Scholar
Kirill Borodin
Google Scholar ID: ptyhLVQAAAAJ
MTUCI
deep learning for audio
gen AI
safe AI
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
11
H-index
1
i10-index
1
Publications
5
Co-authors
3
list available
Publications
16 items
Balalaika-Longform: A Russian Speech Corpus for Continuous Long-Form Text-to-Speech
2026
Cited
0
Collapse, Not Invariance: Diagnosing Auxiliary Objectives in Speech Anti-Spoofing
2026
Cited
0
ProxyMOS: Label-Free Speech Quality Assessment by Multi-Teacher Distillation with Adaptive Routing
2026
Cited
0
ReDimNet2+: Multi-Corpus Data Scaling for Robust Speaker Verification
2026
Cited
0
Repetition, Not Length: Isolating the Counting Failure in Neural Text-to-Speech
2026
Cited
0
RAWD-TTS: Ratio-Free Reward Alignment for Discrete-Diffusion Voice Cloning
2026
Cited
0
Think Shallow, Solve Deep: Controlling Recurrent Dynamics for Reliable Test-Time Depth
2026
Cited
0
The Null Token Knows: Reducing Message-Free Hallucination in ASR and NMT
2026
Cited
0
Load more
Co-authors
3 total
Vasiliy Kudryavtsev
MTUCI
Oleg Y. Rogov
University of Sharjah, MTUCI
Dmitrii Korzh
MTUCI
