Gradient-based learning applied to document recognition

Y LeCun, L Bottou, Y Bengio… - Proceedings of the …, 1998 - ieeexplore.ieee.org
Multilayer neural networks trained with the back-propagation algorithm constitute the best
example of a successful gradient based learning technique. Given an appropriate network …

[PDF][PDF] A tutorial on energy-based learning

Y LeCun, S Chopra, R Hadsell, M Ranzato… - Predicting structured …, 2006 - researchgate.net
Abstract Energy-Based Models (EBMs) capture dependencies between variables by
associating a scalar energy to each configuration of the variables. Inference consists in …

Unsupervised speech recognition

A Baevski, WN Hsu, A Conneau… - Advances in Neural …, 2021 - proceedings.neurips.cc
Despite rapid progress in the recent past, current speech recognition systems still require
labeled training data which limits this technology to a small fraction of the languages spoken …

Fast wordpiece tokenization

X Song, A Salcianu, Y Song, D Dopson… - arxiv preprint arxiv …, 2020 - arxiv.org
Tokenization is a fundamental preprocessing step for almost all NLP tasks. In this paper, we
propose efficient algorithms for the WordPiece tokenization used in BERT, from single-word …

Towards end-to-end unsupervised speech recognition

AH Liu, WN Hsu, M Auli… - 2022 IEEE Spoken …, 2023 - ieeexplore.ieee.org
Unsupervised speech recognition has shown great potential to make Automatic Speech
Recognition (ASR) systems accessible to every language. However, existing methods still …

Wenet 2.0: More productive end-to-end speech recognition toolkit

B Zhang, D Wu, Z Peng, X Song, Z Yao, H Lv… - arxiv preprint arxiv …, 2022 - arxiv.org
Recently, we made available WeNet, a production-oriented end-to-end speech recognition
toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address …