68 citations · 95 across the 3 of their papers we have counts for
3 papers
eess.AS2020★ 2 cited
SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation
Arya D. McCarthy, Liezl Puzon, Juan Pino
We propose autoencoding speaker conversion for training data augmentation in automatic speech translation. This technique directly transforms an audio sequence, resulting in audio…
cs.CL2019★ 25 cited
Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade
Juan Pino, Liezl Puzon, Jiatao Gu +3
For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then translate with machi…
cs.CL2019★ 68 cited
Monotonic Multihead Attention
Xutai Ma, Juan Pino, James Cross +2
Simultaneous machine translation models start generating a target sequence before they have encoded or read the source sequence. Recent approaches for this task either apply a fixe…