Edgaras Ivanovas

Bio: Edgaras Ivanovas is an academic researcher from Vilnius Gediminas Technical University. The author has contributed to research in topics: Biometrics & Feature extraction. The author has an hindex of 4, co-authored 8 publications receiving 58 citations.

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).

Development of Biometric Systems for Person Recognition: Biometric Feature System

Abstract: In this paper biometric feature systems and multimodal databases for biometric recognition systems are analyzed on the basis of scientific publications in IEEE Xplore digital library. It is shown that wavelet transform coefficients are the most universal feature used in biometric person recognition systems – it is among five frequently used features used in all five popular traits. Moreover, face is the most frequently used trait in multimodal person recognition systems – it is used along with 48 % of iris, 44 % of fingerprint, 33 % of voice and 24 % of signature multimodal systems. Analysis of 15 multimodal databases reveals the fact, that older multimodal databases, e. g., XM2VTS, are still widely used for comparison. However databases such as Biosecure are more versatile and should become more popular soon if a free access will be provided.

Development of Biometric Systems for Person Recognition: Biometric Feature Systems, Traits and Acquisition

Abstract: In this paper biometric feature systems and multimodal databases for biometric recognition systems are analyzed on the basis of scientific publications in IEEE Xplore digital library. It is shown that wavelet transform coefficients are the most universal feature used in biometric person recognition systems – it is among five frequently used features used in all five popular traits. Moreover, face is the most frequently used trait in multimodal person recognition systems – it is used along with 48 % of iris, 44 % of fingerprint, 33 % of voice and 24 % of signature multimodal systems. Analysis of 15 multimodal databases reveals the fact, that older multimodal databases, e. g., XM2VTS, are still widely used for comparison. However databases such as Biosecure are more versatile and should become more popular soon if a free access will be provided.

Acceleration of feature extraction for FPGA-based speech recognition

Abstract: The paper describes a field programmable gate array implementation of the main part of speech recognition system - feature extraction. In order to accelerate recognition the whole cepstral analysis scheme is implemented in hardware by the use of intellectual property cores. Two field programmable gate array devices are used for evaluation. Comparative experimental results of four different implementations are presented. They grounds achieved 29 times faster speech analysis in comparison with software based analysis subsystem.

Peculiarities of Wiener Class Systems and their Exploitation for Speech Signal Prediction

Abstract: Straipsnyje nagrinėjamas Vinerio klasės sistemos, sudarytos is begalinės impulsinės reakcijos dinaminės posistemės ir sigmoidinio netiesiskumo, taikymas lietuvių kalbai modeliuoti. Pristatyti skirtingų „ū" balsio pradinių signalo fazių tyrimai. Gauti rezultatai patvirtina Vinerio sistemos modelio pranasumą, palyginti su tiesinės prognozės kodavimo modeliu, - Vinerio sistemos modelio mokymo duomenų aibių vidutinė kvadratinė klaida yra mažesnė apie 18 %, patikros - 17 % ir testavimo - 14 %. Papildomais eksperimentais su sesiais balsiais parodoma, kad Vinerio sistemos modelio taikymas vidutiniskai sumažina prognozės vidutine kvadratine klaidą ne mažiau kaip 13 %. Be to, Vinerio sistemos modelio taikymas vietoj begalinės impulsinės reakcijos modelio vidutiniskai ne mažiau kaip 5 % sumažina penkių balsių ilgalaikės prognozės vidutine kvadratine klaidą. Gautus rezultatus pritaikius telekomunikacijų sistemose, potencialiai galima būtų sumažinti duomenų srautus, padidinti snekos suprantamumą ir sintezuotos snekos natūralumą. Il. 5, bibl. 8, lent. 2 (anglų kalba; santraukos anglų ir lietuvių k.). http://dx.doi.org/10.5755/j01.eee.111.5.368

Artificial neural network-based speech recognition using dwt analysis applied on isolated words from oriental languages

