Related papers: Towards Learning a Universal Non-Semantic Represen…

We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings…

This paper presents a novel semantic-based phrase translation model. A pair of source and target phrases are projected into continuous-valued vector representations in a low-dimensional latent semantic space, where their translation score…

Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates…

Transfer learning aims to faciliate learning tasks in a label-scarce target domain by leveraging knowledge from a related source domain with plenty of labeled data. Often times we may have multiple domains with little or no labeled data as…

We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…

We propose a novel transfer learning method for speech emotion recognition allowing us to obtain promising results when only few training data is available. With as low as 125 examples per emotion class, we were able to reach a higher…

The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces…

Obtaining large, human labelled speech datasets to train models for emotion recognition is a notoriously challenging task, hindered by annotation cost and label ambiguity. In this work, we consider the task of learning embeddings for speech…

Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has…

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific levels of linguistic units. This work introduces universal language representation learning, i.e.,…

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Emotion and intent recognition from speech is essential and has been widely investigated in human-computer interaction. The rapid development of social media platforms, chatbots, and other technologies has led to a large volume of speech…

We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks. Sentence-level…

Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task. The main aim of theoretical guarantees on the subject is…

We develop and investigate several cross-lingual alignment approaches for neural sentence embedding models, such as the supervised inference classifier, InferSent, and sequential encoder-decoder models. We evaluate three alignment…

Learning with a limited number of labeled data is a central problem in real-world applications of machine learning, as it is often expensive to obtain annotations. To deal with the scarcity of labeled data, transfer learning is a…

A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning…

Textless speech-to-speech translation systems are rapidly advancing, thanks to the integration of self-supervised learning techniques. However, existing state-of-the-art systems fall short when it comes to capturing and transferring…

We aim to understand the value of additional labeled or unlabeled target data in transfer learning, for any given amount of source data; this is motivated by practical questions around minimizing sampling costs, whereby, target data is…