Egor Lakomkin

Computer Science · Physical Sciences

8h-index225citations41works9.12yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(25), Speech and Audio Processing(15), Natural Language Processing Techniques(14), Music and Audio Processing(11), Topic Modeling(10)

Publications40 total

Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech
2025· 2 cited
Efficient Streaming LLM for Speech Recognition
2025
M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses
2025
Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens
2025· 1 cited
Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens
arXiv (Cornell University)·2024Open Access
Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech
arXiv (Cornell University)·2024Open Access
Efficient Streaming LLM for Speech Recognition
arXiv (Cornell University)·2024Open Access
M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses
arXiv (Cornell University)·2024Open Access
End-to-End Speech Recognition Contextualization with Large Language Models
2024· 14 cited
Prompting Large Language Models with Speech Recognition Abilities
2024· 77 cited
AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs
2024· 15 citedOpen Access
AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs
arXiv (Cornell University)·2023Open Access
End-to-End Speech Recognition Contextualization with Large Language Models
arXiv (Cornell University)·2023Open Access
Prompting Large Language Models with Speech Recognition Abilities
arXiv (Cornell University)·2023· 2 citedOpen Access
SynthVSR: Scaling Up Visual Speech RecognitionWith Synthetic Supervision
2023· 16 cited
Egocentric Audio-Visual Noise Suppression
2023· 3 cited
SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision
arXiv (Cornell University)·2023· 3 citedOpen Access
Egocentric Audio-Visual Noise Suppression
arXiv (Cornell University)·2022Open Access
Being Greedy Does Not Hurt: Sampling Strategies for End-To-End Speech Recognition
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)·2022
Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition
2020Open Access
page 1 of 2Next →

Frequent Co-authors

Stefan Wermter(17), Cornelius Weber(16), Ozlem Kalinli(12), Sven Magg(11), Junteng Jia(10), Jay Mahadeokar(10), Christian Fuegen(10), Yassir Fathullah(6), Chunyang Wu(6), Mohammad Ali Zamani(6), Yuan Shangguan(4), Mike Seltzer(4), Ruiming Xie(4), Niko Moritz(4), Chunyang Wu(4), Ju Lin(4), Yashesh Gaur(4), Gil Keren(4), Jahn Heymann(3), Ke Li(2)