Related papers: Variational Information Bottleneck for Effective L…
The proliferation of large language models (LLMs) has significantly advanced intelligent systems. Unfortunately, LLMs often face knowledge conflicts between internal memory and retrieved external information, arising from misinformation,…
We tackle a common domain adaptation setting in causal systems. In this setting, the target variable is observed in the source domain but is entirely missing in the target domain. We aim to impute the target variable in the target domain…
As Deep Neural Networks (DNNs) are considered the state-of-the-art in many classification tasks, the question of their semantic generalizations has been raised. To address semantic interpretability of learned features, we introduce a novel…
Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…
Information Bottleneck (IB) is a generalization of rate-distortion theory that naturally incorporates compression and relevance trade-offs for learning. Though the original IB has been extensively studied, there has not been much…
Reverberant speech, denoting the speech signal degraded by reverberation, contains crucial knowledge of both anechoic source speech and room impulse response (RIR). This work proposes a variational Bayesian inference (VBI) framework with…
Graph neural networks (GNNs) excel on relational data by passing messages over node features and structure, but they can amplify training data biases, propagating discriminatory attributes and structural imbalances into unfair outcomes.…
Deep learning models are nowadays broadly deployed to solve an incredibly large variety of tasks. Commonly, leveraging over the availability of "big data", deep neural networks are trained as black-boxes, minimizing an objective function at…
The current paradigm of large-scale pre-training and fine-tuning Transformer large language models has lead to significant improvements across the board in natural language processing. However, such large models are susceptible to…
This paper explores the use of multi-view features and their discriminative transforms in a convolutional deep neural network (CNN) architecture for a continuous large vocabulary speech recognition task. Mel-filterbank energies and…
Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with large losses, which…
The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\mathbf{t}$ by striking a trade-off…
The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address…
Deep neural networks (DNNs) have achieved remarkable success across diverse domains, but their performance can be severely degraded by noisy or corrupted training data. Conventional noise mitigation methods often rely on explicit…
Deep neural networks (DNNs) provide high image classification accuracy, but experience significant performance degradation when perturbation from various sources are present in the input. The lack of resilience to input perturbations makes…
There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker…
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…
Acoustic scene classification is an intricate problem for a machine. As an emerging field of research, deep Convolutional Neural Networks (CNN) achieve convincing results. In this paper, we explore the use of multi-scale Dense connected…
The muti-layer information bottleneck (IB) problem, where information is propagated (or successively refined) from layer to layer, is considered. Based on information forwarded by the preceding layer, each stage of the network is required…
Deep learning approaches are still not very common in the speaker verification field. We investigate the possibility of using deep residual convolutional neural network with spectrograms as an input features in the text-dependent speaker…