Informatica

The problem of speech corpus for design of human-computer interfaces working in voice recognition and synthesis mode is investigated. Specific requirements of speech corpus for speech recognizers and synthesizers were accented. It has been discussed that in order to develop above mentioned speech corpus, it has to consist of two parts. One part of speech corpus should be presented for the needs of Lithuanian text-to-speech synthesizers, another part of speech corpus – for the needs of Lithuanian speech recognition engines. It has been determined that the part of speech corpus designed for speech recognition engines has to ensure the availability to present language specificity by the use of different sets of phonemes. According to the research results, the speech corpus Liepa, which consists of two parts, was developed. This speech corpus opens possibilities for cost-effective and flexible development of human-computer interfaces working in voice recognition and synthesis mode.

The performance of an automatic speech recognition system heavily depends on the used feature set. Quality of speech recognition features is estimated by classification error, but then the recognition experiments must be performed, including both front-end and back-end implementations. We propose a method for features quality estimation that does not require recognition experiments and accelerate automatic speech recognition system development. The key component of our method is usage of metrics right after front-end features computation. The experimental results show that our method is suitable for recognition systems with back-end Euclidean space classifiers.

In this paper we consider random sequences in the background of which specific short-time random elements can emerge. The theory and constructive methods for recognition of short-time specific random elements that may emerge in the background of random sequences are expounded. The results of experimental investigations are presented. The prospects for a wider application of the results obtained are discussed as well.

This study presents developed algorithm for assessment and updating estimates of parameters in the mathematical models of non-stationary processes (for instance, system ageing model, dynamic system models and so on) with respect of prior information and new obtained observations. Proposed algorithm for updating estimates of random parameters is based on modified application of Bayesian approach (BA). Developed algorithm was applied for Ignalina NPP Unit 2 RBMK-1500 reactor's closure of the gas-gap between the pressure tubes and the graphite bore probabilistic analysis.

There is presented a technique of transcribing Lithuanian text into phonemes for speech recognition. Text-phoneme transformation has been made by formal rules and the dictionary. Formal rules were designed to set the relationship between segments of the text and units of formalized speech sounds – phonemes, dictionary – to correct transcription and specify stress mark and position. Proposed the automatic transcription technique was tested by comparing its results with manually obtained ones. The experiment has shown that less than 6% of transcribed words have not matched.

Specifics of hidden Markov model‐based speech recognition are investigated. Influence of modeling simple and context‐dependent phones, using simple Gaussian, two and three‐component Gaussian mixture probability density functions for modeling feature distribution, and incorporating language model are discussed. Word recognition rates and model complexity criteria are used for evaluating suitability of these modifications for practical applications. Development of large vocabulary continuous speech recognition system using HTK toolkit and WSJCAM0 English speech corpus is described. Results of experimental investigations are presented.

The isolated word speech recognition system based on dynamic time warping (DTW) has been developed. Speaker adaptation is performed using speaker recognition techniques. Vector quantization is used to create reference templates for speaker recognition. Linear predictive coding (LPC) parameters are used as features for recognition. Performance is evaluated using 12 words of Lithuanian language pronounced ten times by ten speakers.

The problem of change point detection when the properties of the random process observed suddenly begin changing slowly is considered. The most probable time moments of changes are investigated. Random processes are described by autoregression equations. The situation is studied when slow changes in the properties of a random process take place according to the linear law. An example of solving the problem is presented, realized by computer.