Sequence-to-sequence models can directly translate foreign speech

RJ Weiss, J Chorowski, N Jaitly, Y Wu… - arXiv preprint arXiv …, 2017 - arxiv.org
We present a recurrent encoder-decoder deep neural network architecture that directly
translates speech in one language into text in another. The model does not explicitly …

Must-c: A multilingual corpus for end-to-end speech translation

R Cattoni, MA Di Gangi, L Bentivogli, M Negri… - Computer speech & …, 2021 - Elsevier
End-to-end spoken language translation (SLT) has recently gained popularity thanks to the
advancement of sequence to sequence learning in its two parent tasks: automatic speech …

Direct speech-to-speech translation with a sequence-to-sequence model

Y Jia, RJ Weiss, F Biadsy, W Macherey… - arXiv preprint arXiv …, 2019 - arxiv.org
We present an attention-based sequence-to-sequence neural network which can directly
translate speech from one language into speech in another language, without relying on an …

Speech translation and the end-to-end promise: Taking stock of where we are

M Sperber, M Paulik - arXiv preprint arXiv:2004.06358, 2020 - arxiv.org
Over its three decade history, speech translation has experienced several shifts in its
primary research themes; moving from loosely coupled cascades of speech recognition and …

Statistical approaches to computer-assisted translation

S Barrachina, O Bender, F Casacuberta… - Computational …, 2009 - direct.mit.edu
Current machine translation (MT) systems are still not perfect. In practice, the output from
these systems needs to be edited to correct errors. A way of increasing the productivity of the …

Probabilistic finite-state machines-part I

E Vidal, F Thollard, C De La Higuera… - IEEE transactions on …, 2005 - ieeexplore.ieee.org
Probabilistic finite-state machines are used today in a variety of areas in pattern recognition,
or in fields to which pattern recognition is linked: computational linguistics, machine …

Probabilistic finite-state machines-part II

E Vidal, F Thollard, C De La Higuera… - IEEE transactions on …, 2005 - ieeexplore.ieee.org
Probabilistic finite-state machines are used today in a variety of areas in pattern recognition
or in fields to which pattern recognition is linked. In part I of this paper, we surveyed these …

[PDF][PDF] Generalizing word lattice translation

C Dyer, S Muresan, P Resnik - Proceedings of ACL-08: HLT, 2008 - aclanthology.org
Word lattice decoding has proven useful in spoken language translation; we argue that it
provides a compelling model for translation of text genres, as well. We show that prior work …

Neural lattice-to-sequence models for uncertain inputs

M Sperber, G Neubig, J Niehues, A Waibel - arXiv preprint arXiv …, 2017 - arxiv.org
The input to a neural sequence-to-sequence model is often determined by an up-stream
system, eg a word segmenter, part of speech tagger, or speech recognizer. These up-stream …

Toward robust neural machine translation for noisy input sequences

M Sperber, J Niehues, A Waibel - Proceedings of the 14th …, 2017 - aclanthology.org
Translating noisy inputs, such as the output of a speech recognizer, is a difficult but
important challenge for neural machine translation. One way to increase robustness of …