6 citations · 6 across the 2 of their papers we have counts for
3 papers · 1 filter
Flow Matching-Based Speech Source Separation with Best-of-N Biometric Sampling
Anastasia Zorkina, Alexandr Anikin, Nikita Khmelev +5
Single-channel speech separation remains challenging for real-world deployment due to source permutation ambiguity, sampling variability of generative models, and the difficulty of…
Exploring End-to-End Techniques for Low-Resource Speech Recognition
Vladimir Bataev, Maxim Korenevsky, Ivan Medennikov +1
In this work we present simple grapheme-based system for low-resource speech recognition using Babel data for Turkish spontaneous speech (80 hours). We have investigated different…
Investigation of Using VAE for i-Vector Speaker Verification
Timur Pekhovsky, Maxim Korenevsky
New system for i-vector speaker recognition based on variational autoencoder (VAE) is investigated. VAE is a promising approach for developing accurate deep nonlinear generative mo…