Evaluation of Communication Systems for Full-Face Firefighter Masks

Konferenz: Speech Communication - 12. ITG-Fachtagung Sprachkommunikation
05.10.2016 - 07.10.2016 in Paderborn, Deutschland

Tagungsband: Speech Communication

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Autoren:
Brodersen, Michael (Dräger Safety AG & Co. KGaA, 23560 Lübeck, Germany & Digital Signal Processing and System Theory, Kiel University, 24143 Kiel, Germany)
Jüngling, Thorben Moritz; Schmidt, Gerhard (Digital Signal Processing and System Theory, Kiel University, 24143 Kiel, Germany)

Inhalt:
When firefighters wear full-face masks with so-called selfcontained breathing apparatus for ensuring clean air supply, the speech is strongly attenuated due to the characteristics of the masks. For this reason communication units are attached to the masks to enhance the communication. The microphones of these units are picking up the speech signals. After enhancing the signals, they are played back via loudspeakers (in front of the mask), transmitted via so-called team radio (received from other communication units), and can be connected to a tactical radio. Since communication is important for successful operation of firefighters, different systems should be compared and, to document the progress of enhancement, (automatic) evaluation of such systems should also be investigated. In this paper we present an overview about evaluation strategies and show several first attempts based on measures such as signal-to-noise ratio, spectral distance, delay, speech transmission index, and perceptual objective listening quality assessments.