Related papers: Towards unsupervised phone and word segmentation u…

In settings where only unlabelled speech data is available, zero-resource speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. There are two central problems in…

Recently, the concept of unsupervised learning for superpixel segmentation via CNNs has been studied. Essentially, such methods generate superpixels by convolutional neural network (CNN) employed on a single image, and such CNNs are trained…

Most previous approaches to Chinese word segmentation can be roughly classified into character-based and word-based methods. The former regards this task as a sequence-labeling problem, while the latter directly segments character sequence…

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping…

This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization. Unlike the previous approaches that rely on word embeddings, our method learns embeddings of small text regions from…

In order to leverage and profit from unlabelled data, semi-supervised frameworks for semantic segmentation based on consistency training have been proven to be powerful tools to significantly improve the performance of purely supervised…

Word segmentation stands as a cornerstone of Natural Language Processing (NLP). Based on the concept of "comprehend first, segment later", we propose a new framework to explore the limit of unsupervised word segmentation with Large Language…

We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no action labels are known during training. Despite its simplicity,…

This work proposes a multichannel speech separation method with narrow-band Conformer (named NBC). The network is trained to learn to automatically exploit narrow-band speech separation information, such as spatial vector clustering of…

We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing…

Along with the breakthrough of convolutional neural networks, learning-based segmentation has emerged in many research works. Most of them are based on supervised learning, requiring plenty of annotated data; however, to support…

Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the modeling depth, and source and target vocabularies, which in…

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…

Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in…

Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively…

The visual understanding are often approached from 3 granular levels: image, patch and pixel. Visual Tokenization, trained by self-supervised reconstructive learning, compresses visual data by codebook in patch-level with marginal…

Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the…

Semantic segmentation is a crucial step in many Earth observation tasks. Large quantity of pixel-level annotation is required to train deep networks for semantic segmentation. Earth observation techniques are applied to varieties of…

In the majority of the existing Visual Question Answering (VQA) research, the answers consist of short, often single words, as per instructions given to the annotators during dataset construction. This study envisions a VQA task for natural…

Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training. To address the above problem, we consider an efficient…