Annotation. In the last decade, tremendous progress has been made in the field of speech and language processing with the advent of deep learning approaches and the availability of computing resources. These advances are giving the possibility to address NLP tasks in a new and completely different manner. One of these tasks is to translate audio speech in one language into text in the target language. For years, it has been addressed through the classical approach. The way to face the task was to decode the speech utterance with an ASR module and then translate it with a machine translation system. The classical way is known as "cascade" speech translation. However, in the last years, a new approach has been proposed in which speech is not decoded but directly translated into the language differ than language of the utterance.


The aim of the project: The goal of the project is to develop methods and algorithms for speech translation for two low-resource languages, namely Kazakh and Tatar, based on pre-trained models using some intermediate language. Recent trends are based on the use of a single neural network to translate an input audio signal in one language into text in another. The goal of the project should be achieved through the use of cascading solutions or end-to-end approaches. In particular, we are interested in comparing the performance of the cascade approach with the direct approach. A speech synthesis model for the target language can be added to both methods.

Project objectives: To achieve this goal, the following tasks will be performed within the framework of the project:
1. Data collection and processing
1.1 Collection and processing of audio data for automatic speech recognition system and speech synthesis
1.2 Collection and processing of text data for machine translation system
2. Development of pretrained models
2.1 Development of pretrained models for audio data
2.2 Developing pretrained models for text data
3. Development of machine translation systems
3.1 Development of a machine translation system from Kazakh into an intermediate language
3.2 Development of a machine translation system from an intermediate language into Tatar language
4. Development of a cascading speech translation system
5. Development of a system for end-to-end speech translation with pretrained models
5.1 Design of the end-to-end speech translation model
5.2 Training and testing the end-to-end speech translation system with pretrained models
6. Development of software and web services
6.1 Development of a software module for a cascaded speech translation system
6.2 Development of a software module for a system of end-to-end speech translation
6.3 Software integration and web service development

The main results of the project will be:

1. audio corpora of the Kazakh language;
2. parallel text corpora for Kazakh and Russian languages;
3. pre-trained and fine-tuned models for speech recognition for Kazakh language based on self-supervised learning with gradual specialization of training data;
4. pre-trained and fine-tuned models for machine translation for Kazakh and Russian languages as well as for Tatar and Russian languages;
5. software and a demonstration web service of the Kazakh and Tatar speech translation system that implement the developed methods and algorithms;
6. publications in peer-reviewed journals with high impact factor and in the proceedings of top conferences.

The theoretical significance of this research is that the results of the study can be used in the development of speech translation systems for the related languages (Uzbek, Kyrgyz) and other low resource languages. In addition, with proper design, the proposed model can be used to create speech-to-speech systems using a single neural network. The practical significance of the project is that it will enable domestic software developers to use the developed tools for developing open and commercial speech translation programs for the Kazakh language in other domains (mobile phones, contact centers, etc.). Along with this, it is expected that, from the point of view of the socio-economic impact of the project on Kazakhstan, the project will undoubtedly contribute to the development of the Kazakh language, one of the key areas of the Kazakhstan-2050 Strategy, and it will also promote research in the field of speech processing and natural language, as well as artificial intelligence both in Kazakhstan and in the world.

Project goal: to perform a fundamental study of nano-to-microscale thermal transport in phase-transformed gallium oxide interface thermal nanostructures engineered by high-precision ion-beam engineering to reach predictive understanding of thermal transport performance in future power electronics and thermoelectric systems.

Project description: The need for new interface thermal nanomaterials based on ultrawide bandgap semiconductors is in high demand in advanced power electronics as well as in thermoelectrics. Spatially selective ion implantation is proposed to manipulate thermal transport in Ga2O3 crystals via novel ion-induced transformation from β- to γ-crystalline phase. Radiation-induced phase-transformed Ga2O3 structures as well as nano-patterned periodic superlattices with regularly shaped interfaces will be fabricated to tailor thermal interfaces across γ- and β-phases. Heat propagation in these novel thermal nanomaterials will be investigated by advanced laser-based thermoreflectance techniques with nano- to micro-meter depth resolution in conjunction with multi-scale heat conduction modeling

Project facilitators: Azat Abdullayev (Leading researcher), Kairolla Sekerbayev (Senior researcher), Lyazzat Mukhangaliyeva (Junior Researcher), Rustem Tlegenov (Junior Researcher).

Realisation period: 2023-2025

Expected results: The obtained results of the project are planned to be published in leading international peer-reviewed journals of editorial offices such as Elsevier, AIP Publishing, APS Physics etc.
- at least 2 (two) articles and (or) reviews in peer-reviewed scientific publications in the scientific direction of the project, indexed in the Science Citation Index Expanded of the Web of Science database and (or) having a CiteScore percentile in the Scopus database of at least 35 (thirty-five);
- or at least 1 (one) article or review in a peer-reviewed scientific publication in the scientific direction of the project, indexed in the Science Citation Index Expanded of the Web of Science database and (or) having a CiteScore percentile in the Scopus database of at least 35 (thirty-five), and at least 1 (one) patent included in the database Derwent Innovations Index data (Web of Science, Clarivate Analytics);
- at least 1 (one) article or review in a peer-reviewed foreign or domestic publication recommended by the CQAES;
- or at least 1 (one) article or review in a peer-reviewed scientific publication indexed in the Science Citation Index Expanded and included in the 1st (first) quartile by impact factor in the Web of Science database;

