Alexei Baevski - AI Profile

Information

Engineer

Facebook AI Research

Experience

Education

Bio

Alexei works on natural language processing and speech problems at Facebook AI Research, with a special interest in self-supervised learning across different domains, as well as contributing and maintaining open-source toolkits such as fairseq.

Research Interests

Papers15 papers

Sort

By YearBy Citation

Add Paper

A Comparison of Discrete Latent Variable Models for Speech Representation Learning

Henry Zhou,Alexei Baevski,Michael Auli

ICASSP, pp.3050-3054, (2021)

EIBibtex

Self-training and Pre-training are Complementary for Speech Recognition

Qiantong Xu,Alexei Baevski, Tatiana Likhomanenko, Paden Tomasello, Alexis Conneau,Ronan Collobert,Gabriel Synnaeve,Michael Auli

ICASSP, pp.3030-3034, (2021)

Cited by2EIBibtex

vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations

Alexei Baevski,Steffen Schneider,Michael Auli

ICLR, (2020)

Cited by85EIBibtex

Reservoir Transformer

Sheng Shen,Alexei Baevski, Ari S. Morcos, Kurt Keutzer,Michael Auli,Douwe Kiela

Bibtex

Unsupervised Cross-lingual Representation Learning for Speech Recognition

Alexis Conneau,Alexei Baevski,Ronan Collobert,Abdelrahman Mohamed,Michael Auli

Cited by16Bibtex

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

Alexei Baevski,Henry Zhou,Abdelrahman Mohamed,Michael Auli

NIPS 2020, (2020)

Cited by67EIBibtex

Adaptive Input Representations for Neural Language Modeling

Alexei Baevski,Michael Auli

international conference on learning representations, (2019)

Cited by111EIBibtex

Facebook FAIR's WMT19 News Translation Task Submission

Ng Nathan, Yee Kyra,Baevski Alexei,Ott Myle,Auli Michael, Edunov Sergey

WMT (2), pp.314-319, (2019)

EIBibtex

Effectiveness of self-supervised pre-training for speech recognition

Baevski Alexei,Auli Michael,Mohamed Abdelrahman

Cited by30Bibtex

Pre-trained Language Model Representations for Language Generation

Sergey Edunov,Alexei Baevski,Michael Auli

arXiv: Computation and Language, (2019)

Cited by59EIBibtex

Pay Less Attention with Lightweight and Dynamic Convolutions

Felix Wu, Angela Fan,Alexei Baevski,Yann N. Dauphin,Michael Auli

ICLR, (2019)

Cited by213EIBibtex

Cloze-driven Pretraining of Self-attention Networks

Alexei Baevski, Sergey Edunov, Yinhan Liu,Luke Zettlemoyer,Michael Auli

International Joint Conference on Natural Language Processing, (2019)

Cited by42EIBibtex

fairseq: A Fast, Extensible Toolkit for Sequence Modeling

Myle Ott, Sergey Edunov,Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng,David Grangier,Michael Auli

arXiv: Computation and Language, (2019)

Cited by648EIBibtex

wav2vec: Unsupervised Pre-training for Speech Recognition

Steffen Schneider,Alexei Baevski,Ronan Collobert,Michael Auli

Conference of the International Speech Communication Association, (2019)

Cited by44EIBibtex

Facebook FAIR's WMT19 News Translation Task Submission

Nathan Ng, Kyra Yee,Alexei Baevski,Myle Ott,Michael Auli, Sergey Edunov

FOURTH CONFERENCE ON MACHINE TRANSLATION (WMT 2019), pp.314-319, (2019)

Cited by93Bibtex

View All

Ego Network

D-Core

Author Statistics

Alexei BaevskiEngineer

Papers15 papers