1 citations · 3 across the 12 of their papers we have counts for
19 papers · 1 filter
Sharp Bounds on the Winner's Bias under Independent and Nonnegatively Correlated Noise
Ivan Viakhirev, Kirill Borodin, Grach Mkrtchian
Reporting the best of noisy, unbiased scores overstates the winner's value by up to , where is the total noise variance and the sharp constant depends on how…
Agreement rather than normalisation keeps depth reusable in looped language models
Ivan Viakhirev, Kirill Borodin, Maxim Abramov +1
Looped language models apply one block of layers repeatedly, and the design pays off only if depth is reusable: loop steps beyond the trained budget must remain usable at inference…
Measuring the Verifier's Floor: How Much Apparent Rare-Word Text-to-Speech Error Is ASR Error?
Kirill Borodin, Vasilii Kudryavtsev, Nikita Vasiliev +1
Text-to-speech (TTS) is usually evaluated by transcribing its output with an automatic speech recognition (ASR) system, so the word error rate also counts recognizer errors. We mea…
Text-Only LLM Correctors Break Correct Transcripts: A Repair-Damage Analysis of Audio Grounding in ASR Error Correction
Vasiliy Kudryavtsev, Kirill Borodin, Nikita Vasiliev +2
LLM correctors of ASR output are judged by aggregate WER, which hides what they fix and what they break. We decompose every WER change exactly into repaired tokens, damaged tokens…
Balalaika-Longform: A Russian Speech Corpus for Continuous Long-Form Text-to-Speech
Nikita Vasiliev, Kirill Borodin, Vasilii Kudryavtsev +2
Long-form text-to-speech must retain requested words over extended generations, yet sentence-level training and evaluation can hide omissions and early stops. We introduce Balalaik…
Collapse, Not Invariance: Diagnosing Auxiliary Objectives in Speech Anti-Spoofing
Ksenia Lysikova, Kirill Borodin, Maxim Maslov +1
Speech anti-spoofing countermeasures degrade when the generator, codec or channel changes, and a common remedy is an auxiliary objective that shapes the embedding space; whether it…
ProxyMOS: Label-Free Speech Quality Assessment by Multi-Teacher Distillation with Adaptive Routing
Maxim Trokunov, Kirill Borodin, Nikita Vasiliev +1
Human mean opinion scores (MOS) are costly to collect, and non-intrusive MOS predictors degrade sharply outside their training domain. ProxyMOS turns a pool of public MOS predictor…
RAWD-TTS: Ratio-Free Reward Alignment for Discrete-Diffusion Voice Cloning
Maxim Maslov, Kirill Borodin, Vasilii Kudryavtsev +2
Zero-shot text-to-speech synthesizes new utterances in a speaker's voice from a short reference recording. Voice cloning requires accurate content and preserved speaker identity, b…
ReDimNet2+: Multi-Corpus Data Scaling for Robust Speaker Verification
Kirill Borodin, Vasilii Kudryavtsev, Maxim Maslov +1
Automatic speaker verification must remain reliable across devices, rooms, and compression pipelines. We present ReDimNet2+, which scales training of the compact ReDimNet2 backbone…
Repetition, Not Length: Isolating the Counting Failure in Neural Text-to-Speech
Kirill Borodin, Vasilii Kudryavtsev, Maxim Maslov +1
Text-to-speech models loop, truncate and lose count on text that repeats a phrase many times. We show that repetition itself is what breaks them, not the length that comes with it.…
Think Shallow, Solve Deep: Controlling Recurrent Dynamics for Reliable Test-Time Depth
Ivan Viakhirev, Kirill Borodin, Amirah Almutairi +3
Recurrent-depth reasoners aim to solve harder problems by iterating their update longer at test time, but additional iterations can improve, preserve, or degrade an answer. We show…
The Null Token Knows: Reducing Message-Free Hallucination in ASR and NMT
Kirill Borodin, Vasiliy Kudryavtsev, Ivan Viakhirev +1
Modern encoder-decoder systems can produce fluent text even when their input contains no recoverable message. We study this failure in ASR and NMT through the models' reserved null…
Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative
Ksenia Lysikova, Kirill Borodin, Grach Mkrtchian
RuASD (Russian AntiSpoofing Dataset) is a dedicated, reproducible benchmark for Russian-language speech anti-spoofing designed to evaluate both in-domain discrimination and robustn…
From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales
Ivan Viakhirev, Kirill Borodin, Grach Mkrtchian
Hallucinations in large ASR models present a critical safety risk. In this work, we propose the \textit{Spectral Sensitivity Theorem}, which predicts a phase transition in deep net…
Combining Masked Language Modeling and Cross-Modal Contrastive Learning for Prosody-Aware TTS
Kirill Borodin, Vasiliy Kudryavtsev, Maxim Maslov +3
Text encoders in neural text-to-speech (TTS) see only linguistic content, so prosody must be inferred from paired data and synthesised intonation is often flat. Contrastive text-au…
Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision
Kirill Borodin, Kirill Kondrashov, Nikita Vasiliev +4
CCTV safety monitoring demands anomaly detectors combine reliable clip-level accuracy with predictable per-clip latency despite weak supervision. This work investigates compact vis…
When Spoof Detectors Travel: Evaluation Across 66 Languages in the Low-Resource Language Spoofing Corpus
Kirill Borodin, Vasiliy Kudryavtsev, Maxim Maslov +2
We introduce LRLspoof, a large-scale multilingual synthetic-speech corpus for cross-lingual spoof detection, comprising 2,732 hours of audio generated with 24 open-source TTS syste…
From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification
Vasiliy Kudryavtsev, Kirill Borodin, German Berezin +3
Automated animal identification is a practical task for reuniting lost pets with their owners, yet current systems often struggle due to limited dataset scale and reliance on unimo…
Interpreting Multi-Branch Anti-Spoofing Architectures: Correlating Internal Strategy with Empirical Performance
Ivan Viakhirev, Kirill Borodin, Mikhail Gorodnichev +1
Multi-branch deep neural networks like AASIST3 achieve state-of-the-art comparable performance in audio anti-spoofing, yet their internal decision dynamics remain opaque compared t…