Alert button
Picture for Hugo Van hamme

Hugo Van hamme

Alert button

Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition

Oct 27, 2022
Steven Vander Eeckt, Hugo Van hamme

Figure 1 for Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition
Figure 2 for Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition
Viaarxiv icon

Weak-Supervised Dysarthria-invariant Features for Spoken Language Understanding using an FHVAE and Adversarial Training

Oct 24, 2022
Jinzi Qi, Hugo Van hamme

Figure 1 for Weak-Supervised Dysarthria-invariant Features for Spoken Language Understanding using an FHVAE and Adversarial Training
Figure 2 for Weak-Supervised Dysarthria-invariant Features for Spoken Language Understanding using an FHVAE and Adversarial Training
Figure 3 for Weak-Supervised Dysarthria-invariant Features for Spoken Language Understanding using an FHVAE and Adversarial Training
Viaarxiv icon

Multi-Source Transformer Architectures for Audiovisual Scene Classification

Oct 18, 2022
Wim Boes, Hugo Van hamme

Figure 1 for Multi-Source Transformer Architectures for Audiovisual Scene Classification
Figure 2 for Multi-Source Transformer Architectures for Audiovisual Scene Classification
Viaarxiv icon

Optimizing Temporal Resolution Of Convolutional Recurrent Neural Networks For Sound Event Detection

Oct 18, 2022
Wim Boes, Hugo Van hamme

Figure 1 for Optimizing Temporal Resolution Of Convolutional Recurrent Neural Networks For Sound Event Detection
Figure 2 for Optimizing Temporal Resolution Of Convolutional Recurrent Neural Networks For Sound Event Detection
Viaarxiv icon

Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition

Oct 14, 2022
Jakob Poncelet, Hugo Van hamme

Figure 1 for Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition
Figure 2 for Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition
Figure 3 for Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition
Figure 4 for Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition
Viaarxiv icon

Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications

Oct 01, 2022
Bastiaan Tamm, Helena Balabin, Rik Vandenberghe, Hugo Van hamme

Figure 1 for Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications
Figure 2 for Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications
Figure 3 for Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications
Figure 4 for Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications
Viaarxiv icon

Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection

Sep 27, 2022
Wim Boes, Hugo Van hamme

Figure 1 for Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection
Figure 2 for Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection
Figure 3 for Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection
Figure 4 for Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection
Viaarxiv icon

Multi-encoder attention-based architectures for sound recognition with partial visual assistance

Sep 26, 2022
Wim Boes, Hugo Van hamme

Figure 1 for Multi-encoder attention-based architectures for sound recognition with partial visual assistance
Figure 2 for Multi-encoder attention-based architectures for sound recognition with partial visual assistance
Figure 3 for Multi-encoder attention-based architectures for sound recognition with partial visual assistance
Figure 4 for Multi-encoder attention-based architectures for sound recognition with partial visual assistance
Viaarxiv icon

Relating the fundamental frequency of speech with EEG using a dilated convolutional network

Jul 05, 2022
Corentin Puffay, Jana Van Canneyt, Jonas Vanthornhout, Hugo Van hamme, Tom Francart

Figure 1 for Relating the fundamental frequency of speech with EEG using a dilated convolutional network
Figure 2 for Relating the fundamental frequency of speech with EEG using a dilated convolutional network
Figure 3 for Relating the fundamental frequency of speech with EEG using a dilated convolutional network
Figure 4 for Relating the fundamental frequency of speech with EEG using a dilated convolutional network
Viaarxiv icon

Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders

Jul 01, 2022
Lies Bollens, Tom Francart, Hugo Van hamme

Figure 1 for Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders
Figure 2 for Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders
Figure 3 for Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders
Viaarxiv icon