Ngoc T. Vu

TL;DR: The goal with this survey paper is to offer researchers pointers to relevant meta-learning works in NLP and attract more attention from the NLP community to drive future innovation.

TL;DR: This work proposes a speaker anonymization pipeline that leverages high quality automatic speech recognition and synthesis systems to generate speech conditioned on phonetic transcriptions and anonymized speaker embeddings, and outperforms baselines provided in the Voice Privacy Challenge 2020 in terms of privacy robustness against a lazy-informed attacker.

TL;DR: In this article , the authors present a system that extends a speech-totext-to-speech anonymization pipeline with prosody cloning and show how to control the cloning by multiplying pitch and energy sequences with random offset values.

TL;DR: This paper used the AmericasNLI dataset to evaluate the performance of different machine translation models for 10 Indigenous languages of the Americas and found that translation-based approaches outperformed all other models on that task.