This paper focuses on correcting failures in Cockpit Voice Recorders when dealing with speech intelligibility. A common problem of Cockpit Voice Recorders is the failure of the erase function, causing speech to be recorded on top of each other rendering the recording unintelligible.  The current study investigates the potential benefit of computational speech intelligibility systems in providing guidance for functional cockpit voice recorders. This paper focuses on the Articulation Index, the Speech Intelligibility Index, and the Speech Transmission Index. These all use the Signal-to-Noise Ratio to help measure intelligibility. This paper determines a threshold for the Signal-to-Noise Ratio and intelligibility with layered continuous human speech to improve functionality of cockpit recordings.

Author: Foster, Jane
Affiliation: National Transportation Safety Board, Washington, DC, USA
AES Conference: 2017 AES International Conference on Audio Forensics (June 2017)
Paper Number: 3-2
Publication Date: June 6, 2017 Import into BibTeX
Subject: Speech Intelligibility
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=18747

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_6.pdf

Start a discussion about this paper!