Picture for Kwanghee Choi

Kwanghee Choi

Wav2Gloss: Generating Interlinear Glossed Text from Speech

Add code
Mar 19, 2024
Figure 1 for Wav2Gloss: Generating Interlinear Glossed Text from Speech
Figure 2 for Wav2Gloss: Generating Interlinear Glossed Text from Speech
Figure 3 for Wav2Gloss: Generating Interlinear Glossed Text from Speech
Figure 4 for Wav2Gloss: Generating Interlinear Glossed Text from Speech
Viaarxiv icon

OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer

Add code
Jan 30, 2024
Viaarxiv icon

Understanding Probe Behaviors through Variational Bounds of Mutual Information

Add code
Dec 15, 2023
Viaarxiv icon

Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study

Add code
Sep 27, 2023
Figure 1 for Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
Figure 2 for Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
Figure 3 for Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
Figure 4 for Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
Viaarxiv icon

Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification

Add code
May 28, 2023
Figure 1 for Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification
Figure 2 for Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification
Figure 3 for Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification
Figure 4 for Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification
Viaarxiv icon

Unsupervised Speech Representation Pooling Using Vector Quantization

Add code
Apr 08, 2023
Figure 1 for Unsupervised Speech Representation Pooling Using Vector Quantization
Figure 2 for Unsupervised Speech Representation Pooling Using Vector Quantization
Figure 3 for Unsupervised Speech Representation Pooling Using Vector Quantization
Figure 4 for Unsupervised Speech Representation Pooling Using Vector Quantization
Viaarxiv icon

OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset

Add code
Jan 16, 2023
Figure 1 for OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset
Figure 2 for OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset
Figure 3 for OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset
Figure 4 for OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset
Viaarxiv icon

Data-driven Approach for Automatically Correcting Faulty Road Maps

Add code
Nov 12, 2022
Figure 1 for Data-driven Approach for Automatically Correcting Faulty Road Maps
Figure 2 for Data-driven Approach for Automatically Correcting Faulty Road Maps
Figure 3 for Data-driven Approach for Automatically Correcting Faulty Road Maps
Figure 4 for Data-driven Approach for Automatically Correcting Faulty Road Maps
Viaarxiv icon

Automatic Severity Assessment of Dysarthric speech by using Self-supervised Model with Multi-task Learning

Add code
Oct 27, 2022
Figure 1 for Automatic Severity Assessment of Dysarthric speech by using Self-supervised Model with Multi-task Learning
Figure 2 for Automatic Severity Assessment of Dysarthric speech by using Self-supervised Model with Multi-task Learning
Figure 3 for Automatic Severity Assessment of Dysarthric speech by using Self-supervised Model with Multi-task Learning
Figure 4 for Automatic Severity Assessment of Dysarthric speech by using Self-supervised Model with Multi-task Learning
Viaarxiv icon

Opening the Black Box of wav2vec Feature Encoder

Add code
Oct 27, 2022
Figure 1 for Opening the Black Box of wav2vec Feature Encoder
Figure 2 for Opening the Black Box of wav2vec Feature Encoder
Figure 3 for Opening the Black Box of wav2vec Feature Encoder
Figure 4 for Opening the Black Box of wav2vec Feature Encoder
Viaarxiv icon