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 …

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 …

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 …

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 …

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 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 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 …

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 …

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 …

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 …