Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Language Data

Peering into Neural Networks—How Sequence Models View State of the Union Speeches from Three U.S. Presidents

Annotation Artifacts in Natural Language Inference Data

CMU Sphinx Frequently Asked Questions

How to use an Existing DNN Recognizer for Decoding in Kaldi

Exploring the Boost Graph Library

How to build a deep learning model in 15 minutes

Requests for Research

Gradient Descent in a Nutshell