Related papers: Deep word embeddings for visual speech recognition
Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…
Grounding language in vision is an active field of research seeking to construct cognitively plausible word and sentence representations by incorporating perceptual knowledge from vision into text-based representations. Despite many…
With the rise of low power speech-enabled devices, there is a growing demand to quickly produce models for recognizing arbitrary sets of keywords. As with many machine learning tasks, one of the most challenging parts in the model creation…
Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…
Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like…
Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video…
Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is…
We present a clustering-based language model using word embeddings for text readability prediction. Presumably, an Euclidean semantic space hypothesis holds true for word embeddings whose training is done by observing word co-occurrences.…
We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four types of visual co-occurrences between object and attribute…
Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existence of similar information on vector representations of…
This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms the embedding space of pretrained vision models into the…
We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-existing vocabulary.…
In this paper we propose the application of feature hashing to create word embeddings for natural language processing. Feature hashing has been used successfully to create document vectors in related tasks like document classification. In…
Embeddings play a pivotal role in the efficacy of Large Language Models. They are the bedrock on which these models grasp contextual relationships and foster a more nuanced understanding of language and consequently perform remarkably on a…
Traditional visual speech recognition systems consist of two stages, feature extraction and classification. Recently, several deep learning approaches have been presented which automatically extract features from the mouth images and aim to…
Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it…
In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…
Understanding human language has been a sub-challenge on the way of intelligent machines. The study of meaning in natural language processing (NLP) relies on the distributional hypothesis where language elements get meaning from the words…
Ambiguity is ubiquitous in natural language. Resolving ambiguous meanings is especially important in information retrieval tasks. While word embeddings carry semantic information, they fail to handle ambiguity well. Transformer models have…