Virtual Evidence for Training Speech Recognizers Using Partially Labeled Data

Collecting supervised training data for automatic speech recognition (ASR) systems is both time consuming and expensive. In this paper we use the notion of virtual evidence in a graphical-model based system to reduce the amount of supervisory training data required for sequence learning tasks. We apply this approach to a TIMIT phone recognition system, and show that our VE-based training scheme can, relative to a baseline trained with the full segmentation, yield similar results with only 15.3% of the frames labeled (keeping the number of utterances fixed).

• Type: Conference
• Year: 2007
• Where: NAACL
• Authors: Amarnag Subramanya, Jeff A. Bilmes
• Keywords: Automatic Speech Recognition, Computational Linguistics, NAACL 2007, Supervised Training Data, Training Data