A non-speech audio CAPTCHA based on acoustic event detection and classification. Meutzner, H. & Kolossa, D. In 2016 24th European Signal Processing Conference (EUSIPCO), pages 2250-2254, Aug, 2016.
A non-speech audio CAPTCHA based on acoustic event detection and classification [pdf]Paper  doi  abstract   bibtex   
The completely automated public Turing test to tell computers and humans apart (CAPTCHA) represents an established method to prevent automated abuse of web services. Most websites provide an audio CAPTCHA - in addition to a conventional visual scheme - to facilitate access for a wider range of users. These audio CAPTCHAs are generally based on distorted speech, rendering the task difficult for untrained or non-native listeners, while still being vulnerable against attacks that make use of automatic speech recognition techniques. In this work, we propose a novel and universally usable type of audio CAPTCHA that is solely based on the classification of acoustic sound events. We show that the proposed CAPTCHA leads to satisfactorily high human success rates, while being robust against recently proposed attacks, more than currently available speech-based CAPTCHAs.
@InProceedings{7760649,
  author = {H. Meutzner and D. Kolossa},
  booktitle = {2016 24th European Signal Processing Conference (EUSIPCO)},
  title = {A non-speech audio CAPTCHA based on acoustic event detection and classification},
  year = {2016},
  pages = {2250-2254},
  abstract = {The completely automated public Turing test to tell computers and humans apart (CAPTCHA) represents an established method to prevent automated abuse of web services. Most websites provide an audio CAPTCHA - in addition to a conventional visual scheme - to facilitate access for a wider range of users. These audio CAPTCHAs are generally based on distorted speech, rendering the task difficult for untrained or non-native listeners, while still being vulnerable against attacks that make use of automatic speech recognition techniques. In this work, we propose a novel and universally usable type of audio CAPTCHA that is solely based on the classification of acoustic sound events. We show that the proposed CAPTCHA leads to satisfactorily high human success rates, while being robust against recently proposed attacks, more than currently available speech-based CAPTCHAs.},
  keywords = {computer network security;speech recognition;Web services;Web sites;human success rates;acoustic sound events;automatic speech recognition;nonnative listeners;untrained listeners;distorted speech;visual scheme;Web sites;Web services;automated public Turing test;acoustic event classification;acoustic event detection;nonspeech audio CAPTCHA;CAPTCHAs;Acoustics;Acoustic distortion;Databases;Nonlinear distortion;Speech},
  doi = {10.1109/EUSIPCO.2016.7760649},
  issn = {2076-1465},
  month = {Aug},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2016/papers/1570251627.pdf},
}
Downloads: 0