A Procedure for Unsupervised Lexicon Learning
Abstract
We describe an incremental unsupervised procedure to learn words from transcribed continuous speech. The algorithm is based on a conservative and traditional statistical model, and results of empirical tests show that it is competitive with other algorithms that have been proposed recently for this task.
Cite
Text
Venkataraman. "A Procedure for Unsupervised Lexicon Learning." International Conference on Machine Learning, 2001.Markdown
[Venkataraman. "A Procedure for Unsupervised Lexicon Learning." International Conference on Machine Learning, 2001.](https://mlanthology.org/icml/2001/venkataraman2001icml-procedure/)BibTeX
@inproceedings{venkataraman2001icml-procedure,
title = {{A Procedure for Unsupervised Lexicon Learning}},
author = {Venkataraman, Anand},
booktitle = {International Conference on Machine Learning},
year = {2001},
pages = {569-576},
url = {https://mlanthology.org/icml/2001/venkataraman2001icml-procedure/}
}