Picture for Ju-ho Kim

Ju-ho Kim

MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms

Add code
Jun 11, 2024
Figure 1 for MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms
Figure 2 for MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms
Figure 3 for MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms
Figure 4 for MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms
Viaarxiv icon

HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods

Add code
Sep 15, 2023
Viaarxiv icon

Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models

Add code
Sep 14, 2023
Viaarxiv icon

PAS: Partial Additive Speech Data Augmentation Method for Noise Robust Speaker Verification

Add code
Jul 20, 2023
Figure 1 for PAS: Partial Additive Speech Data Augmentation Method for Noise Robust Speaker Verification
Figure 2 for PAS: Partial Additive Speech Data Augmentation Method for Noise Robust Speaker Verification
Figure 3 for PAS: Partial Additive Speech Data Augmentation Method for Noise Robust Speaker Verification
Viaarxiv icon

One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification

Add code
Jun 08, 2023
Figure 1 for One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification
Figure 2 for One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification
Figure 3 for One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification
Figure 4 for One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification
Viaarxiv icon

Integrated Parameter-Efficient Tuning for General-Purpose Audio Models

Add code
Nov 04, 2022
Viaarxiv icon

Convolution channel separation and frequency sub-bands aggregation for music genre classification

Add code
Nov 03, 2022
Figure 1 for Convolution channel separation and frequency sub-bands aggregation for music genre classification
Figure 2 for Convolution channel separation and frequency sub-bands aggregation for music genre classification
Figure 3 for Convolution channel separation and frequency sub-bands aggregation for music genre classification
Figure 4 for Convolution channel separation and frequency sub-bands aggregation for music genre classification
Viaarxiv icon

Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector

Add code
Jun 28, 2022
Figure 1 for Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector
Figure 2 for Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector
Figure 3 for Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector
Figure 4 for Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector
Viaarxiv icon

Extended U-Net for Speaker Verification in Noisy Environments

Add code
Jun 27, 2022
Figure 1 for Extended U-Net for Speaker Verification in Noisy Environments
Figure 2 for Extended U-Net for Speaker Verification in Noisy Environments
Figure 3 for Extended U-Net for Speaker Verification in Noisy Environments
Figure 4 for Extended U-Net for Speaker Verification in Noisy Environments
Viaarxiv icon

RawNeXt: Speaker verification system for variable-duration utterances with deep layer aggregation and extended dynamic scaling policies

Add code
Dec 15, 2021
Figure 1 for RawNeXt: Speaker verification system for variable-duration utterances with deep layer aggregation and extended dynamic scaling policies
Figure 2 for RawNeXt: Speaker verification system for variable-duration utterances with deep layer aggregation and extended dynamic scaling policies
Figure 3 for RawNeXt: Speaker verification system for variable-duration utterances with deep layer aggregation and extended dynamic scaling policies
Figure 4 for RawNeXt: Speaker verification system for variable-duration utterances with deep layer aggregation and extended dynamic scaling policies
Viaarxiv icon