A speech-driven information retrieval system is expected to be useful for gathering information with greater ease. In a conventional system, users have to decide on the contents of their utterance before speaking, which takes quite a long time when their request is complicated. To overcome that problem, it is required for the retrieval system to handle a spontaneously spoken query directly. In this work, we propose an extension technique of spoken content retrieval (SCR) for effectively using spontaneously spoken queries. Acoustic features of meaningful terms in the retrieval may have prominence compared to other terms. Also, those terms will have linguistic specificity. From this assumption, we predict the contribution of terms included in spontaneously spoken queries using acoustic and linguistic features, and incorporate it in the query likelihood model (QLM) which is a probabilistic retrieval model. We verified the effectiveness of the proposed method through experiments. Our proposed method was successful in improving retrieval performance under various conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.