Abstract
We offer a supervised machine learning approach for recognizing erroneous words in the output of a speech recognizer. We have investigated several sets of features combined with two word configurations, and compared the performance of two classifiers: Decision Trees and Naïve Bayes. Evaluation was performed on a corpus of 400 spoken referring expressions, with Decision Trees yielding a high recognition accuracy.
Original language | English |
---|---|
Title of host publication | Australasian Language Technology Association Workshop 2013 - Proceedings of the Workshop (ALTA) |
Editors | Sarvnaz Karimi, Karin Verspoor |
Place of Publication | Stroudsburg PA USA |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 101-105 |
Number of pages | 5 |
Publication status | Published - 2013 |
Event | Australasian Language Technology Association Workshop 2013 - Queensland University of Technology, Brisbane, Australia Duration: 4 Dec 2013 → 6 Dec 2013 Conference number: 11th https://www.aclweb.org/anthology/events/alta-2013/ (Proceedings) |
Conference
Conference | Australasian Language Technology Association Workshop 2013 |
---|---|
Abbreviated title | ALTAW 2013 |
Country/Territory | Australia |
City | Brisbane |
Period | 4/12/13 → 6/12/13 |
Internet address |
|