@inproceedings{4ebe7216a4d1427dad9e2947829f9b3e,
title = "Learning a lexicon and translation model from phoneme lattices",
abstract = "Language documentation begins by gathering speech. Manual or automatic transcription at the word level is typically not possible because of the absence of an orthography or prior lexicon, and though manual phonemic transcription is possible, it is prohibitively slow. On the other hand, translations of the minority language into a major language are more easily acquired. We propose a method to harness such translations to improve automatic phoneme recognition. The method assumes no prior lexicon or translation model, instead learning them from phoneme lattices and translations of the speech being transcribed. Experiments demonstrate phoneme error rate improvements against two baselines and the model's ability to learn useful bilingual lexical entries.",
author = "Oliver Adams and Graham Neubig and Trevor Cohn and Steven Bird and Do, {Quoc Truong} and Satoshi Nakamura",
year = "2016",
month = jan,
day = "1",
doi = "10.18653/v1/D16-1263",
language = "English",
volume = "1",
series = "EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "2377--2382",
editor = "Jian Su and Kevin Duh and Xavier Carreras",
booktitle = "Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing",
note = "2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016 ; Conference date: 01-11-2016 Through 05-11-2016",
}