8 accepted papers
We investigate the label noise problem in supervised binary classification settings and resurface the underutilized instance-_only_ dependent noise model through loss correction. On the one hand, based on risk equivalence, the instance-aware loss correction scheme completes the bridge from _empirica…
Learning joint representations across multiple modalities remains a central challenge in multimodal machine learning. Prevailing approaches predominantly operate in pairwise settings, aligning two modalities at a time. While some recent methods aim to capture higher-order interactions among multiple
Multimodal learning holds the promise for richer information extraction by capturing dependencies across data sources. Yet, current training methods often underperform due to modality competition, a phenomenon where modalities contend for training resources, leaving some underoptimized. This raises…
In this paper, we describe the epilepsy detection grand challenge, in association with ICASSP 2023. The challenge was centered on seizure detection using wearable behind-the-ear EEG. Two separate tasks were set for the participants: 1) obtain the best overall performance in seizure detection; 2) sys…
We propose a regularization method, so-called temporal smoothness regularization, for training deep neural networks for automatic sleep staging in small data settings. In intuition, we constrain the cross-entropy losses of any two adjacent epochs in the sequential input to be as close to each other…
Multi-source datasets often present the challenge of source-wise missing data which can render large portions of the dataset inaccessible. The applicability of traditional missing data techniques on multi-source datasets is poorly understood. We present the first quantitative evaluation of the state…
We propose a multi-label multi-task framework based on a convolutional recurrent neural network to unify detection of isolated and overlapping audio events. The framework leverages the power of convolutional recurrent neural network architectures; convolutional layers learn effective features over w…
To decode auditory attention from electroencephalography (EEG) recordings in a cocktail-party scenario with two competing speakers a least-squares method has recently been proposed, showing a promising decoding accuracy. This method however requires the clean speech signals of both the attended and…