Enhancing Transformer for End-to-end Speech-to-Text Translation

54 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Fairseq S2T: Fast Speech-to-Text Modeling with Fairseq (2020, methodology): “Compared with previous Transformer-based approaches (Di Gangi et al., 2019b; Inaguma et al., 2020), our bilingual models achieve comparative results to the state of the art without applying additional techniques such as speed perturbation and pre-trained decoder from MT.”
Speech Translation and the End-to-End Promise: Taking Stock of Where We Are (2020, background): “…of the latter approach, so follow-up work concentrates on compiling ST corpora from available web sources (Godard et al., 2018; Kocabiyikoglu et al., 2018; Sanabria et al., 2018; di Gangi et al., 2019a; Boito et al., 2020; Beilharz et al., 2020; Iranzo-Sánchez et al., 2020; Wang et al., 2020a).”
A Comparative Study on End-to-End Speech to Text Translation (2019, methodology): “Here, we focus on LSTM-based models rather than the transformer [14, 17, 25].”
FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN (2020, methodology): “…LibriSpeech ASR corpus (Panayotov et al., 2015), • Mozilla Common Voice,22 • Speech-Translation TED corpus.23 For English→Czech Translation: • MuST-C (Di Gangi et al., 2019a), release 1.1 contains English-Czech pair, • CzEng 1.7 (Bojar et al., 2016).24 Note that CzEng overlaps with…”