speech synthesis based on Hidden Markov Models has been an important technique for the production of artificial voices, due to its ability to produce results with high intelligibility and sophisticated features such as voice conversion and accent modification with a small footprint, particularly for low-resource languages where deep learning-based techniques remain unexplored. Despite the progress, the quality of the results, mainly based on Hidden Markov Models (HMM) does not reach those of the predominant approaches, based on unit selection of speech segments of deep learning. One of the proposals to improve the quality of HMM-based speech has been incorporating postfiltering stages, which pretend to increase the quality while preserving the advantages of the process. In this paper, we present a new approach to postfiltering synthesized voices with the application of discriminative postfilters, with several long short-term memory (LSTM) deep neural networks. Our motivation stems from modeling specific mapping from synthesized to natural speech on those segments corresponding to voiced or unvoiced sounds, due to the different qualities of those sounds and how HMM-based voices can present distinct degradation on each one. The paper analyses the discriminative postfilters obtained using five voices, evaluated using three objective measures, Mel cepstral distance and subjective tests. The results indicate the advantages of the discriminative postilters in comparison with the HTS voice and the non-discriminative postfilters.

scholarly journals An Automobile Environment Detection System Based on Deep Neural Network and its Implementation Using IoT-Enabled In-Vehicle Air Quality Sensors

2020 ◽  
Vol 12 (6) ◽  
pp. 2475 ◽  
Author(s):  
Jae-joon Chung ◽  
Hyun-Jung Kim
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Air Quality ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Detection System ◽  
Learning Models ◽  
Generative Adversarial Network ◽  
Detection Model ◽  
Adversarial Network

This paper elucidates the development of a deep learning–based driver assistant that can prevent driving accidents arising from drowsiness. As a precursor to this assistant, the relationship between the sensation of sleep depravity among drivers during long journeys and CO2 concentrations in vehicles is established. Multimodal signals are collected by the assistant using five sensors that measure the levels of CO, CO2, and particulate matter (PM), as well as the temperature and humidity. These signals are then transmitted to a server via the Internet of Things, and a deep neural network utilizes this information to analyze the air quality in the vehicle. The deep network employs long short-term memory (LSTM), skip-generative adversarial network (GAN), and variational auto-encoder (VAE) models to build an air quality anomaly detection model. The deep learning models gather data via LSTM, while the semi-supervised deep learning models collect data via GANs and VAEs. The purpose of this assistant is to provide vehicle air quality information, such as PM alerts and sleep-deprived driving alerts, to drivers in real time and thereby prevent accidents.

scholarly journals Biometric User Identification Based on Human Activity Recognition Using Wearable Sensors: An Experiment Using Deep Learning Models

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 308
Author(s):  
Sakorn Mekruksavanich ◽  
Anuchit Jitpattanakul
Keyword(s):  
Deep Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Short Term Memory ◽  
Wearable Sensors ◽  
The Elderly ◽  
Human Activity Recognition ◽  
Learning Models ◽  
User Identification ◽  
Sensory Data

Currently, a significant amount of interest is focused on research in the field of Human Activity Recognition (HAR) as a result of the wide variety of its practical uses in real-world applications, such as biometric user identification, health monitoring of the elderly, and surveillance by authorities. The widespread use of wearable sensor devices and the Internet of Things (IoT) has led the topic of HAR to become a significant subject in areas of mobile and ubiquitous computing. In recent years, the most widely-used inference and problem-solving approach in the HAR system has been deep learning. Nevertheless, major challenges exist with regard to the application of HAR for problems in biometric user identification in which various human behaviors can be regarded as types of biometric qualities and used for identifying people. In this research study, a novel framework for multi-class wearable user identification, with a basis in the recognition of human behavior through the use of deep learning models, is presented. In order to obtain advanced information regarding users during the performance of various activities, sensory data from tri-axial gyroscopes and tri-axial accelerometers of the wearable devices are applied. Additionally, a set of experiments were shown to validate this work, and the proposed framework’s effectiveness was demonstrated. The results for the two basic models, namely, the Convolutional Neural Network (CNN) and the Long Short-Term Memory (LSTM) deep learning, showed that the highest accuracy for all users was 91.77% and 92.43%, respectively. With regard to the biometric user identification, these are both acceptable levels.

scholarly journals Anomaly Detection Using Deep Neural Network for IoT Architecture

