Skip to main content
x

INFORMATION PROCESSES ANALYSIS AND MODELING LABORATORY

 

Мусабаев

The main activities of the laboratory are the development of algorithms, methods and software systems for the solution of the following problems:

1) Analysis and modeling of information processes;     

2) Digital signal processing;

3) Automatic synthesis of the speech by text;

4) Automatic speech recognition;

5) Automatic processing of text data and extraction of knowledge from texts;

6) Realization of computer vision systems.

The systems of synthesis and speech recognition, speech database, tools for automatic generation and marking the speech database, automatic processing of texts in Kazakh language have been implemented.

The obtained results:

  1. A method of phonetic-acoustic classification of the speech signal, which allows to unify the acoustic-phonetic structure of the language, has been proposed.
  1. A specialized language of phonetic representation which allows to set and describe phonetic and intonational forms of the speech has been created.  Input data of the model are described with its help. That allows flexible intersystem interaction.
  1. An algorithm of phonetic transcription of texts in Kazakh has been designed.
  1. A framework, implementing the unified methods of speech signal synthesis by a phonemic text regarding Kazakh language, has been developed.
  1. Tools in the form of an information system for automatic generation of  digital voice portrait of a person (DVPP) based on the digital recording of a natural speech signal pronounced by a person whose digital portrait is being formed; the DVPP standard defining the structure of the used models and their parameters, acceptable ranges of these parameters' values changes, and also presentation format, storage and data exchange have been developed. Standard procedures of DVPP use in speech synthesis systems, recognition and voice identification have been defined in this standard.
  1.  Algorithms to solve the problem of computer speech synthesis based on DVPP technology, and program implementation of the corresponding information system have been built. 

 

APPLIED PROJECT

 Development of a semantic analysis system of text search of new  generation focused on Kazakh language

     

f

Automatic processing of texts in  Kazakh language 

System of recording and correcting spelling mistakes in the text in office packages

• Analysis of texts in Kazakh language

•   Machine translate

•  Text comprehension

    Speech technologies:

• Recognition of Kazakh speech

• Synthesis of Kazakh speech

• Voice control by robotic complexes

j

Automatic processing of texts in  Kazakh language 

·        Lexical database (150 thousand words)

·        Lexical analyzer

·        Morphological analyzer

·        Syntax analyzer

·        Semantic analyzer

·        Spelling

·        Translation system from Kazakh to Latin texts

j

Checking spelling errors in Kazakh texts

Violation of the law of synharmonism in vowels

Violation of the law of synharmonism in consonants

Spacing a space

Inserting the symbol of  adjacent key m  

Inserting an extra letter   

Skipping a letter in a word

  Synthesis of Kazakh speech in the text

Robotics

Talking intelligent devices

Smart House

Language learning systems

Voice Translators

Audio books

Telephony systems (call centers)

Information kiosks

The help system for silent and blind people

Publications

Koibagarov K. C, Amirgaliyev Y. N., Mussabayev T. R. Development of a software module of recognition of the Kazakh language on the basis of the Markov model // Bulletin of National engineering Academy of the RK. -2013. - № 3 (49). – pp. 45-50.

Mamyrbayev O. Z., Kalimoldayev M. N., Mussabayev R. R. Methods of using VAD in systems of Kazakh speech recognition // Problems of Informatics: sci.-tech. journal of ICMMG SB RAS. – 2013. - №. 1(18). - pp. 63 - 68.

Kalimoldayev M.N., Mamyrbayev O. Z.,  R. R. Musabayev,  Orazbekov Z. N. Segmentation and processing of the speech signal using the algorithm of the average frequency of crossing levels // Problems of Informatics: scientific and technical journal of ICM & mg SB RAS. -2014. - № 1(22). -pp.73-81.

K. Koibagarov, E. Amirgaliev, T. Musabayev, O. Mambetayev. Morphological parser module for Kazakh language // The 12th International Scientific Conference Information Technologies and Management.  - Riga, 2014. – p.49-51.

R. Mussabayev, T. Mussabayev, A. Tairova. Development of multilevel speech segmentation system for constructing the speech databases of speech recognizers and synthesizers // The 12th International Scientific ConferenceInformation Technologies and Management. – Riga, 2014. -p.58-60.

Koibagarov K.C., R. R. Mussabayev, Kalimoldayev M.N. Development of the linguistic processor in the Kazakh language // Problems of computer science. Institute of computational mathematics and mathematical Geophysics, Siberian branch of the Russian Academy of Sciences. - Novosibirsk, 2014. - No. 3. - pp. 64-72.

Kalimoldayev M.,  Koibagarov K.,  Zharmagambetov A.,  Pak A.  The application of the connectionist method of semantic similarity for kazakh language // Electronics, Computer and Computation (ICECCO). – Almaty, 2015. (Scopus) (Electronic resource).

Kenshimov Ch., Amirgaliyev B., Kupgulova P. Pedestrian Detection Algorithm for Overlapping and Non overlapping Conditions  // XII- th International Conference on Electronics Computer and Computation,  ICECCO 2015. – Almaty,  2015. (Sсopus).

Kenshimov Ch., Amirgaliyev B., Kuatov K., Kairanbay M. License Plate Verification Method for Automatic License Plate Recognition Systems. // 12- th International Conference on Electronics Computer and Computation,  ICECCO. – Almaty, 2015. (Sсopus) (Electronic resource)

Amirgaliyev B., Kupagulova P., Kenshimov Ch. Pedestrian Detection Algorithm for Overlapping and Non-overlapping Conditions // 12th International Conference on Electronics, Computer and Computation ICECCO. – Almaty, 2015. (Scopus) (Electronic resource).

Amirgaliyev B., Kuatov K., Baibatyr Zh., Kenshimov Ch., Kairanbay M., Jantassov A. Statistical Inference in ALPR System. 9th IEEE International Conference // Application of Information and Communication technologies.- Almaty, 2015. (Scopus) (Electronic resource).

Kalimoldayev M. N. Amirgaliyev E. N., Mamyrbayev O. Z., R.R. Musabayev Method of developing a system of multimodal recognition of Kazakh speech // proc.rep. All-Russian Conf. "Mathematical methods of pattern recognition ММРО-17". Moscow – Kaliningrad, 2015. – p.246.

Mussabayev R.R., Amirgaliyev Ye. N., Tairova A.T., Mussabayev T.R., Koibagarov K.Ch. The technology for the automatic formation of the personal digital voice pattern // 10th IEEE International Conference on Application of Information and Communication Technologies. – 2016. -p.422-426. (Thomson)

Mussabayev R.R., Kalimoldayev M.N., Amirgaliyev Ye.N., Mussabayev T.R. Automatic speech segmentation using throat-acoustic correlation coefficients // Open Engeenering. – 2016. –N.6. –p.335-346. (Scopus)