Unsupervised Speech Recognition
Alexei Baevski, Wei-Ning Hsu, Alexis Conneau, Michael Auli
People
Michael Auli
Research Scientist
I am a Research Scientist at Facebook AI Research since 2015. Previously, I was a postdoc at Microsoft Research in Redmond working on improving translation quality using recurrent neural networks. I earned my Ph.D. at the University of Edinburgh for my work on syntactic parsing with approximate inference where I was advised by Adam Lopez and Philipp Koehn. I received a distinguished paper award at EMNLP in 2011 for my work on combinatory categorial grammar parsing.
Interests
Natural language processing, parsing, statistical machine translation, language modeling, structured prediction, large-scale discriminative training, deep learning, recurrent neural networks
Latest Publications
NeurIPS
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli
Wizard of Wikipedia: Knowledge-Powered Conversational Agents
Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston
Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling
Shruti Bhosale, Kyra Yee, Sergey Edunov, Michael Auli
On The Evaluation of Machine Translation Systems Trained With Back-Translation
Sergey Edunov, Myle Ott, Marc'Aurelio Ranzato, Michael Auli
vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
Alexei Baevski, Steffen Schneider, Michael Auli
