Skip to main content

SLLL

  • Home
  • People
    • Executive
    • Academics
    • Professional staff
    • Visitors
    • Current HDR students
    • Graduated HDR students
    • Alumni
  • Events
    • Event series
    • Conferences
      • Past conferences
  • News
  • Students
    • Study with us
      • Undergraduate study
      • Graduate coursework
      • Higher degree by research
    • Current students
      • Honours
      • Student exchange
      • Language placement test
    • Overseas study tours
    • Language videos
    • Summer Scholars Program
  • Study options
  • Research
    • Research projects
      • Sydney Speaks Project
        • People
          • Members
          • Students
        • Dissemination
        • Corpora
    • Speech & Language Lab
  • Classics Museum
    • About
    • Classics Museum Catalogue
    • Museum Events
    • Curator-led Tours
    • Friends of the Museum
    • Volunteer Guides
    • Collections Management
    • Research
  • Contact us

Centres

  • Australian National Dictionary Centre
  • Centre for Australian Literary Cultures
  • Centre for Classical Studies
  • Centre for Early Modern Studies
  • Institute for Communication in Health Care

Centre for Australian Literary Cultures

Institute for Communication in Health Care

Linguistics

SLLL

Partners

  • ARC Centre of Excellence in the Dynamics of Language
  • Linguistics at ANU

Networks

Related Sites

  • ANU College of Arts & Social Sciences
  • Research School of Humanities and the Arts
  • Australian National Internships Program

Administrator

Breadcrumb

HomeUpcoming EventsCoEDL Linguistics Seminar : Kimiya Akita, A Study of Japanese Rhythm In Forensic Voice Comparison: An Application of The Free Software Toolkit 'Julius'
CoEDL Linguistics Seminar : Kimiya Akita, A Study of Japanese rhythm in Forensic Voice Comparison: An Application of the Free Software Toolkit 'Julius'

Abstract: This is a preliminary study on the usefulness of rhythmic information as forensic voice comparison features in Japanese. In this study, we focus on phoneme and syllable duration and their average power as the rhythmic features. Two different segmentation schemes are employed in this study: One is manual and the other is automatic segmentation using a third party tool “Speech Segmentation Toolkit” with an open-source speech recognition engine “Julius”. The speech samples (two recordings at two different sessions) read out by 100 male Japanese speakers were extracted from the National Research Institute of Police Science, Japan (NRIPS) database. The likelihood ratios were estimated by the Multivariate Kernel Density formula for the 100 same-speaker comparisons and 9900 different-speaker comparisons for each phoneme and syllable, and then they were respectively logistic-regression fused. This study will look into what types of phonemes and syllables tend to carry more individuating information, while showing the magnitude of the LRs obtained from Japanese rhythmic information. This study will also compare the performance between the automatic and manual segmentations.

Date & time

  • Fri 22 Nov 2019, 3:30 pm - 3:30 pm

Location

Engma Room, Coombs 3.165

Speakers

  • Kimiya Akita

Contact

  •  Jane Simpson
     Send email