Alert button
Picture for Hugo Van hamme

Hugo Van hamme

Alert button

Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding

Jun 28, 2022
Pu Wang, Hugo Van hamme

Figure 1 for Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding
Figure 2 for Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding
Figure 3 for Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding
Figure 4 for Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding
Viaarxiv icon

Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition

Mar 30, 2022
Steven Vander Eeckt, Hugo Van hamme

Figure 1 for Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition
Figure 2 for Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition
Figure 3 for Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition
Figure 4 for Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition
Viaarxiv icon

Continual Learning for Monolingual End-to-End Automatic Speech Recognition

Dec 17, 2021
Steven Vander Eeckt, Hugo Van hamme

Figure 1 for Continual Learning for Monolingual End-to-End Automatic Speech Recognition
Figure 2 for Continual Learning for Monolingual End-to-End Automatic Speech Recognition
Figure 3 for Continual Learning for Monolingual End-to-End Automatic Speech Recognition
Viaarxiv icon

A Multi-Resolution Front-End for End-to-End Speech Anti-Spoofing

Oct 11, 2021
Wei Liu, Meng Sun, Xiongwei Zhang, Hugo Van hamme, Thomas Fang Zheng

Figure 1 for A Multi-Resolution Front-End for End-to-End Speech Anti-Spoofing
Figure 2 for A Multi-Resolution Front-End for End-to-End Speech Anti-Spoofing
Figure 3 for A Multi-Resolution Front-End for End-to-End Speech Anti-Spoofing
Figure 4 for A Multi-Resolution Front-End for End-to-End Speech Anti-Spoofing
Viaarxiv icon

Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch

Sep 29, 2021
Jakob Poncelet, Hugo Van hamme

Figure 1 for Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch
Figure 2 for Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch
Figure 3 for Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch
Figure 4 for Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch
Viaarxiv icon

On the long-term learning ability of LSTM LMs

Jun 16, 2021
Wim Boes, Robbe Van Rompaey, Lyan Verwimp, Joris Pelemans, Hugo Van hamme, Patrick Wambacq

Figure 1 for On the long-term learning ability of LSTM LMs
Figure 2 for On the long-term learning ability of LSTM LMs
Figure 3 for On the long-term learning ability of LSTM LMs
Figure 4 for On the long-term learning ability of LSTM LMs
Viaarxiv icon

A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech

Jun 15, 2021
Pu Wang, Bagher BabaAli, Hugo Van hamme

Figure 1 for A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech
Figure 2 for A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech
Figure 3 for A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech
Figure 4 for A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech
Viaarxiv icon

Speech Disorder Classification Using Extended Factorized Hierarchical Variational Auto-encoders

Jun 14, 2021
Jinzi Qi, Hugo Van hamme

Figure 1 for Speech Disorder Classification Using Extended Factorized Hierarchical Variational Auto-encoders
Figure 2 for Speech Disorder Classification Using Extended Factorized Hierarchical Variational Auto-encoders
Figure 3 for Speech Disorder Classification Using Extended Factorized Hierarchical Variational Auto-encoders
Viaarxiv icon

Audiovisual transfer learning for audio tagging and sound event detection

Jun 09, 2021
Wim Boes, Hugo Van hamme

Figure 1 for Audiovisual transfer learning for audio tagging and sound event detection
Figure 2 for Audiovisual transfer learning for audio tagging and sound event detection
Figure 3 for Audiovisual transfer learning for audio tagging and sound event detection
Figure 4 for Audiovisual transfer learning for audio tagging and sound event detection
Viaarxiv icon

Predicting speech intelligibility from EEG using a dilated convolutional network

May 19, 2021
Bernd Accou, Mohammad Jalilpour Monesi, Hugo Van hamme, Tom Francart

Figure 1 for Predicting speech intelligibility from EEG using a dilated convolutional network
Figure 2 for Predicting speech intelligibility from EEG using a dilated convolutional network
Figure 3 for Predicting speech intelligibility from EEG using a dilated convolutional network
Figure 4 for Predicting speech intelligibility from EEG using a dilated convolutional network
Viaarxiv icon