Abstract: Speech recognition is an emerging research area having its focus on human computer interactions (HCI) and expert systems. Analyzing speech signals are often tricky for processing, due to the non-stationary nature of audio signals. The work in this paper presents a system for speaker independent speech recognition, which is tested on isolated words from three oriental languages, i.e., Urdu,Persian, and Pashto. The proposed approach combines discrete wavelet transform (DWT) and feed-forward artificial neural network (FFANN) for the purpose of speech recognition. DWT is used for feature extraction and the FFANN is utilized for the classification purpose. The task of isolated word recognition is accomplished with speech signal capturing, creating a code bank of speech samples, and then by applying pre-processing techniques.For classifying a wave sample, four layered FFANN model is used with resilient back-propagation (Rprop). The proposed system yields high accuracy for two and five classes.For db-8 level-5 DWT filter 98.40%, 95.73%, and 95.20% accuracy rate is achieved with 10, 15, and 20 classes, respectively. Haar level-5 DWT filter shows 97.20%, 94.40%, and 91% accuracy ratefor 10, 15, and 20 classes, respectively. The proposed system is also compared with a baseline method where it shows better performance. The proposed system can be utilized as a communication interface to computing and mobile devices for low literacy regions.

A Systematic Analysis of Automatic Speech Recognition: An Overview

Abstract: Most high-flying and primary means of communication among humans is speech. Despite the researches and developments in the field of automatic speech recognition the accuracy of the said is still a research challenge. This paper reviews past work comparing modern speech recognition systems and humans to determine how far recent dramatic progress in technology has evolved towards the objective of human-like performance. An overview of sources of knowledge is introduced and the use of knowledge to create and verify hypotheses is discussed.

Review of the Blockchain Technology in the Energy Sector

Abstract: With the appearance of Blockchain technology, besides cryptocurrency, interest in the use of this technology in various fields has increased, including in the energy sector. Since Blockchain technology has repeatedly proven its importance in various fields, now the advantages of technology have become obvious in large energy companies. Many developed countries are massively starting to introduce Blockchain technology into the energy industry. While it is mainly pilot projects or just technology testing but already now Blockchain can qualify for creating new energy markets. The energy sector is currently at the stage of transition from a centralized system to a decentralized one in which complete autonomy will be achieved through the production and storage of energy.

FPGA based fast Lithuanian isolated word recognition system

Abstract: The article presents the Lithuanian isolated word recognition system implementation in a FPGA hard-core. The pursued objective is the acceleration of the previous soft-core implementation at both key stages: feature extraction and recognition. The 12-th order cepstral analysis is used to extract speech signal features, while for isolated word recognition a dynamic time warping is used. Implementation completely done in the VHDL hard-core allowed us to 320 times speed-up the signal cepstrum calculation and 348 times - one dynamic time warping comparison with border constraints. The recognition system works in real time and is built on medium class FPGA, operating at 50 MHz main clock frequency. It is tested on 6 times repeated 100 Lithuanian words dictionary. Speaker dependent recognition tests done for 10 speakers yield the 97.7 % average recognition accuracy (with 4.9 % recognition improvement over the previous implementation).

Quality Estimation Methodology of Speech Recognition Features

Abstract: The best feature set selection is the key of successful speech recognition system. Quality measure is needed to characterize the chosen feature set. Variety of feature quality metrics are proposed by other authors. However, no guidance is given to choose the appropriate metric. Also no metrics investigations for speech features were made. In the paper the methodology for quality estimation of speech features is presented. Metrics have to be chosen on the ground of their correlation with classification results. Linear Frequency Cepstrum (LFCC), Mel Frequency Cepstrum (MFCC), Perceptual Linear Prediction (PLP) analyses were selected for experiment. The most proper metric was chosen in combination with Dynamic Time Warping (DTW) classifier. Experimental investigation results are presented. Ill. 5, bibl. 18, tabl. 3 (in English; abstracts in English and Lithuanian). http://dx.doi.org/10.5755/j01.eee.110.4.302