Picture for Tatiana Likhomanenko

Tatiana Likhomanenko

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

Add code
May 24, 2024
Viaarxiv icon

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

Feb 01, 2024
Viaarxiv icon

AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition

Add code
Sep 29, 2023
Figure 1 for AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition
Figure 2 for AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition
Figure 3 for AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition
Figure 4 for AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition
Viaarxiv icon

Federated Learning with Differential Privacy for End-to-End Speech Recognition

Sep 29, 2023
Viaarxiv icon

Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR

Add code
Sep 22, 2023
Figure 1 for Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR
Figure 2 for Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR
Figure 3 for Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR
Figure 4 for Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR
Viaarxiv icon

How to Scale Your EMA

Jul 27, 2023
Figure 1 for How to Scale Your EMA
Figure 2 for How to Scale Your EMA
Figure 3 for How to Scale Your EMA
Figure 4 for How to Scale Your EMA
Viaarxiv icon

VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON

Add code
Jun 18, 2023
Figure 1 for VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON
Figure 2 for VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON
Figure 3 for VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON
Viaarxiv icon

Unsupervised ASR via Cross-Lingual Pseudo-Labeling

May 19, 2023
Figure 1 for Unsupervised ASR via Cross-Lingual Pseudo-Labeling
Figure 2 for Unsupervised ASR via Cross-Lingual Pseudo-Labeling
Figure 3 for Unsupervised ASR via Cross-Lingual Pseudo-Labeling
Figure 4 for Unsupervised ASR via Cross-Lingual Pseudo-Labeling
Viaarxiv icon

Stabilizing Transformer Training by Preventing Attention Entropy Collapse

Add code
Mar 11, 2023
Figure 1 for Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Figure 2 for Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Figure 3 for Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Figure 4 for Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Viaarxiv icon

Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data

Dec 20, 2022
Figure 1 for Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
Figure 2 for Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
Figure 3 for Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
Figure 4 for Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
Viaarxiv icon