Picture for Kyuwoong Hwang

Kyuwoong Hwang

Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer

Add code
Aug 31, 2023
Viaarxiv icon

SubSpectral Normalization for Neural Audio Data Processing

Add code
Mar 25, 2021
Figure 1 for SubSpectral Normalization for Neural Audio Data Processing
Figure 2 for SubSpectral Normalization for Neural Audio Data Processing
Figure 3 for SubSpectral Normalization for Neural Audio Data Processing
Figure 4 for SubSpectral Normalization for Neural Audio Data Processing
Viaarxiv icon

Query-by-example on-device keyword spotting

Add code
Oct 22, 2019
Figure 1 for Query-by-example on-device keyword spotting
Figure 2 for Query-by-example on-device keyword spotting
Figure 3 for Query-by-example on-device keyword spotting
Figure 4 for Query-by-example on-device keyword spotting
Viaarxiv icon

Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning

Add code
Oct 14, 2019
Figure 1 for Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning
Figure 2 for Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning
Figure 3 for Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning
Figure 4 for Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning
Viaarxiv icon

Acoustic Scene Classification Based on a Large-margin Factorized CNN

Add code
Oct 14, 2019
Figure 1 for Acoustic Scene Classification Based on a Large-margin Factorized CNN
Figure 2 for Acoustic Scene Classification Based on a Large-margin Factorized CNN
Figure 3 for Acoustic Scene Classification Based on a Large-margin Factorized CNN
Figure 4 for Acoustic Scene Classification Based on a Large-margin Factorized CNN
Viaarxiv icon

Orthogonality Constrained Multi-Head Attention For Keyword Spotting

Add code
Oct 10, 2019
Figure 1 for Orthogonality Constrained Multi-Head Attention For Keyword Spotting
Figure 2 for Orthogonality Constrained Multi-Head Attention For Keyword Spotting
Figure 3 for Orthogonality Constrained Multi-Head Attention For Keyword Spotting
Figure 4 for Orthogonality Constrained Multi-Head Attention For Keyword Spotting
Viaarxiv icon

An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network

Add code
Aug 06, 2019
Figure 1 for An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network
Figure 2 for An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network
Figure 3 for An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network
Figure 4 for An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network
Viaarxiv icon