Exploring pause fillers in conversational speech for forensic phonetics: findings in a Spanish cohort including twins

Tsanas, Athanasios and San Segundo, Eugenia and Gómez Vilda, Pedro (2017). Exploring pause fillers in conversational speech for forensic phonetics: findings in a Spanish cohort including twins. In: "8th International Conference on Pattern Recognition Systems (ICPRS-17)", 11-13 Jul 2017, Madrid, España. ISBN 978-1-78561-652-5. pp. 232-237. https://doi.org/10.1049/cp.2017.0161.

Description

Title: Exploring pause fillers in conversational speech for forensic phonetics: findings in a Spanish cohort including twins
Author/s:
  • Tsanas, Athanasios
  • San Segundo, Eugenia
  • Gómez Vilda, Pedro
Item Type: Presentation at Congress or Conference (Article)
Event Title: 8th International Conference on Pattern Recognition Systems (ICPRS-17)
Event Dates: 11-13 Jul 2017
Event Location: Madrid, España
Title of Book: ICPRS 2017: 8th International Conference on Pattern Recognition Systems
Date: 2017
ISBN: 978-1-78561-652-5
Subjects:
Freetext Keywords: Forensic phonetics; Fundamental frequency contour; Pause fillers; Speech signal processing
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Arquitectura y Tecnología de Sistemas Informáticos
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (972kB) | Preview

Abstract

Pause fillers occur naturally during conversational speech, and have recently generated interest in their use for forensic applications. We extracted pause fillers from conversational speech from 54 speakers, including twins, whose voices are often perceptually similar. Overall 872 tokens of the sound [e:] were extracted (7-33 tokens per speaker), and objectively characterised using 315 acoustic measures. We used a Random Forest (RF) classifier and tested its performance using a leaveone- sample-out scheme to obtain probabilistic estimates of binary class membership denoting whether a query token belongs to a speaker. We report results using the Receiver Operating Characteristic (ROC) curve, and computing the Area Under the Curve (AUC). When the RF was presented with at least 20 tokens in the training phase for each of the two classes, we observed AUC in the range 0.71-0.98. These findings have important implications in the potential of pause fillers as an additional objective tool in forensic speaker verification.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainTEC2012-38630- C04-01UnspecifiedUniversidad Politécnica de MadridEvaluación multimodal de trastornos neurológicos mediante la caracterización de la voz, dinámica de los pliegues vocales y secuencias sacádicas
Government of SpainTEC2012-38630-C04-04UnspecifiedUniversidad Politécnica de MadridDetección del trastorno neurológico por medio de correlatos de la fonación obtenidos por modelado inverso a partir de la fuente glótica
Government of SpainTEC2016-77791-C4- 4-RUnspecifiedUniversidad Politécnica de MadridDescripción biométrica del locutor basada en correlatos de acción motora y estado cognitivo con aplicaciones en seguridad y rehabilitación

More information

Item ID: 50736
DC Identifier: http://oa.upm.es/50736/
OAI Identifier: oai:oa.upm.es:50736
DOI: 10.1049/cp.2017.0161
Official URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8362101&tag=1
Deposited by: Memoria Investigacion
Deposited on: 06 Jun 2019 06:19
Last Modified: 06 Jun 2019 06:19
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM