Header

UZH-Logo

Maintenance Infos

Comparisons of speaker recognition strengths using suprasegmental duration and intensity variability: an artificial neural networks approach


He, Lei; Glavitsch, Ulrike; Dellwo, Volker (2015). Comparisons of speaker recognition strengths using suprasegmental duration and intensity variability: an artificial neural networks approach. In: International Congress of Phonetic Sciences, Glasgow, 10 August 2015 - 14 August 2015. University of Glasgow, 395.

Abstract

This study compares the speaker recognition strengths based on suprasegmental duration and intensity variability in the speech signal using artificial neural networks. Such algorithm can well capture the nonlinear effects in the data, and is more robust against noise in the data. Three rounds of classification tasks were performed with 1) duration metrics, 2) intensity metrics, and 3) the combination of duration and intensity metrics as the independent variables. The results indicated that both intensity and combined metrics significantly outperformed the duration metrics. Moreover, the combination of intensity and duration metrics showed higher probability of improved speaker classifications than intensity metrics over duration metrics.

Abstract

This study compares the speaker recognition strengths based on suprasegmental duration and intensity variability in the speech signal using artificial neural networks. Such algorithm can well capture the nonlinear effects in the data, and is more robust against noise in the data. Three rounds of classification tasks were performed with 1) duration metrics, 2) intensity metrics, and 3) the combination of duration and intensity metrics as the independent variables. The results indicated that both intensity and combined metrics significantly outperformed the duration metrics. Moreover, the combination of intensity and duration metrics showed higher probability of improved speaker classifications than intensity metrics over duration metrics.

Statistics

Altmetrics

Downloads

7 downloads since deposited on 08 Nov 2016
0 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Department of Comparative Language Science
06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
490 Other languages
890 Other literatures
410 Linguistics
Uncontrolled Keywords:duration variability, intensity variability, speaker recognition, artificial neural networks
Language:English
Event End Date:14 August 2015
Deposited On:08 Nov 2016 13:17
Last Modified:27 Nov 2020 07:25
Publisher:University of Glasgow
ISBN:978-0-85261-941-4
Additional Information:Proceedings Chapter: Forensic Phonetics and Speaker Characteristics
OA Status:Closed
Free access at:Official URL. An embargo period may apply.
Official URL:https://www.internationalphoneticassociation.org/icphs-proceedings/ICPhS2015/Papers/ICPHS0395.pdf
Related URLs:https://www.internationalphoneticassociation.org/icphs/icphs2015 (Organisation)