Related papers: Learning Speaker Representations with Mutual Infor…

The fast increase of web services and mobile apps, which collect personal data from users, increases the risk that their privacy may be severely compromised. In particular, the increasing variety of spoken language interfaces and voice…

Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven…

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…

Multimodal representation learning poses significant challenges in capturing informative and distinct features from multiple modalities. Existing methods often struggle to exploit the unique characteristics of each modality due to unified…

Understanding internal representations of neural models is a core interest of mechanistic interpretability. Due to its large dimensionality, the representation space can encode various aspects about inputs. To what extent are different…

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose…

Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data…

Online Class-Incremental continual Learning (OCIL) addresses the challenge of continuously learning from a single-channel data stream, adapting to new tasks while mitigating catastrophic forgetting. Recently, Mutual Information (MI)-based…

Model inversion (MI) attacks allow to reconstruct average per-class representations of a machine learning (ML) model's training data. It has been shown that in scenarios where each class corresponds to a different individual, such as face…

We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data. In particular, we face the case where some attributes (bias) of the data, if learned by the model, can severely…

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Lately there have been novel developments in deep learning towards solving the cocktail party problem. Initial results are very promising and allow for more research in the domain. One technique that has not yet been explored in the neural…

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore models that are capable of combining the attributes of multiple inputs such that a resynthesised…

This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert…

We propose a method named AudioFormer,which learns audio feature representations through the acquisition of discrete acoustic codes and subsequently fine-tunes them for audio classification tasks. Initially,we introduce a novel perspective…

Self-supervised representation learning maps high-dimensional data into a meaningful embedding space, where samples of similar semantic contents are close to each other. Most of the recent representation learning methods maximize cosine…

We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, we propose a novel data-driven way to model the distance…

The key challenge in unaligned multimodal language sequences lies in effectively integrating information from various modalities to obtain a refined multimodal joint representation. Recently, the disentangle and fuse methods have achieved…

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…

In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker model without additional training on the target speaker's…