1 citations · 3 across the 12 of their papers we have counts for
3 papers · 1 filter
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.…
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…
Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech
Kirill Borodin, Nikita Vasiliev, Vasiliy Kudryavtsev +3
We introduce Balalaika, an open-source, data-centric pipeline for processing audio and producing prosody-aware annotations. It combines semantic VAD for context-preserving segmenta…