Picture for Eungbeom Kim

Eungbeom Kim

Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation

Add code
Jun 12, 2024
Viaarxiv icon

Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test

Add code
May 22, 2023
Figure 1 for Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test
Figure 2 for Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test
Figure 3 for Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test
Viaarxiv icon

Improving Audio-Language Learning with MixGen and Multi-Level Test-Time Augmentation

Add code
Oct 31, 2022
Figure 1 for Improving Audio-Language Learning with MixGen and Multi-Level Test-Time Augmentation
Figure 2 for Improving Audio-Language Learning with MixGen and Multi-Level Test-Time Augmentation
Figure 3 for Improving Audio-Language Learning with MixGen and Multi-Level Test-Time Augmentation
Figure 4 for Improving Audio-Language Learning with MixGen and Multi-Level Test-Time Augmentation
Viaarxiv icon

Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification

Add code
Apr 06, 2022
Figure 1 for Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
Figure 2 for Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
Figure 3 for Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
Figure 4 for Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
Viaarxiv icon