3 citations · 5 across the 4 of their papers we have counts for
4 papers
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…
UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model
Anastasiia Iashchenko, Pavel Andreev, Ivan Shchekotov +2
This paper introduces UnDiff, a diffusion probabilistic model capable of solving various speech inverse tasks. Being once trained for speech waveform generation in an unconditional…
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…