Filler words as a speaker classification feature

Shunichi Ishihara, Yuko Kinoshita

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

Many of us can think of iconic words or expressions that our close friends or family often use. This study investigated the potential of idiosyncrasies in usage of filler words as a speaker classification parameter, using spontaneous Japanese speech. We estimated likelihood ratios (LRs) based on which filler words were used and how often, and performed speaker discrimination tests using the LRs. As a result we discovered that speakers’ choices of fillers can predict speaker’s identity to some degree, and that this has potential as an additional feature for speaker classification.
Original languageEnglish
Title of host publicationProceedings of the 13th Australasian International Conference on Speech Science and Technology
Place of PublicationMelbourne
PublisherAustralasian Speech Science and Technology Association
Pages34-37
Number of pages4
ISBN (Print)9780958194631
Publication statusPublished - 2010
Event13th Australasian International Conference on Speech Science and Technology - Melbourne, Australia
Duration: 14 Dec 201016 Dec 2010

Conference

Conference13th Australasian International Conference on Speech Science and Technology
CountryAustralia
CityMelbourne
Period14/12/1016/12/10

    Fingerprint

Cite this

Ishihara, S., & Kinoshita, Y. (2010). Filler words as a speaker classification feature. In Proceedings of the 13th Australasian International Conference on Speech Science and Technology (pp. 34-37). Melbourne: Australasian Speech Science and Technology Association.