Related papers: JEPA as a Neural Tokenizer: Learning Robust Speech…

Audio representation learning based on deep neural networks (DNNs) emerged as an alternative approach to hand-crafted features. For achieving high performance, DNNs often need a large amount of annotated data which can be difficult and…

The adoption of advanced deep learning (DL) architecture in stuttering detection (SD) tasks is challenging due to the limited size of the available datasets. To this end, this work introduces the application of speech embeddings extracted…

Recently, autoregressive models have demonstrated remarkable performance in class-conditional image generation. However, the application of next-token prediction to high-resolution text-to-image generation remains largely unexplored. In…

Self-Supervised Learning (SSL) has shifted from pixel-level reconstruction to latent space prediction, spearheaded by the Joint Embedding Predictive Architecture (JEPA). While effective, standard JEPA models typically rely on a…

We evaluate JEPA-style predictive representation learning versus reconstruction-based autoencoders on a controlled "TV-series" linear dynamical system with known latent state and a single noise parameter. While an initial comparison…

The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. On the other…

We propose Text-Aligned Speech Tokens with Multiple Layer-Aggregation (TASLA), which is a text-aligned speech tokenization framework that aims to address the problem that under a low-frame-rate and text-aligned regime, single-source speech…

Recently, self-supervised representation learning relying on vast amounts of unlabeled data has been explored as a pre-training method for autonomous driving. However, directly applying popular contrastive or generative methods to this…

Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological learners require. An alternative paradigm has emerged in which…

Joint-Embedding Predictive Architecture (JEPA) is increasingly used for visual representation learning and as a component in model-based RL, but its behavior remains poorly understood. We provide a theoretical characterization of a simple,…

Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positions, feature…

The adoption of advanced deep learning architectures in stuttering detection (SD) tasks is challenging due to the limited size of the available datasets. To this end, this work introduces the application of speech embeddings extracted from…

Reconstructing the speech audio envelope from scalp neural recordings (EEG) is a central task for decoding a listener's attentional focus in applications like neuro-steered hearing aids. Current methods for this reconstruction, however,…

Current approaches to memory in neural systems rely on similarity-based retrieval: given a query, find the most representationally similar stored state. This assumption -- that useful memories are similar memories -- fails to capture a…

The joint-embedding predictive architecture (JEPA) recently has shown impressive results in extracting visual representations from unlabeled imagery under a masking strategy. However, we reveal its disadvantages, notably its insufficient…

Accurately modeling and controlling vehicle exhaust emissions during transient events, such as rapid acceleration, is critical for meeting environmental regulations and optimizing powertrains. Conventional data-driven methods, such as…

Voice disorders negatively impact the quality of daily life in various ways. However, accurately recognizing the category of pathological features from raw audio remains a considerable challenge due to the limited dataset. A promising…

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented…

Deep learning techniques have considerably improved speech processing in recent years. Speaker representations extracted by deep learning models are being used in a wide range of tasks such as speaker recognition and speech emotion…

Deep learning enabled semantic communications are attracting extensive attention. However, most works normally ignore the data acquisition process and suffer from robustness issues under dynamic channel environment. In this paper, we…