Related papers: On Target Segmentation for Direct Speech Translati…

Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the modeling depth, and source and target vocabularies, which in…

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or…

Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more detailed information that ultimately could lead to better…

For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to…

Direct speech-to-text translation (ST) models are usually trained on corpora segmented at sentence level, but at inference time they are commonly fed with audio split by a voice activity detector (VAD). Since VAD segmentation is not…

Learning word representations has recently seen much success in computational linguistics. However, assuming sequences of word tokens as input to linguistic analysis is often unjustified. For many languages word segmentation is a…

Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character…

Chinese word segmentation has entered the deep learning era which greatly reduces the hassle of feature engineering. Recently, some researchers attempted to treat it as character-level translation, which further simplified model designing,…

Subword segmenters like BPE operate as a preprocessing step in neural machine translation and other (conditional) language models. They are applied to datasets before training, so translation or text generation quality relies on the quality…

Speech segmentation is an essential part of speech translation (ST) systems in real-world scenarios. Since most ST models are designed to process speech segments, long-form audio must be partitioned into shorter segments before translation.…

The audio segmentation mismatch between training data and those seen at run-time is a major problem in direct speech translation. Indeed, while systems are usually trained on manually segmented corpora, in real use cases they are often…

Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in…

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…

Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language…

Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation. However, both training and working procedures of the current neural models are…

Subwords are the most widely used output units in end-to-end speech recognition. They combine the best of two worlds by modeling the majority of frequent words directly and at the same time allow open vocabulary speech recognition by…

Having recognized gender bias as a major issue affecting current translation technologies, researchers have primarily attempted to mitigate it by working on the data front. However, whether algorithmic aspects concur to exacerbate unwanted…

Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…

Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech translation aiming to summarize the current state-of-the-art…

Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot…