activity
20202026
most citedDynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition

12 citations · 17 across the 3 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.SD2026

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…