Robust Topic Inference for Latent Semantic Language Model Adaptation
Resource
IEEE Automatic Speech Recognition and Understanding Workshop, Kyoto, Japan, (ASRU)
Journal
IEEE Automatic Speech Recognition and Understanding Workshop
Pages
177-182
Date Issued
2007-12
Author(s)
Abstract
We perform topic-based, unsupervised language model adaptation under an N-best rescoring framework by using previous-pass system hypotheses to infer a topic mixture which is used to select topic-dependent LMs for interpolation with a topici-ndependent LM. Our primary focus is on techniques for improving the robustness of topic inference for a given utterance with respect to recognition errors, including the use of ASR confidence and contextual information from surrounding utterances. We describe a novel application of metadata-based pseudo-story segmentation to language model adaptation, and present good improvements to character error rate on multigenre GALE Project data in Mandarin Chinese.
SDGs
Type
conference paper