3 papers
cs.SD2024
Learning Disentangled Audio Representations through Controlled Synthesis
Yusuf Brima, Ulf Krumnack, Simone Pika +1
This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanat…
eess.AS2023
Learning Disentangled Speech Representations
Yusuf Brima, Ulf Krumnack, Simone Pika +1
Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluati…
cs.SD2023
Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction
Yusuf Brima, Ulf Krumnack, Simone Pika +1
Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statist…