activity
20182026
most citedMultilingual Translation with Extensible Multilingual Pretraining and Finetuning

153 citations · 358 across the 17 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.CL2021★ 1 cited

Textless Speech-to-Speech Translation on Real Data

Ann Lee, Hongyu Gong, Paul-Ambroise Duquenne +8

We present a textless speech-to-speech translation (S2ST) system that can translate speech from one language into another language and can be built without the need of any text dat…

cs.CL2021

Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention

Xutai Ma, Hongyu Gong, Danni Liu +6

We present a direct simultaneous speech-to-speech translation (Simul-S2ST) model, Furthermore, the generation of translation is independent from intermediate text representations.…

eess.AS2021★ 4 cited

fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit

Changhan Wang, Wei-Ning Hsu, Yossi Adi +5

This paper presents fairseq S^2, a fairseq extension for speech synthesis. We implement a number of autoregressive (AR) and non-AR text-to-speech models, and their multi-speaker va…

cs.CL2021

PermuteFormer: Efficient Relative Position Encoding for Long Sequences

Peng Chen

A recent variation of Transformer, Performer, scales Transformer to longer sequences with a linear attention mechanism. However, it is not compatible with relative position encodin…

cs.CL2021

Direct speech-to-speech translation with discrete units

Ann Lee, Peng-Jen Chen, Changhan Wang +9

We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation…

cs.CL2021★ 82 cited

The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

Naman Goyal, Cynthia Gao, Vishrav Chaudhary +7

One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current evaluation benchmarks eithe…