I am a senior applied scientist at Nvidia NeMo team and a PhD student at ITMO University (computer science). I am interested in Automatic Speech Recognition, Digital Signal Processing, and Natural Language Processing. My current research area is End-to-End ASR systems.
Senior Applied Scientist, Nvidia Armenia LLC
Oct, 2022 - Present
Developing of Automatic Speech Recognition (ASR) systems for NeMo toolkit.
Transferring conversational technology to NVIDIA's software product teams, specifically to NVIDIA Riva.
Assisting internal teams and customers with applying the developed conversational technology
Research Scientist, STC Ltd
Jun, 2017 - Sep, 20225 years 3 months
Research state-of-the-art ASR architectures and techniques.
Design, develop and test hybrid ASR models for different languages.
Extended research and development of End-to-End ASR systems (CTC, RNN-T, and Attention Encoder-Decoder).
Prize-winning places in international competitions: VOICES 2019, CHiME-6 2020.
Article publications in scientific journals and conferences (INTERSPEECH, SENSORS, SPECOM).
Automatic Speech Recognition (ASR)
Research and Development (R&D)
Academic writing
Digital Signal Processing (DSP)
Natural Language Processing (NLP)
Machine Learning (ML)
Pytorch
NeMo
Espnet
Kaldi
Computer Science, Doctor of Philosophy - PhD, ITMO University
Dec, 2019 - Sep, 2023
Computer Systems Networking and Telecommunications, Master's degree, Peter the Great St.Petersburg Polytechnic University
Dec, 2016 - Dec, 2018
Computer Systems Networking and Telecommunications, Bachelor's degree, Peter the Great St.Petersburg Polytechnic University
Dec, 2012 - Dec, 2016
High Reduction of Input Sequence Length for End-to-End Speech Recognition , ICASSP 2023
Published on: May 05, 2023
Improving out of vocabulary words recognition accuracy for an end-to-end Russian speech recognition system , Scientific and Technical Journal of Information Technologies, Mechanics and Optics
Published on: Dec 12, 2022
LT-LM: A Novel Non-Autoregressive Language Model for Single-Shot Lattice Rescoring , Proc. Interspeech 2021
Published on: Aug 30, 2021
Dynamic Acoustic Unit Augmentation with BPE-Dropout for Low-Resource End-to-End Speech Recognition , MDPI Sensors
Published on: Apr 28, 2021
You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation , IEEE Xplore
Published on: Nov 25, 2020
Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription , Proc. Interspeech 2020
Published on: Oct 26, 2020
Target-Speaker Voice Activity Detection: A Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario , Proc. Interspeech 2020
Published on: Oct 25, 2020
Exploration of End-to-End ASR for OpenSTT – Russian Open Speech-to-Text Dataset , Lecture Notes in Computer Science book series (LNCS, volume 12335)
Published on: Sep 29, 2020