Publications

Export 12 results:
Author Title Type [ Year(Desc)]
Filters: Author is K.W. Cheuk  [Clear All Filters]
2018
Cheuk K.W., BT B, Roig G., Herremans D..  2018.  Blacklisted speaker identification using triplet neural networks. MCE2018 competition. PDF icon SUTD_description.pdf (133.08 KB)
2019
Cheuk K.W., BT B, Roig G., Herremans D..  2019.  Latent space representation for multi-target speaker detection and identification with a sparse dataset using Triplet neural networks. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2019). PDF icon 1910.01463.pdf (934.76 KB)
Cheuk K.W., Agres K., Herremans D..  2019.  nnAudio: A PyTorch Audio Processing Tool Using 1D Convolution neural networks. ISMIR - Late Breaking Demo. PDF icon nnAudio.pdf (399.08 KB)
2020
Cheuk K.W., Agres K., Herremans D..  2020.  The impact of Audio input representations on neural network based music transcription. Proceedings of the International Joint Conference on Neural Networks (IJCNN). PDF icon 2001.09989.pdf (1.87 MB)
Cheuk K.W., Anderson H., Agres K., Herremans D..  2020.  nnAudio: An on-the-fly GPU Audio to Spectrogram Conversion Toolbox Using 1D Convolution Neural Networks. IEEE Access. PDF icon nnAudio.pdf (10.2 MB)
Cheuk K.W., Luo Y.J., BT B, Roig G., Herremans D..  2020.  Regression-based music emotion prediction using triplet neural networks. Proceedings of the International Joint Conference on Neural Networks (IJCNN). PDF icon 2001.09988.pdf (777.31 KB)
Luo Y.J., Cheuk K.W., Nakano T., Goto M., Herremans D..  2020.  Unsupervised disentanglement of pitch and timbre for isolated musical instrument sounds. Proceedings of the International Society of Music Information Retrieval (ISMIR).
2021
Cheuk K.W., Luo Y.J., Benetos E., Herremans D..  2021.  The Effect of Spectrogram Reconstructions on Automatic Music Transcription:An Alternative Approach to Improve Transcription Accuracy. Proceedings of the International Conference on Pattern Recognition (ICPR2020). PDF icon 2010.09969.pdf (3.46 MB)
Cheuk K.W., Su L., Herremans D..  2021.  ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data. ACM Multimedia.
Cheuk K.W., Luo Y.J., Benetos E., Herremans D..  2021.  Revisiting the Onsets and Frames Model with Additive Attention. Proceedings of the International Joint Conference on Neural Networks (IJCNN). PDF icon 2104.06607.pdf (1.52 MB)
2022
Cheuk K.W., Choi K., Kong Q., Li B., Won M., Hung A., Wang J.-C., Herremans D..  2022.  Jointist: Joint Learning for Multi-instrument Transcription and Its Applications. PDF icon 2206.10805.pdf (427.51 KB)
Kwan Y.H., Cheuk K.W., Herremans D..  2022.  Understanding Audio Features via Trainable Basis Functions. Arxiv preprint. PDF icon 2204.11437.pdf (7.36 MB)