Gradient-based learning applied to document recognition
Multilayer neural networks trained with the back-propagation algorithm constitute the best
example of a successful gradient based learning technique. Given an appropriate network …
example of a successful gradient based learning technique. Given an appropriate network …
[PDF][PDF] A tutorial on energy-based learning
Abstract Energy-Based Models (EBMs) capture dependencies between variables by
associating a scalar energy to each configuration of the variables. Inference consists in …
associating a scalar energy to each configuration of the variables. Inference consists in …
Unsupervised speech recognition
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 …
labeled training data which limits this technology to a small fraction of the languages spoken …
Fast wordpiece tokenization
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 …
propose efficient algorithms for the WordPiece tokenization used in BERT, from single-word …
Towards end-to-end unsupervised speech recognition
Unsupervised speech recognition has shown great potential to make Automatic Speech
Recognition (ASR) systems accessible to every language. However, existing methods still …
Recognition (ASR) systems accessible to every language. However, existing methods still …
Wenet 2.0: More productive end-to-end speech recognition toolkit
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 …
toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address …