GGSM and VOIP telephonic voice recordings are frequently used in forensic voice comparisons. However, speech compression, enhancement and error correction algorithms are likely to modify speaker specific voice characteristics. We performed high-quality voice recordings and concomitant GSM and VOIP telephonic voice recordings so that clean high-quality and telephonic versions of the same speech are available. Sustained vowel tasks are also included allowing F0 (AVG and STD), Jitter, Shimmer and HNR extraction for pairs of contemporaneous recordings. Twenty female and seventeen male volunteer subjects participated in the study. We describe the voice recording experiments, present results for five vowels and five acoustic parameters for each subject in GSM and VOIP communication, and we discuss the implications of the main results.

Authors: Fernandes, Vania; Ferreira, Anibal
Affiliation: University of Porto, Porto, Portugal
AES Conference: 2017 AES International Conference on Audio Forensics (June 2017)
Paper Number: 2-3
Publication Date: June 6, 2017 Import into BibTeX
Subject: Speaker Recognition
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=18745

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location:   /conf/2017/forensics/audio_forensics_2017_paper_20.pdf

Start a discussion about this paper!