Dialogue Speech Recognition by Combining Hierarchical Topic Classification and Language Model Switching

Ian R. LANE  Tatsuya KAWAHARA  Tomoko MATSUI  Satoshi NAKAMURA  

IEICE TRANSACTIONS on Information and Systems   Vol.E88-D   No.3   pp.446-454
Publication Date: 2005/03/01
Online ISSN: 
DOI: 10.1093/ietisy/e88-d.3.446
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Spoken Language Systems
speech recognition,  topic detection,  topic-dependent language modeling,  support vector machines,  multi-domain spoken dialogue,  

Full Text: PDF>>
Buy this Article

An efficient, scalable speech recognition architecture combining topic detection and topic-dependent language modeling is proposed for multi-domain spoken language systems. In the proposed approach, the inferred topic is automatically detected from the user's utterance, and speech recognition is then performed by applying an appropriate topic-dependent language model. This approach enables users to freely switch between domains while maintaining high recognition accuracy. As topic detection is performed on a single utterance, detection errors may occur and propagate through the system. To improve robustness, a hierarchical back-off mechanism is introduced where detailed topic models are applied when topic detection is confident and wider models that cover multiple topics are applied in cases of uncertainty. The performance of the proposed architecture is evaluated when combined with two topic detection methods: unigram likelihood and SVMs (Support Vector Machines). On the ATR Basic Travel Expression Corpus, both methods provide a significant reduction in WER (9.7% and 10.3%, respectively) compared to a single language model system. Furthermore, recognition accuracy is comparable to performing decoding with all topic-dependent models in parallel, while the required computational cost is much reduced.