Real-time Auditory Contrast Enhancement
Author(s) -
Marian Weger,
Thomas Hermann,
Robert Höldrich
Publication year - 2019
Language(s) - English
Resource type - Conference proceedings
DOI - 10.21785/icad2019.026
Subject(s) - computer science , sharpening , contrast (vision) , latency (audio) , speech recognition , speech enhancement , percussion , natural sounds , artificial intelligence , acoustics , telecommunications , physics , noise reduction
Every day, we rely on the information that is encoded in the auditory feedback of our physical interactions. With the goal to perceptually enhance those sound characteristics that are relevant to us — especially within professional practices such as percussion and auscultation — we introduce the method of real-time Auditory Contrast Enhancement (ACE). It is derived from algorithms for speech enhancement as well as from the remarkable sound processing mechanisms of our ears. ACE is achieved by individual sharpening of spectral and temporal structures contained in a sound while maintaining its natural gestalt. With regard to the targeted real-time applications, the proposed method is designed for low latency. As the discussed examples illustrate, it is able to significantly enhance spectral and temporal contrast.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom