'Meet AdBlock Radio, an adblocker for live radio streams and podcasts. Its creator, Alexandre Storelli, told Motherboard he hopes to help companies "develop alternative business models for radio and podcast lovers that do not want ads." "Ads exploit the weaknesses of many defenseless souls," Storelli told Motherboard. "Ads dishonestly tempt people, steal their time and promise them a higher social status. Blocking them will be a relieving experience for many." Most audio ads exploit "auditory artifacts" to produce an ad that can't be ignored or tuned out because it feels louder than it actually is -- this has gotten so bad that there has actually been a "sonic arms race" where ads have been made increasingly louder over the years. "Adblock Radio detects audio ads with machine-learning and Shazam-like techniques," Storelli wrote about the project. He said he's been working on it for more than three years and that it uses techniques such as speech recognition, acoustic fingerprinting, and machine learning to detect known ad formats. It uses a crowdsourced database of ads and "acoustic fingerprinting," which converts audio features into a series of numbers that can be combed by an algorithm. Storelli has made Adblock Radio open-source and given detailed instructions on how to build on it, integrate it into user devices, and deploy it in a way that pressures radio stations (and podcasts) to self-regulate the quality of their ads.' -- source: https://entertainment.slashdot.org/story/19/09/25/2056215 Cheers, Peter -- Peter Reutemann Dept. of Computer Science University of Waikato, NZ +64 (7) 858-5174 http://www.cms.waikato.ac.nz/~fracpete/ http://www.data-mining.co.nz/