Tatiana Likhomanenko
17 papers · 2019–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (27) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Triple Crown
ποΈ
Keyword Collector
(70)
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(12)
Speech & Audio
(9)
Learning Types Β· Machine Learning
(9)
Deep Learning
(8)
Recognition
(7)
Application Areas
(5)
Architectures
(5)
Natural Language Processing
(3)
Learning Types Β· Deep Learning
(3)
Applications
(2)
Core Methods
(2)
Optimization & Theory
(2)
Techniques
(2)
Artificial Intelligence
(1)
Computer Science
(1)
Keywords
automatic speech recognition
(5)
self-supervised learning
(5)
semi-supervised learning
(4)
machine translation
(3)
representation learning
(2)
domain generalization
(2)
word error rate
(2)
connectionist temporal classification
(2)
language model
(2)
data augmentation
(2)
multilingual nlp
(1)
knowledge distillation
(1)
domain adaptation
(1)
neural network optimization
(1)
attention mechanism
(1)
deep learning
(1)
speech transcription
(1)
model robustness
(1)
speech recognition
(1)
curriculum learning
(1)
Papers
DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective
Interspeech 2025
Theory, Analysis, and Best Practices for Sigmoid Self-Attention
ICLR 2025
Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
Interspeech 2024
Generating Gender Alternatives in Machine Translation
ACL 2024
Continuous pseudo-labeling from the start
ICLR 2023
How to Scale Your EMA
NeurIPS 2023
Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
ACL 2023
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
ICML 2023
Flashlight: Enabling Innovation in Tools for Machine Learning
ICML 2022
Position Prediction as an Effective Pretraining Strategy
ICML 2022
CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings
NeurIPS 2021
Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Interspeech 2021
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Interspeech 2021
slimIPL: Language-Model-Free Iterative Pseudo-Labeling
Interspeech 2021
Iterative Pseudo-Labeling for Speech Recognition
Interspeech 2020
Scaling Up Online Speech Recognition Using ConvNets
Interspeech 2020
Who Needs Words? Lexicon-Free Speech Recognition
Interspeech 2019