Ronan Collobert

Ronan Collobert joined Facebook in September 2014 as a Research Scientist in the AI Research Group. Over the past four years he was a researcher at the Idiap Research Institute in Switzerland, leading the Applied Machine Learning group. He also spent six years at NEC Labs in Princeton, NJ. His current interests are around deep learning in general, with applications in natural language, image and speech processing. Ronan also hacks Torch (a machine learning library) in his free time. He received his PhD from University of Pierre & Marie Curie in Paris under the supervision of the Bengio brothers (Idiap in Swizterland, and University of Montreal).

Ronan's Publications

January 13, 2020

RESEARCH

ML APPLICATIONS

Scaling up online speech recognition using ConvNets

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). The system has almost three times the throughput of a well tuned hybrid ASR baseline…

Vineel Pratap, Qiantong Xu, Jacob Kahn, Gilad Avidov, Tatiana Likhomanenko, Awni Hannun, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert

January 13, 2020

September 15, 2019

RESEARCH

ML APPLICATIONS

wav2vec: Unsupervised Pre-training for Speech Recognition

We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training.…

Steffen Schneider, Alexei Baevski, Ronan Collobert, Michael Auli

September 15, 2019