Related papers: Re-translation versus Streaming for Simultaneous T…

Transformer models using segment-based processing have been an effective architecture for simultaneous speech translation. However, such models create a context mismatch between training and inference environments, hindering potential…

Neural machine translation systems require large amounts of training data and resources. Even with this, the quality of the translations may be insufficient for some users or domains. In such cases, the output of the system must be revised…

We propose iteratively prompting a large language model to self-correct a translation, with inspiration from their strong language understanding and translation capability as well as a human-like translation approach. Interestingly,…

Automated machine learning techniques benefited from tremendous research progress in recently. These developments and the continuous-growing demand for machine learning experts led to the development of numerous AutoML tools. However, these…

Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context. However, there is a counterintuitive phenomenon about the context usage between training and…

Machine Translation (MT) has achieved remarkable performance, with growing interest in speech translation and multimodal approaches. However, despite these advancements, MT quality assessment remains largely text centric, typically relying…

Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for…

A common use of machine translation in the industry is providing initial translation hypotheses, which are later supervised and post-edited by a human expert. During this revision process, new bilingual data are continuously generated.…

Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed…

Transferring knowledge across many streaming processes remains an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the target domain, covariate shift of source and target domain,…

A large number of machine translation approaches have recently been developed to facilitate the fluid migration of content across languages. However, the literature suggests that many obstacles must still be dealt with to achieve better…

The black-box nature of end-to-end speech translation (E2E ST) systems makes it difficult to understand how source language inputs are being mapped to the target language. To solve this problem, we would like to simultaneously generate…

Multi-source translation systems translate from multiple languages to a single target language. By using information from these multiple sources, these systems achieve large gains in accuracy. To train these systems, it is necessary to have…

Streaming speech-to-text translation (StreamST) is the task of automatically translating speech while incrementally receiving an audio stream. Unlike simultaneous ST (SimulST), which deals with pre-segmented speech, StreamST faces the…

Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. We therefore conduct…

We study the application of active learning techniques to the translation of unbounded data streams via interactive neural machine translation. The main idea is to select, from an unbounded stream of source sentences, those worth to be…

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…

The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS systems, typically trained and inferenced on complete…

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that…