Unsupervised Speech Recognition
Michael Auli, Alexei Baevski, Alexis Conneau, Wei-Ning Hsu
People
Alexei Baevski
Research Engineer
I work at Facebook AI Research on NLP problems and toolkits such as as Fairseq. Previously, I worked on Facebook Search, specifically on spell correction and query suggestion problems. Before that, I was at a financial risk management start-up where I worked as an engineer and a manager. I hold a Bachelor’s degree in computer science from University of Toronto.
Interests
NLP on its own and combined with other fields like vision (e.g. visual question answering), conversational systems (chatbots, conversational search, assistants), recommender systems and performance optimizations for existing algorithms
Latest Publications
NeurIPS
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
Michael Auli, Alexei Baevski, Abdelrahman Mohamed, Henry Zhou
Effectiveness of self-supervised pre-training for ASR
, Alexei Baevski, Abdelrahman Mohamed
vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
Michael Auli, Alexei Baevski, Steffen Schneider
Cloze-driven Pretraining of Self-attention Networks
Michael Auli, Alexei Baevski, Sergey Edunov, Yinhan Liu, Luke Zettlemoyer
wav2vec: Unsupervised Pre-training for Speech Recognition
Michael Auli, Alexei Baevski, Ronan Collobert, Steffen Schneider