Related papers: Helping the Weak Makes You Strong: Simple Multi-Ta…

This article describes an efficient end-to-end speech translation (E2E-ST) framework based on non-autoregressive (NAR) models. End-to-end speech translation models have several advantages over traditional cascade systems such as inference…

Multilingual understanding models (or encoder-based), pre-trained via masked language modeling, have achieved promising results on many language understanding tasks (e.g., mBERT). However, these non-autoregressive (NAR) models still…

Non-autoregressive (NAR) transformer models have been studied intensively in automatic speech recognition (ASR), and a substantial part of NAR transformer models is to use the casual mask to limit token dependencies. However, the casual…

Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common…

Research on multilingual speech recognition remains attractive yet challenging. Recent studies focus on learning shared structures under the multi-task paradigm, in particular a feature sharing structure. This approach has been found…

Many language pairs are low resource, meaning the amount and/or quality of available parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have…

We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task,…

Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a…

Automatic speech recognition (ASR) systems often rely on autoregressive (AR) Transformer decoder architectures, which limit efficient inference parallelization due to their sequential nature. To this end, non-autoregressive (NAR) approaches…

Continual learning (CL) over non-stationary data streams remains one of the long-standing challenges in deep neural networks (DNNs) as they are prone to catastrophic forgetting. CL models can benefit from self-supervised pre-training as it…

Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training. Target-side monolingual data plays an important role in boosting fluency for phrase-based…

How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent…

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We…

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem. Recently, the structure of directed acyclic graph has achieved great success in NAT, which tackles…

Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…

Existing approaches to neural machine translation condition each output word on previously generated outputs. We introduce a model that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude…

While Autoregressive (AR) Transformer-based Generative Language Models are frequently employed for lookahead tasks, recent research suggests a potential discrepancy in their ability to perform planning tasks that require multi-step…

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…

Human beings can leverage knowledge from relative tasks to improve learning on a primary task. Similarly, multi-task learning methods suggest using auxiliary tasks to enhance a neural network's performance on a specific primary task.…

Structured prediction tasks, like machine translation, involve learning functions that map structured inputs to structured outputs. Recurrent Neural Networks (RNNs) have historically been a popular choice for such tasks, including in…