Tatiana Likhomanenko

tata-antares's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 14 papers about 2 months ago

Stabilizing Transformer Training by Preventing Attention Entropy Collapse

Paper • 2303.06296 • Published Mar 11, 2023 • 1

Libri-Light: A Benchmark for ASR with Limited or No Supervision

Paper • 1912.07875 • Published Dec 17, 2019

Self-training and Pre-training are Complementary for Speech Recognition

Paper • 2010.11430 • Published Oct 22, 2020

Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training

Paper • 2104.01027 • Published Apr 2, 2021 • 1

How to Scale Your EMA

Paper • 2307.13813 • Published Jul 25, 2023 • 9

Pseudo-Labeling for Massively Multilingual Speech Recognition

Paper • 2111.00161 • Published Oct 30, 2021

Position Prediction as an Effective Pretraining Strategy

Paper • 2207.07611 • Published Jul 15, 2022 • 1

Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition

Paper • 2405.15216 • Published May 24, 2024 • 16

dMel: Speech Tokenization made Simple

Paper • 2407.15835 • Published Jul 22, 2024

Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?

Paper • 2402.00340 • Published Feb 1, 2024 • 2

Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models

Paper • 2409.10788 • Published Sep 16, 2024

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers and Gradient Clipping

Paper • 2310.00098 • Published Sep 29, 2023

VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON

Paper • 2306.07890 • Published Jun 13, 2023

Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition

Paper • 2507.05724 • Published Jul 8 • 1

authored a paper about 1 year ago

Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Paper • 2409.04431 • Published Sep 6, 2024 • 2