43 citations · 69 across the 6 of their papers we have counts for
6 papers
Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech
Vadim Popov, Wenju Gu, Tasnima Sadekova +2
Continuous diffusion for categorical data is a framework belonging to the diffusion family and aiming at generating discrete data. The scientific interest to such models has been c…
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders
Georgii Aparin, Vadim Popov, Tasnima Sadekova +1
Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input. We invest…
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders
Georgii Aparin, Tasnima Sadekova, Alexey Rukhovich +5
Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whis…
Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss
Artem Khrapov, Vadim Popov, Tasnima Sadekova +2
Diffusion models are known to be vulnerable to outliers in training data. In this paper we study an alternative diffusion loss function, which can preserve the high quality of gene…
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
Vadim Popov, Ivan Vovk, Vladimir Gogoryan +3
Voice conversion is a common speech synthesis task which can be solved in different ways depending on a particular real-world scenario. The most challenging one often referred to a…
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Vadim Popov, Ivan Vovk, Vladimir Gogoryan +2
Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has pro…