Gintautas Tamulevičius

Bio: Gintautas Tamulevičius is an academic researcher from Vilnius University. The author has contributed to research in topics: Feature (machine learning) & Feature selection. The author has an hindex of 7, co-authored 25 publications receiving 134 citations. Previous affiliations of Gintautas Tamulevičius include Vilnius Gediminas Technical University.

Hardware Accelerated FPGA Implementation of Lithuanian Isolated Word Recognition System

Abstract: Enhancement of FPGA implementation of Lithuanian isolated word recognition system is presented. Software based recognizer implementation was used as the basis for enhancement. The feature extraction (as the most time required process) and local distance calculation (as the most times performed process) were selected for hardware implementation. Reduction of recording quality of speech was selected as the way to reduce the amount of the data to analyze. Experimental testing shows correctness of made solutions. Integration of Fast Fourier Transform module reduced the recognition time by 1.6 times, and lower quality of records increased the recognition rate by 2.8 % for speaker dependent and by 4.2 % for speaker independent recognition. The overall achieved acceleration is 6 times, average time of recognition of one word is 15.7 s. Ill. 8, bibl. 14. (in English; summaries in English, Russian and Lithuanian).

Real-Time Maritime Traffic Anomaly Detection Based on Sensors and History Data Embedding.

Abstract: The automated identification system of vessel movements receives a huge amount of multivariate, heterogeneous sensor data, which should be analyzed to make a proper and timely decision on vessel movements. The large number of vessels makes it difficult and time-consuming to detect abnormalities, thus rapid response algorithms should be developed for a decision support system to identify abnormal movements of vessels in areas of heavy traffic. This paper extends the previous study on a self-organizing map application for processing of sensor stream data received by the maritime automated identification system. The more data about the vessel’s movement is registered and submitted to the algorithm, the higher the accuracy of the algorithm should be. However, the task cannot be guaranteed without using an effective retraining strategy with respect to precision and data processing time. In addition, retraining ensures the integration of the latest vessel movement data, which reflects the actual conditions and context. With a view to maintaining the quality of the results of the algorithm, data batching strategies for the neural network retraining to detect anomalies in streaming maritime traffic data were investigated. The effectiveness of strategies in terms of modeling precision and the data processing time were estimated on real sensor data. The obtained results show that the neural network retraining time can be shortened by half while the sensitivity and precision only change slightly.

A Study of Cross-Linguistic Speech Emotion Recognition Based on 2D Feature Spaces

Abstract: In this research, a study of cross-linguistic speech emotion recognition is performed. For this purpose, emotional data of different languages (English, Lithuanian, German, Spanish, Serbian, and Polish) are collected, resulting in a cross-linguistic speech emotion dataset with the size of more than 10.000 emotional utterances. Despite the bi-modal character of the databases gathered, our focus is on the acoustic representation only. The assumption is that the speech audio signal carries sufficient emotional information to detect and retrieve it. Several two-dimensional acoustic feature spaces, such as cochleagrams, spectrograms, mel-cepstrograms, and fractal dimension-based space, are employed as the representations of speech emotional features. A convolutional neural network (CNN) is used as a classifier. The results show the superiority of cochleagrams over other feature spaces utilized. In the CNN-based speaker-independent cross-linguistic speech emotion recognition (SER) experiment, the accuracy of over 90% is achieved, which is close to the monolingual case of SER.

Improving Speech Recognition Rate through Analysis Parameters

Abstract: Speech signal is redundant and non-stationary by nature. Because of vocal tract inertness these variations are not very rapid and the signal can be considered as stationary in short segments. It is presumed that in short-time magnitude spectrum the most distinct information of speech is contained. This is the main reason for speech signal analysis in frame-by-frame manner. The analyzed speech signal is segmented into overlapping segments (so-called frames) for this purpose. Segments of 15-25 ms with the overlap of 10-15 ms are used usually. In this paper we present results of our investigation of analysis window length and frame shift influence on speech recognition rate. We have analyzed three different cepstral analysis approaches for this purpose: mel frequency cepstral analysis (MFCC), linear prediction cepstral analysis (LPCC) and perceptual linear prediction cepstral analysis (PLPC). The highest speech recognition rate was obtained using 10 ms length analysis window with the frame shift varying from 7.5 to 10 ms (regardless of analysis type). The highest increase of recognition rate was 2.5 %.

