Related papers: A Simple HMM with Self-Supervised Representations …

Unsupervised localization and segmentation are long-standing computer vision challenges that involve decomposing an image into semantically-meaningful segments without any labeled data. These tasks are particularly interesting in an…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…

Masked Image Modeling (MIM) has emerged as a promising approach for Self-Supervised Learning (SSL) of visual representations. However, the out-of-the-box performance of MIMs is typically inferior to competing approaches. Most users cannot…

Despite the superior performance of Deep Learning (DL) on numerous segmentation tasks, the DL-based approaches are notoriously overconfident about their prediction with highly polarized label probability. This is often not desirable for…

Most network-based speech recognition methods are based on the assumption that the labels of two adjacent speech samples in the network are likely to be the same. However, assuming the pairwise relationship between speech samples is not…

Generative Spoken Language Modeling research focuses on optimizing speech Language Models (LMs) using raw audio recordings without accessing any textual supervision. Such speech LMs usually operate over discrete units obtained from…

Predicting masked from visible parts of an image is a powerful self-supervised approach for visual representation learning. However, the common practice of masking random patches of pixels exhibits certain failure modes, which can prevent…

The paper studies optimal coding of hidden Markov sources (HMS), which represent a broad class of practical sources obtained through noisy acquisition processes, beside their explicit modeling use in speech processing and recognition, image…

This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages. Our approach may be described by the following two steps procedure:…

Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…

Variation in speech is often quantified by comparing phonetic transcriptions of the same utterance. However, manually transcribing speech is time-consuming and error prone. As an alternative, therefore, we investigate the extraction of…

Automatic skin lesion segmentation on dermoscopic images is an essential component in computer-aided diagnosis of melanoma. Recently, many fully supervised deep learning based methods have been proposed for automatic skin lesion…

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…

Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which…

Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation,…

Self-supervised models have revolutionized speech processing, achieving new levels of performance in a wide variety of tasks with limited resources. However, the inner workings of these models are still opaque. In this paper, we aim to…

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

Semi-supervised learning (SSL) is a promising machine learning paradigm to address the issue of label scarcity in medical imaging. SSL methods were originally developed in image classification. The state-of-the-art SSL methods in image…