Related papers: Can Latent Alignments Improve Autoregressive Machi…

Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work…

Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to…

Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition. Most recent approaches have attempted to solve this problem by implicitly…

Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in…

Recently, end-to-end models have been widely used in automatic speech recognition (ASR) systems. Two of the most representative approaches are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models.…

Non-autoregressive (NAR) neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model. Under this framework, we leverage large monolingual corpora to improve the NAR model's performance, with the…

Non-autoregressive (NAR) transformer models have achieved significantly inference speedup but at the cost of inferior accuracy compared to autoregressive (AR) models in automatic speech recognition (ASR). Most of the NAR transformers take a…

Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local…

The attentional mechanism has proven to be effective in improving end-to-end neural machine translation. However, due to the intricate structural divergence between natural languages, unidirectional attention-based models might only capture…

In recent years, Neural Machine Translation (NMT) has achieved notable results in various translation tasks. However, the word-by-word generation manner determined by the autoregressive mechanism leads to high translation latency of the NMT…

Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of conventional models. Connectionist temporal classification…

Imposing constraints on machine translation systems presents a challenging issue because these systems are not trained to make use of constraints in generating adequate, fluent translations. In this paper, we leverage the capabilities of…

Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently,…

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…

Neural encoder-decoder models of machine translation have achieved impressive results, rivalling traditional translation models. However their modelling formulation is overly simplistic, and omits several key inductive biases built into…

Speech-to-text alignment is a critical component of neural textto-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line. However, these alignments tend to be brittle and often…

Fully non-autoregressive neural machine translation (NAT) is proposed to simultaneously predict tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the…

Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framework of NAR models necessitates conditional independence…

Combining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation and low latency. In this paper, we investigate the potential…