Ghent University Academic Bibliography

Conference Paper
C1
open access

GCT : gated contextual transformer for sequential audio tagging

Yuanbo Hou (UGent) , Yun Wang, Wenwu Wang and Dick Botteldooren (UGent)

(2023) ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Conference Paper
C1
open access

Adaptive axonal delays in feedforward spiking neural networks for accurate spoken word recognition

Pengfei Sun (UGent) , Ehsan Eqlimi (UGent) , Yansong Chua, Paul Devos (UGent) and Dick Botteldooren (UGent)

(2023) ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Add to list

Conference Paper
P1
open access

Tackling the score shift in cross-lingual speaker verification by exploiting language information

Jenthe Thienpondt (UGent) , Brecht Desplanques (UGent) and Kris Demuynck (UGent)

(2022) 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). In International Conference on Acoustics Speech and Signal Processing ICASSP p.7187-7191

Add to list

Gradient variance loss for structure-enhanced image super-resolution

Lusine Abrahamyan, Anh Minh Truong (UGent) , Wilfried Philips (UGent) and Nikos Deligiannis

(2022) ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). In International Conference on Acoustics Speech and Signal Processing ICASSP p.3219-3223

Add to list

Conference Paper
P1
open access

A differentiable optimisation framework for the design of individualised DNN-based hearing-aid strategies

Fotios Drakopoulos (UGent) and Sarah Verhulst (UGent)

(2022) ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). In International Conference on Acoustics Speech and Signal Processing ICASSP p.351-355

Add to list

Conference Paper
P1
open access

Axonal delay as a short-term memory for feed forward deep spiking neural networks

Pengfei Sun (UGent) , Longwei Zhu and Dick Botteldooren (UGent)

(2022) ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing p.8932-8936

Add to list

Conference Paper
P1
open access

Rule-embedded network for audio-visual voice activity detection in live musical video streams

Yuanbo Hou (UGent) , Yi Deng, Bilei Zhu, Zejun Ma and Dick Botteldooren (UGent)

(2021) ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing p.4165-4169

Add to list

Conference Paper
P1
open access

The Idlab voxsrc-20 submission : large margin fine-tuning and quality-aware score calibration in DNN based speaker verification

Jenthe Thienpondt (UGent) , Brecht Desplanques (UGent) and Kris Demuynck (UGent)

(2021) ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing p.5814-5818

Add to list

Conference Paper
P1
open access

Learning perception and planning with deep active inference

Ozan Catal (UGent) , Tim Verbelen (UGent) , Johannes Nauta (UGent) , Cedric De Boom (UGent) and Bart Dhoedt (UGent)

(2020) ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). In International Conference on Acoustics Speech and Signal Processing ICASSP p.3952-3956

Add to list

Conference Paper
P1
open access

Least squares DOA estimation with an informed phase unwrapping and full bandwidth robustness

Alexander Bohlender (UGent) , A. Spriet, W. Tirry and Nilesh Madhu (UGent)

(2020) ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). In International Conference on Acoustics Speech and Signal Processing ICASSP p.4841-4845

Academic Bibliography

GCT : gated contextual transformer for sequential audio tagging

Adaptive axonal delays in feedforward spiking neural networks for accurate spoken word recognition

Tackling the score shift in cross-lingual speaker verification by exploiting language information

Gradient variance loss for structure-enhanced image super-resolution

A differentiable optimisation framework for the design of individualised DNN-based hearing-aid strategies

Axonal delay as a short-term memory for feed forward deep spiking neural networks

Rule-embedded network for audio-visual voice activity detection in live musical video streams

The Idlab voxsrc-20 submission : large margin fine-tuning and quality-aware score calibration in DNN based speaker verification

Learning perception and planning with deep active inference

Least squares DOA estimation with an informed phase unwrapping and full bandwidth robustness

Contents

Support

Contact