Recommended Biometric Stress Management System

Abstract: The experiences of undergoing economic crises attest that the loss of employment prompts an outbreak of mental illnesses and suicides, increases the numbers of heart attacks and strokes and negatively affects other illnesses suffered by individuals under stress. Negative stress can devastate a person, cause depression, lower productivity on the job and the competitiveness of businesses and damage the quality of life. The Recommended Biometric Stress Management System, which the aforementioned authors of this article have developed, can assist in determining the level of negative stress and resolve the problem for lessening it. The system can help to manage current stressful situation and to minimise future stress by making the level of future need satisfaction more rational. In the first case, the system facilitates individuals to make a real-time assessment of their stress level and, after they fill in a stress management questionnaire, to get rational tips for the reduction of current stress based on the best global practice accumulated in the system. The multi-variant design and multiple criteria analysis methods are used for that purpose. The generation of recommendations and the selection of the most rational are based on criteria systems and on Maslow’s Hierarchy of Needs. Since this is an interdisciplinary area of research, psychologists, philosophers and experts in information management and decision-making theories and intelligent and biometric technologies participated in the development of this system. Over the course of this system’s development, the biometric technologies of information, intelligence and voice were integrated. The case study submitted in this article demonstrates this developed system.

The Self-Organizing Map

Abstract: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

Advanced Digital Signal Processing And Noise Reduction

Abstract: advanced digital signal processing and noise reduction is available in our digital library an online access to it is set as public so you can download it instantly. Our books collection spans in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Kindly say, the advanced digital signal processing and noise reduction is universally compatible with any devices to read.

Techniques for Noise Robustness in Automatic Speech Recognition

Abstract: Spend your few moment to read a book even only few pages. Reading book is not obligation and force for everybody. When you don't want to read, you can get punishment from the publisher. Read a book becomes a choice of your different characteristics. Many people with reading habit will always be enjoyable to read, or on the contrary. For some reasons, this techniques for noise robustness in automatic speech recognition tends to be the representative book in this website.

A Review on Speech Emotion Recognition Using Deep Learning and Attention Mechanism

Abstract: Emotions are an integral part of human interactions and are significant factors in determining user satisfaction or customer opinion. speech emotion recognition (SER) modules also play an important role in the development of human–computer interaction (HCI) applications. A tremendous number of SER systems have been developed over the last decades. Attention-based deep neural networks (DNNs) have been shown as suitable tools for mining information that is unevenly time distributed in multimedia content. The attention mechanism has been recently incorporated in DNN architectures to emphasise also emotional salient information. This paper provides a review of the recent development in SER and also examines the impact of various attention mechanisms on SER performance. Overall comparison of the system accuracies is performed on a widely used IEMOCAP benchmark database.

Development and validation of a machine learning algorithm for predicting the risk of postpartum depression among pregnant women.

Abstract: Objective There is a scarcity in tools to predict postpartum depression (PPD). We propose a machine learning framework for PPD risk prediction using data extracted from electronic health records (EHRs). Methods Two EHR datasets containing data on 15,197 women from 2015 to 2018 at a single site, and 53,972 women from 2004 to 2017 at multiple sites were used as development and validation sets, respectively, to construct the PPD risk prediction model. The primary outcome was a diagnosis of PPD within 1 year following childbirth. A framework of data extraction, processing, and machine learning was implemented to select a minimal list of features from the EHR datasets to ensure model performance and to enable future point-of-care risk prediction. Results The best-performing model uses from clinical features related to mental health history, medical comorbidity, obstetric complications, medication prescription orders, and patient demographic characteristics. The model performances as measured by area under the receiver operating characteristic curve (AUC) are 0.937 (95% CI 0.912 - 0.962) and 0.886 (95% CI 0.879-0.893) in the development and validation datasets, respectively. The model performances were consistent when tested using data ending at multiple time periods during pregnancy and at childbirth. Limitations The prevalence of PPD in the study data represented a treatment prevalence and is likely lower than the illness prevalence. Conclusions EHRs and machine learning offer the ability to identify women at risk for PPD early in their pregnancy. This may facilitate scalable and timely prevention and intervention, reducing negative outcomes and the associated burden.