Gintautas Tamulevicius

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.

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 %.

Acceleration of feature extraction for FPGA-based speech recognition

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.

SFS feature selection technique for multistage emotion recognition

Feature selection is very relevant for speech emotion recognition task. Still, there is no consensus on optimal feature set and classification scheme for this task. Sequential forward selection (SFS) technique for multistage emotion classification scheme is proposed in this paper. Feature sets were formed from initial collection of 6552 speech emotion features. Experimental study was performed using Berlin emotional speech and Lithuanian spoken language emotions databases. The proposed multistage classification scheme was compared with single stage scheme. Multistage scheme determined higher order of feature sets and demonstrated higher classification accuracy than single stage scheme by 0.5-4.3 %. The superiority of SFS technique against maximal individual efficiency and minimal cross-correlation selection criterions in multistage classification scheme was 20 % approximately.

Adequacy analysis of autoregressive model for Lithuanian semivowels

Autoregressive model order and parameter estimation technique is proposed and applied for modeling of Lithuanian semivowels. According to experimental results adequate modeling of semivowels requires for model order 72 in average. The appropriate order value differs for female and male voices. Besides, there are remarkable differencies between word starting and middle phones - the last ones are influenced by surrounding vowels inevitably. This results in need for higher order models and higher prediction error attained. The adequacy of autoregressive model was confirmed objectively and subjectively.

Comparative study of multi-stage classification scheme for recognition of Lithuanian speech emotions

This paper presents the experimental study of multi-stage classification based recognition of Lithuanian speech emotions. Three different criteria for feature selection were compared for this purpose: Maximal Efficiency, Minimal Cross-Correlation feature criterions, and the Sequential Feature Selection. A large database of spoken emotional Lithuanian language was used in this experiment - each of 5 emotions was represented by 1000 utterances. The results of the speaker-independent emotion recognition experiment show the superiority of multi-stage classification using the SFS technique by 0.7-8 %. This classification scheme gave the highest recognition accuracy and the smallest feature set.

Multi-Stage Recognition of Speech Emotion Using Sequential Forward Feature Selection

Abstract The intensive research of speech emotion recognition introduced a huge collection of speech emotion features. Large feature sets complicate the speech emotion recognition task. Among various feature selection and transformation techniques for one-stage classification, multiple classifier systems were proposed. The main idea of multiple classifiers is to arrange the emotion classification process in stages. Besides parallel and serial cases, the hierarchical arrangement of multi-stage classification is most widely used for speech emotion recognition. In this paper, we present a sequential-forward-feature-selection-based multi-stage classification scheme. The Sequential Forward Selection (SFS) and Sequential Floating Forward Selection (SFFS) techniques were employed for every stage of the multi-stage classification scheme. Experimental testing of the proposed scheme was performed using the German and Lithuanian emotional speech datasets. Sequential-feature-selection-based multi-stage classification outperformed the single-stage scheme by 12–42 % for different emotion sets. The multi-stage scheme has shown higher robustness to the growth of emotion set. The decrease in recognition rate with the increase in emotion set for multi-stage scheme was lower by 10–20 % in comparison with the single-stage case. Differences in SFS and SFFS employment for feature selection were negligible.