Документ взят из кэша поисковой машины. Адрес оригинального документа : http://www.intsys.msu.ru/en/invest/speech/research/
Дата изменения: Unknown
Дата индексирования: Thu Feb 27 22:31:43 2014
Кодировка: Windows-1251
Intelligent Systems :: Research :: :: Research
Русская версия этой страницы
To the Start Page
The Chair of Mathematical Theory of Intelligent Systems and
Laboratory of Problems of Theoretical Cybernetics
of Moscow State University Official Website
To the Start Page News MaTIS Chair Staff Science Teaching Research Magazine Culture Full-text Search
 Computer Solver development of the Automatic solver of mathematical problems
 Computer Teacher development of computer teaching systems
 Information Monitoring creating the systems of information monitoring
 Search in Databases systems of fast search in extensive databases
Research
Main directions of scientific research
Articles
Scientific publications about speech technologies
Demos
Computer demos and presentations
Contacts
Contact information (phones, e-mails)

Information on Basic Directions of Scientific Research

The basic work of our group of mathematicians is devoted to theoretical problems in automata theory.  An automata is a device that has input and output channels and internal memory and is capable to translate input influence into output reactions.  It is possible to get new automata using the existing ones by connecting the input and output channels. A complex analysis is required to find the principal possibility of solution of this problem (that is called the problem of completeness).  The problem of completeness is falls under the category of problems unsolvable in general case.  It is possible to solve it for special classes of automata.  The mathematical apparatus that arises from here is a set of rules of input information tests.  It is possible this apparatus in an applied investigations on recognition of consecutive information.

As a result of this, it become possible to construct recognition algorithms and models of artificial organs of sense in parallel with the theoretical work.

Our main scientific works are:

  • 1985 - model of color eyesight of humans and animals (in co-operation with the chair of psychophysiology of the MSU);
  • 1987 - an automata algorithm of photo pictures recognition;
  • 1993 - semantic frequency analysis of texts;
  • 1994 - the management of all-Russia speech recognition project;
  • 1995 - model of subjective phoneme perception;
  • 1996 - the problem of separation of symbols in printed texts and hand-writing;
  • 1998 - usage of non-audio sensors for speech recognition;
  • 1999 - lip reading, hand-writing recognition, the model of constancy of color eyesight of humans.

The work on all these problems were done in the form of students diploma works, each including a theoretical part and a demo computer program.  They used an automata model of input information representation.

The theoretical investigation on perspectives of usage of new mathematical methods for speech recognition can be fulfilled in the following directions:


Signal level.

  1. Search for new types of speech signal parameters.  Reduction of dimension of speech signals description space using special methods like factor analysis and others.
  2. Making experiments on algorithmization of ways of speech recognition by humans.  Investigation of hearing apparatus neurophysiology.  Construction of subjective sound metrics.  Finding the dimension of space of subjective speech features.  Testing the hypothesis of local speech recognition by humans (in co-operation with the chair of psychophysiology of the MSU)
  3. Search for speaker-independent features on reliable phoneme segmentation of speech.  Investigation of possibility of local phoneme identification.  Investigation of dependence of sounds parameters on phonetic environment.  Automatic extraction of features, allowing us to define the class of phoneme.
  4. Investigation of possibility of using the additional (non-acoustic) sources of information for speech recognition.


Semantic level.

  1. Automatization of process of construction of semantic grammars in the given theme.
  2. Investigation of possibilities of semantic grammars usage.  Construction of themes library.
  3. Algorithms of fast recognition of theme of speech using audio information from the known list of possible themes.


Mathematical methods of recognition.

  1. Search for parameters of stochastic vectors, characterizing the phonemes.  The investigation for type of its stochastic distribution.  Modifications and enhancing of HMM.
  2. Construction of discrete methods of fast pre-recognition on the base of phoneme segmentation and using the features of separate phonemes.
  3. Syntheses of hierarchical recognizer - structural automata, working with different levels of details of speech signal simultaneously.
  4. Investigations of possibilities of usage of methods of fussy logic, optimal control and others in solving of problems of speech recognition. 
  5. Usage of autocorrelation and autocomparing methods for solving a problem of speaker-independent recognition.

 

Deputy head of the Laboratory of Problems of Theoretical Cybernetics of the Lomonosov Moscow State University

Prof. Dmitry Babin
  

   ї 2001-2013. The Chair of Mathematical Theory of Intelligent Systems, Laboratory of Problems of Theoretical Cybernetics
XWare
 Full-text search
 
Only exact word forms      Give up to search results per page
Rambler's Top100 Рейтинг@Mail.ru