Methodology: In this project, we will fabricate γ-phase Ga2O3 films and nano-structures by irradiating β-phase Ga2O3 wafers with ion beams having energies over keV – MeV range. Moreover, we will test the fabrication of periodic heterostructures (superlattices) consisting of γ- and β- phases to manipulate heat conduction. Importantly, by applying several irradiation regimes such as atomic, cluster, and sequential ion implantation, we intend to investigate the role of the γ/β interface quality on interface thermal conductance. The irradiation recipes will be constantly tailored by thermal propagation measurement and structural characterization techniques such as XRD, RBS-C and TEM. The core part of the work is in the advanced laser-based thermoreflectance measurements of thermal transport in the fabricated structures. We will non-destructively probe the depth-resolved thermal transport data on micro- to nanometer scale using time-domain thermoreflectance (TDTR) and modulated thermoreflectance (MTR) setups. Measured results will be used to validate multiscale modeling ranging from molecular dynamics to semi-analytical Klemens-Callaway continuum model of phonon-mediated heat transport in irradiated Ga2O3 structures.

Contacts: Azat Abdullayev, azat.abdullaev@nu.edu.kz, +77472723929

Assessment and development of technology for NAPL displacement from fractured media: experiments and modeling

Project goal: The main goal is to develop effective and environmentally friendly soil remediation technologies specifically designed for low-permeability fractured sites contaminated by non-aqueous phase liquids (NAPLs). The project aims to enhance remediation performance in accordance with Kazakhstan's Environmental Code standards.
Project description: The project involves creating and testing novel complex fluids, such as colloidal gas aphrons (CGAs) and polymer solutions, to enhance the removal of NAPLs from fractured geological media. Experimental studies at various scales, along with advanced numerical modeling, will provide insights into fluid behavior, ultimately supporting the design of scalable remediation methods.

Project facilitators: PI - Dr. Sagyn Omirbekov (Senior Researcher, NLA), Dr. Yerlan Amanbek (Nazarbayev University), Dr. Timur Merembayev (International Information Technology University), Dr. Bakbergen Bekbau (KMG Engineering LLP), Adil Baigadilov (BRGM, France), Ali Sipullayev (Research Assistant, NLA), Dana Sapobekova (Research Assistant, NLA)

Project partners: International Collaborators: Dr. Stéfan Colombano (BRGM, France), Dr. Maxime Cochennec (BRGM, France)

Realisation period: 2023-2025

Expected results: - Development of new eco-friendly fluids for the remediation of NAPL-contaminated fractured media.
- Reduction of residual saturation of contaminants to comply with Environmental Code standards.
- Advanced numerical models to predict fluid behavior in fractured geological formations.
- Scientific dissemination through high-quality journal publications and international conferences.

Methodology: The methodology consists of four interconnected work packages:
1. Literature review on colloidal systems, polymers, and surfactants.
2. Fluid characterization, including laboratory formation and testing of CGAs and polymers.
3. Multiscale experimental studies encompassing capillary tube flow tests, core-flood experiments, and two-dimensional tank tests.
4. Numerical modeling using UTCHEM, Eclipse 100, and tNavigator to simulate fluid flow dynamics and validate experimental outcomes.

Contacts: Sagyn Omirbekov, sagyn.omirbekov@nu.edu.kz, +7 701 301 77 22

Ion beam surface engineering control of thermal energy transport across wide bandgap semiconductor - metal interfaces

Project goal: The goal of this project is to investigate the use of ion-beam induced surface modification to enhance interfacial thermal transport across metal-WBGS interfaces. We will employ a combination of advanced experimental and computational techniques to study the effect of ion-beam surface engineering to aim for enhanced interfacial thermal conductance.

Project description: Power electronics is pivotal for efficient and reliable systems, especially in Kazakhstan's growing energy sector heavily reliant on fossil fuels. Integrating WBGS (SiC, GaN, Ga2O3 and AlN) in power electronics offers higher efficiency, reducing costs and enhancing grid stability. This project explores the potential of ion-beam enabled surface engineering for subsequent enhancement of interfacial thermal transport across WBGS-metal contact interfaces. Utilizing TDTR nanoscale thermal transport measuring technique and NEMD heat transport simulations, we aim to deepen understanding and contribute to the development of more efficient and reliable power electronics

Project facilitators: PI - Kairolla Sekerbayev (Senior Researcher), Abdullayev Azat (Leading Researcher), Rustem Tlegenov (Junior Researcher), Lyazzat Mukhangaliyeva (Junior Researcher)

Realisation period: 2024-2026

Expected results: Two articles and (or) reviews in peer-reviewed scientific publications indexed in the Science Citation Index Expanded and included in the 1st (first) and (or) 2nd (second) quartile by impact factor in the Web of Science database and (or) having a CiteScore percentile in the Scopus database of at least 70 (seventy) will be submitted

Methodology: Wide bandgap semiconductors (β-Ga₂O₃, GaN, SiC, and AlN) will be irradiated with ions at keV energies using a high-energy accelerator. Structural characterization of the treated WBGS surfaces will be performed using grazing incidence X-ray diffraction (GIXRD) and atomic force microscopy (AFM). The structural properties of the metal film deposited on the pre-treated WBGS surfaces will be studied using various advanced techniques: RBS-C, cross-sectional SEM, and FIB-HRTEM. Surface modification, PDOS, and ITC will be simulated using molecular dynamics (MD) to evaluate a wide range of WBGS materials and irradiation parameters

Contacts: Kairolla Sekerbayev, kairolla.sekerbayev@nu.edu.kz, +77773822382