Practical Test & Measurement: Objective Listening Effort Evaluation

This article by Hans W. Gierlich and Jan Reimes - two top experts in communication technologies from HEAD acoustics GmbH - details the expanded effort for understanding speech under noisy conditions, and addresses a new approach recently introduced by HEAD acoustics, resulting in a new model that can be used to test active noise cancellation (ANC) performance in complex scenarios where the system needs to distinguish between speech signals as part of the background noise and speech signals directed toward the users of these devices. This article was originally published in audioXpress, April 2020.

Speech recognition platforms suffer from poor recognition rates in a noisy environment such as kids in the back seat of cars, radio, ambulance passing by, or heavy rain. Video conferencing becomes ineffective when one of the participants is in a noisy environment like a coffee shop. Israel’s Hi Auto developed a software-only speech enhancement and speaker separation system that eliminates the most challenging noises and focus only on the speaker.

During Musikmesse 2017, Audionamix, officially released the world's first speech-specific, stand alone separation software, TRAX Pro 3 SP. TRAX Pro 3 SP allows audio engineers to isolate speech from background elements in mono or stereo recordings, separate speech from any kind of noise, improve speech intelligibility in archival recordings, clean up dialogue in film post-production without the need for ADR, and much more.

CEDAR Trinity allows continuous recording and monitoring with real time audio enhancing of up to eight channels of audio. With multiple CEDAR Trinity Satellite systems connected to any CEDAR Trinity host, multiple users can monitor and record live feeds for days, weeks, months or even years.