2021 ◽  
Vol 11 (15) ◽  
pp. 7050
Author(s):  
Zeeshan Ahmad ◽  
Adnan Shahid Khan ◽  
Kashif Nisar ◽  
Iram Haider ◽  
Rosilah Hassan ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Deep Neural Network ◽  
Detection System ◽  
Traffic Monitoring ◽  
Detection Accuracy ◽  
Learning Models ◽  
Prime Concern ◽  
Entry Points

The revolutionary idea of the internet of things (IoT) architecture has gained enormous popularity over the last decade, resulting in an exponential growth in the IoT networks, connected devices, and the data processed therein. Since IoT devices generate and exchange sensitive data over the traditional internet, security has become a prime concern due to the generation of zero-day cyberattacks. A network-based intrusion detection system (NIDS) can provide the much-needed efficient security solution to the IoT network by protecting the network entry points through constant network traffic monitoring. Recent NIDS have a high false alarm rate (FAR) in detecting the anomalies, including the novel and zero-day anomalies. This paper proposes an efficient anomaly detection mechanism using mutual information (MI), considering a deep neural network (DNN) for an IoT network. A comparative analysis of different deep-learning models such as DNN, Convolutional Neural Network, Recurrent Neural Network, and its different variants, such as Gated Recurrent Unit and Long Short-term Memory is performed considering the IoT-Botnet 2020 dataset. Experimental results show the improvement of 0.57–2.6% in terms of the model’s accuracy, while at the same time reducing the FAR by 0.23–7.98% to show the effectiveness of the DNN-based NIDS model compared to the well-known deep learning models. It was also observed that using only the 16–35 best numerical features selected using MI instead of 80 features of the dataset result in almost negligible degradation in the model’s performance but helped in decreasing the overall model’s complexity. In addition, the overall accuracy of the DL-based models is further improved by almost 0.99–3.45% in terms of the detection accuracy considering only the top five categorical and numerical features.

scholarly journals A Hybrid Optimized LSTM Models for Human Activity Recognition with IOT Devices

2021 ◽  
pp. 182-189
Author(s):  
S. Arokiaraj ◽  
Dr. N. Viswanathan
Keyword(s):  
Deep Learning ◽  
Internet Of Things ◽  
Short Term Memory ◽  
The Other ◽  
Learning Models ◽  
Computational Overhead ◽  
Temporal Features ◽  
Human Movements ◽  
Proposed Model ◽  
Iot Devices

With the advent of Internet of things(IoT),HA (HA) recognition has contributed the more application in health care in terms of diagnosis and Clinical process. These devices must be aware of human movements to provide better aid in the clinical applications as well as user’s daily activity.Also , In addition to machine and deep learning algorithms, HA recognition systems has significantly improved in terms of high accurate recognition. However, the most of the existing models designed needs improvisation in terms of accuracy and computational overhead. In this research paper, we proposed a BAT optimized Long Short term Memory (BAT-LSTM) for an effective recognition of human activities using real time IoT systems. The data are collected by implanting the Internet of things) devices invasively. Then, proposed BAT-LSTM is deployed to extract the temporal features which are then used for classification to HA. Nearly 10,0000 dataset were collected and used for evaluating the proposed model. For the validation of proposed framework, accuracy, precision, recall, specificity and F1-score parameters are chosen and comparison is done with the other state-of-art deep learning models. The finding shows the proposed model outperforms the other learning models and finds its suitability for the HA recognition.

scholarly journals Deep-Learning-Based Approach to Anomaly Detection Techniques for Large Acoustic Data in Machine Operation

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5446
Author(s):  
Hyojung Ahn ◽  
Inchoon Yeo
Keyword(s):  
Deep Learning ◽  
Anomaly Detection ◽  
Short Term Memory ◽  
Detection System ◽  
Noisy Environments ◽  
Acoustic Data ◽  
Detection Techniques ◽  
Machine Operation ◽  
Detection Technology ◽  
Environment Noise

As the workforce shrinks, the demand for automatic, labor-saving, anomaly detection technology that can perform maintenance on advanced equipment such as vehicles has been increasing. In a vehicular environment, noise in the cabin, which directly affects users, is considered an important factor in lowering the emotional satisfaction of the driver and/or passengers in the vehicles. In this study, we provide an efficient method that can collect acoustic data, measured using a large number of microphones, in order to detect abnormal operations inside the machine via deep learning in a quick and highly accurate manner. Unlike most current approaches based on Long Short-Term Memory (LSTM) or autoencoders, we propose an anomaly detection (AD) algorithm that can overcome the limitations of noisy measurement and detection system anomalies via noise signals measured inside the mechanical system. These features are utilized to train a variety of anomaly detection models for demonstration in noisy environments with five different errors in machine operation, achieving an accuracy of approximately 90% or more.

