Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Incremental Learning of MAP Context-Dependent Edit Operations for Spoken Phone Number Recognition in an Embedded Platform

Hahn Koo (1), Yan Ming Cheng (2)

(1) University of Illinois at Urbana Champaign, USA; (2) Motorola Labs, USA

Error-corrective post-processing (ECPP) has great potential to reduce speech recognition errors beyond that obtained by speech model improvement. ECPP approaches aim to learn error-corrective rules to directly reduce speech recognition errors. This paper presents our investigation into one such approach, incremental learning of maximum a posteriori (MAP) context-dependent edit operations. Limiting our dataset to spoken telephone number recognition output, we have evaluated this approach in an automotive environment using an embedded speech recognizer in a mobile device. We have found that a reduction of approximately 44กซ49% in speech recognition string errors can be achieved after learning.

Full Paper

Bibliographic reference.  Koo, Hahn / Cheng, Yan Ming (2006): "Incremental learning of MAP context-dependent edit operations for spoken phone number recognition in an embedded platform", In INTERSPEECH-2006, paper 1032-Thu1CaP.3.