Related papers: Neural approaches to spoken content embedding

Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity. However, prior works have shown that modelling A2W…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against…

Embedding words in a vector space has gained a lot of attention in recent years. While state-of-the-art methods provide efficient computation of word similarities via a low-dimensional matrix embedding, their motivation is often left…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…

Textual entailment is a fundamental task in natural language processing. It refers to the directional relation between text fragments such that the "premise" can infer "hypothesis". In recent years deep learning methods have achieved great…

Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic…

Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution. By studying word evolution, we can infer social trends and language constructs over different periods of…

Distributed language representation has become the most widely used technique for language representation in various natural language processing tasks. Most of the natural language processing models that are based on deep learning…

Modern ASR systems are typically trained on large-scale pseudo-labeled, in-the-wild data spanning multiple domains. While such heterogeneous data benefit generalist models designed for broad deployment, they pose challenges for specialist…

Conventional word embeddings represent words with fixed vectors, which are usually trained based on co-occurrence patterns among words. In doing so, however, the power of such representations is limited, where the same word might be…

Search behaviour is characterised using synonymy and polysemy as users often want to search information based on meaning. Semantic representation strategies represent a move towards richer associative connections that can adequately capture…

Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest…

We investigate unsupervised models that can map a variable-duration speech segment to a fixed-dimensional representation. In settings where unlabelled speech is the only available resource, such acoustic word embeddings can form the basis…

Word embedding (WE) techniques are advanced textual semantic representation models oriented from the natural language processing (NLP) area. Inspired by their effectiveness in facilitating various NLP tasks, more and more researchers…

Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured…

A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…