Related papers: Does Joint Training Really Help Cascaded Speech Tr…
This paper describes the cascaded multimodal speech translation systems developed by Imperial College London for the IWSLT 2019 evaluation campaign. The architecture consists of an automatic speech recognition (ASR) system followed by a…
Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech…
This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to build a single multilingual translation system with a…
Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation…
Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and…
When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…
Speech Translation (ST) is a machine translation task that involves converting speech signals from one language to the corresponding text in another language; this task has two different approaches, namely the traditional cascade and the…
Many existing speech translation benchmarks focus on native-English speech in high-quality recording conditions, which often do not match the conditions in real-life use-cases. In this paper, we describe our speech translation system for…
When a channel model is available, learning how to communicate on fading noisy channels can be formulated as the (unsupervised) training of an autoencoder consisting of the cascade of encoder, channel, and decoder. An important limitation…
There has been a growing interest in using end-to-end acoustic models for singing voice synthesis (SVS). Typically, these models require an additional vocoder to transform the generated acoustic features into the final waveform. However,…
Speech-to-Text Translation (S2TT) systems built from Automatic Speech Recognition (ASR) and Text-to-Text Translation (T2TT) modules face two major limitations: error propagation and the inability to exploit prosodic or other acoustic cues.…
This paper presents a plug-and-play approach for translation with terminology constraints. Terminology constraints are an important aspect of many modern translation pipelines. In both specialized domains and newly emerging domains (such as…
The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches. However, on the closely related task of word alignment, traditional…
An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Recently, iterative back-translation…
Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation model along with an auxiliary text to text translation task.…
Recent advances in automatic quality estimation for machine translation have exclusively focused on written language, leaving the speech modality underexplored. In this work, we formulate the task of quality estimation for speech…
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…
Direct speech translation (ST) has shown to be a complex task requiring knowledge transfer from its sub-tasks: automatic speech recognition (ASR) and machine translation (MT). For MT, one of the most promising techniques to transfer…
End-to-end speech-to-text translation can provide a simpler and smaller system but is facing the challenge of data scarcity. Pre-training methods can leverage unlabeled data and have been shown to be effective on data-scarce settings. In…
Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of…