Improving Automatic Speech Recognition for Lectures through Transformation-based Rules Learned from Minimal Data

We demonstrate that transformation-based learning can be used to correct noisy speech recognition transcripts in the lecture domain with an average word error rate reduction of 12.9%. Our method is distinguished from earlier related work by its robustness to small amounts of training data, and its resulting efficiency, in spite of its use of true word error rate computations as a rule scoring function.

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: Cosmin Munteanu, Gerald Penn, Xiaodan Zhu
• Keywords: ACL 2009, Computational Linguistics, Error Rate Computations, Error Rate Reduction, Word Error Rate