3 citations · 5 across the 4 of their papers we have counts for
5 papers
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Team Kandinsky, Julia Agafonova, Bulat Akhmatov +85
We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-audio-video generation, comprising Kandinsky 6.0 Video Lite (3B parameters) and Kan…
KVAE: Family of Tokenizers for Multimodal Generative Models
Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov +11
Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part…
FINALLY: fast and universal speech enhancement with studio-like quality
Nicholas Babaev, Kirill Tamogashev, Azat Saginbaev +6
In this paper, we address the challenge of speech enhancement in real-world recordings, which often contain various forms of distortion, such as background noise, reverberation, an…
Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds
Hanbin Bae, Pavel Andreev, Azat Saginbaev +4
This paper introduces a speech enhancement solution tailored for true wireless stereo (TWS) earbuds on-device usage. The solution was specifically designed to support conversations…
Iterative autoregression: a novel trick to improve your low-latency speech enhancement model
Pavel Andreev, Nicholas Babaev, Azat Saginbaev +2
Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future in…