Alexei Baevski

On-demand compute reduction with stochastic wav2vec 2.0

Michael Auli, Wei-Ning Hsu, Apoorv Vyas, 2022, INTERSPEECH.

Offline Visual Representation Learning for Embodied Navigation

Dhruv Batra, Vincent-Pierre Berges, Arjun Majumdar, 2022, ArXiv.

Towards End-to-End Unsupervised Speech Recognition

Alexander H. Liu, Michael Auli, Wei-Ning Hsu, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

Michael Auli, Jiatao Gu, Qiantong Xu, 2022, ICML.

XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale pdf

Juan Pino, Changhan Wang, Kritika Singh, 2021, INTERSPEECH.

OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav

Dhruv Batra, Z. Kira, Arjun Majumdar, 2023, ArXiv.

Improved Language Identification Through Cross-Lingual Self-Supervised Learning

Diptanu Gon Choudhury, Michael Auli, Yatharth Saraf, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unified Speech-Text Pre-training for Speech Translation and Recognition

Michael Auli, Jiatao Gu, J. Pino, 2022, ACL.

Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training

Michael Auli, Wei-Ning Hsu, Ramon Sanabria, 2022, ArXiv.

Introducing Semantics into Speech Encoders

Yizhou Sun, Hung-yi Lee, Shang-Wen Li, 2022, ACL.

Reference values of indices of spontaneous baroreceptor reflex sensitivity.

J. Tank, M. Weck, Alexei Baevski, 2000, American journal of hypertension.