# Artificial Intelligence in Speech Modelling

**Source**: https://english.spbu.ru/admission/programms/graduate/artificial-intelligence-speech-modelling
**Parent**: https://english.spbu.ru/admission/programms/graduate

*In Russian*

Level of education Master

Type of instruction Full-time

Duration 2 years

Programme description

The programme is aimed at training specialists in artificial intelligence and big data in speech technologies. Graduates of the programme will be specialists in a wide range of areas: methods and algorithms for processing large amounts of audio materials to automatically generate speech messages; extraction of content information from a voice signal, in particular information about the speaker (social characteristics, physiological, mental state, etc.), verification and identification of the speaker; designing of conversational agents and human-machine speech-based interface; linguistic aspects of artificial intelligence.

Main courses

##### Description and modeling of language (speech and text)

- Formal Methods for Speech Modelling
- Phonology and Speech
- Psychological and Physiological Aspects of Speech
- Acoustic Analysis of Speech Signals
- Segmental and Suprasegmental Units of Language
- Phonetic Universals
- Types and Forms of Speech

##### Courses in Machine learning

- The Mathematics of Machine Learning
- Probability and Statistical Models
- Machine Learning
- Neural Networks and Deep Learning
- Big Data Analytics
- Key Technology

##### Courses in language processing

- Automatic Speech Recognition
- Automatic Speech Synthesis
- Human Identification by Voice
- Analysis of multimodal data in identification of psycho-physiological state of individual
- Speech and Multimodal Data Corpora Design
- Automatic Transcription

##### Courses in software engineering

- Python Programming
- Neural Networks Programming
- Text Processing and Speech Technology
- Digital Processing of Speech Signals
- Programming of Text Generation and Processing

Our advantages

- The programme is designed to train highly qualified specialists who can: apply both the latest mathematical apparatus used to design of AI systems and knowledge in the field of linguistics, psychology and physiology; find solutions to current scientific and technical problems in business and academic research. Graduates of the programme will acquire both practical skills in AI problems solving and a theoretical knowledge of linguistics, which will allow them to further improve their qualifications

Main areas of research

- Automatic Speech Recognition
- Automatic Speech Synthesis
- Human Identification by Voice
- Analysis of Multimodal Data in Identification of Psycho-physiological State of Individual
- Speech and Multimodal Data Corpora
- Design Design of Speech Technologies for Under-Resourced Languages
- Design of Conversational Agents

Teaching staff

- Pavel Skrelin, Professor, expert in phonology, phonetics, and speech technologies; expert in automatic speech synthesis and recognition, modelling of segmental and suprasegmental units, development of speech corpora, and automatic speech signal analysis; Chairperson of the Special Interest Group on Russian Speech Analysis of the International Speech Communication Association (ISCA SIGRU).
- Vera Evdokimova, Associate Professor, expert in phonetics, speech technology, and computational linguistics; expert in human voice identification, acoustic analysis of speech signals, modelling of segmental units, analysis of various types of speech, and the development of speech corpora.
- Uliana Kochetkova, Associate Professor, expert in Russian and French phonetics and speech technologies; expert in intonation analysis, modelling of suprasegmental units, and the development of speech and multimodal corpora.
- Svetlana Tananaiko, Associate Professor, expert in phonology and phonetics; expert in the Russian language, its dialectal variation, and phonetic interference between languages
- Elena Shamina, Associate Professor, expert in Russian and English phonetics, phonology, and methods of foreign language teaching; expert in phonetic interference between languages
- Karina Evgrafova, Associate Professor, expert in Russian and English phonetics, phonology, singing speech, and methods of foreign language teaching

Career opportunities

- Linguist
- Teacher
- Researcher
- Programmer
- Statistitian
- Data analysis specialist
- Information Technologies (IT) Senior Project Manager

[This webpage may contain outdated information. The programme descriptions and admission requirements for the 2026/2027 academic year are currently being updated. For the latest information on 2026/2027 admission, please visit the Admissions Office website.](https://abiturient.spbu.ru/en/)

[Tuition](https://english.spbu.ru/admission/tuition)

[Create Your Personal Account](https://cabinet.spbu.ru/)