English Alphabet Recognition with Telephone Speech
Abstract
A recognition system is reported which recognizes names spelled over the telephone with brief pauses between letters. The system uses separate neural networks to locate segment boundaries and classify letters. The letter scores are then used to search a database of names to find the best scoring name. The speaker-independent classification rate for spoken let(cid:173) ters is 89%. The system retrieves the correct name, spelled with pauses between letters, 91 % of the time from a database of 50,000 names.
Cite
Text
Fanty et al. "English Alphabet Recognition with Telephone Speech." Neural Information Processing Systems, 1991.Markdown
[Fanty et al. "English Alphabet Recognition with Telephone Speech." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/fanty1991neurips-english/)BibTeX
@inproceedings{fanty1991neurips-english,
title = {{English Alphabet Recognition with Telephone Speech}},
author = {Fanty, Mark and Cole, Ronald A. and Roginski, Krist},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {199-206},
url = {https://mlanthology.org/neurips/1991/fanty1991neurips-english/}
}