scholarly journals Efficient Deep Learning Models for DGA Domain Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Juhong Namgung ◽  
Siwoon Son ◽  
Yang-Sae Moon
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Ensemble Model ◽  
Learning Models ◽  
Short Term ◽  
Domain Names ◽  
Additional Information ◽  
Domain Sequence ◽  
Long Short Term Memory ◽  
And Control

In recent years, cyberattacks using command and control (C&C) servers have significantly increased. To hide their C&C servers, attackers often use a domain generation algorithm (DGA), which automatically generates domain names for the C&C servers. Accordingly, extensive research on DGA domain detection has been conducted. However, existing methods cannot accurately detect continuously generated DGA domains and can easily be evaded by an attacker. Recently, long short-term memory- (LSTM-) based deep learning models have been introduced to detect DGA domains in real time using only domain names without feature extraction or additional information. In this paper, we propose an efficient DGA domain detection method based on bidirectional LSTM (BiLSTM), which learns bidirectional information as opposed to unidirectional information learned by LSTM. We further maximize the detection performance with a convolutional neural network (CNN) + BiLSTM ensemble model using Attention mechanism, which allows the model to learn both local and global information in a domain sequence. Experimental results show that existing CNN and LSTM models achieved F1-scores of 0.9384 and 0.9597, respectively, while the proposed BiLSTM and ensemble models achieved higher F1-scores of 0.9618 and 0.9666, respectively. In addition, the ensemble model achieved the best performance for most DGA domain classes, enabling more accurate DGA domain detection than existing models.

scholarly journals Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

2021 ◽  
Vol 7 ◽  
pp. e795
Author(s):  
Pooja Vinayak Kamat ◽  
Rekha Sugandhi ◽  
Satish Kumar
Keyword(s):  
Deep Learning ◽  
Anomaly Detection ◽  
Short Term Memory ◽  
Rotating Machinery ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Learning Models ◽  
Vibration Data ◽  
Degradation Data ◽  
Useful Life

Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.

Abstract 279: Multi-task Learning Improves Model Performance in Predicting Rare Catastrophic Events in Healthcare Claims Dataset

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_4) ◽  
Author(s):  
ChienYu Chi ◽  
Yen-Pin Chen ◽  
Adrian Winkler ◽  
Kuan-Chun Fu ◽  
Fie Xu ◽  
...  
Keyword(s):  
Cardiac Arrest ◽  
Deep Learning ◽  
Short Term Memory ◽  
Learning System ◽  
Research Database ◽  
Learning Models ◽  
Catastrophic Events ◽  
Single Task ◽  
Task Learning ◽  
Hospital Cardiac Arrest

Introduction: Predicting rare catastrophic events is challenging due to lack of targets. Here we employed a multi-task learning method and demonstrated that substantial gains in accuracy and generalizability was achieved by sharing representations between related tasks Methods: Starting from Taiwan National Health Insurance Research Database, we selected adult people (>20 year) experienced in-hospital cardiac arrest but not out-of-hospital cardiac arrest during 8 years (2003-2010), and built a dataset using de-identified claims of Emergency Department (ED) and hospitalization. Final dataset had 169,287 patients, randomly split into 3 sections, train 70%, validation 15%, and test 15%.Two outcomes, 30-day readmission and 30-day mortality are chosen. We constructed the deep learning system in two steps. We first used a taxonomy mapping system Text2Node to generate a distributed representation for each concept. We then applied a multilevel hierarchical model based on long short-term memory (LSTM) architecture. Multi-task models used gradient similarity to prioritize the desired task over auxiliary tasks. Single-task models were trained for each desired task. All models share the same architecture and are trained with the same input data Results: Each model was optimized to maximize AUROC on the validation set with the final metrics calculated on the held-out test set. We demonstrated multi-task deep learning models outperform single task deep learning models on both tasks. While readmission had roughly 30% positives and showed miniscule improvements, the mortality task saw more improvement between models. We hypothesize that this is a result of the data imbalance, mortality occurred roughly 5% positive; the auxiliary tasks help the model interpret the data and generalize better. Conclusion: Multi-task deep learning models outperform single task deep learning models in predicting 30-day readmission and mortality in in-hospital cardiac arrest patients.

Sign in / Sign up

Export Citation Format

Share Document