Web: http://arxiv.org/abs/2203.13687

June 16, 2022, 1:11 a.m. | Hung-Shin Lee, Pin-Tuan Huang, Yao-Fei Cheng, Hsin-Min Wang

cs.LG updates on arXiv.org arxiv.org

In our previous work, we proposed a discriminative autoencoder (DcAE) for
speech recognition. DcAE combines two training schemes into one. First, since
DcAE aims to learn encoder-decoder mappings, the squared error between the
reconstructed speech and the input speech is minimized. Second, in the code
layer, frame-based phonetic embeddings are obtained by minimizing the
categorical cross-entropy between ground truth labels and predicted
triphone-state scores. DcAE is developed based on the Kaldi toolkit by treating
various TDNN models as encoders. In …

arxiv speech speech recognition

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY