Loading...
Please wait, while we are loading the content...
Similar Documents
Systemand Method for Auditory Captchas Background of the Invention
| Content Provider | Semantic Scholar |
|---|---|
| Copyright Year | 2017 |
| Abstract | (75) Inventors: Steven Hart LEWIS, Middletown, NJ (US); John Baldasare, Neptune, (57) ABSTRACT NJ (US) Disclosed herein are systems, methods, and computer read Correspondence Address: able-media for performing an audible human verification. AT&T LEGAL DEPARTMENT NDQ The method includes determining that a human verification is ATTN: PATENT DOCKETING, ONE AT & T needed, presenting an audible challenge to a user which WAY, ROOM 2A-207 exploits a known issue with automatic speech recognition BEDMINSTER, NJ 07921 (US) processes, receiving a response to the audible challenge, and Verifying that a human provided the response. The known (73) Assignee: AT&T Intellectual Property I, issue with automatic speech recognition processes can be L.P., Reno, NV (US) recognition of a non-word, in which case the user can be asked to spell the recognized non-word. The known issue (21) Appl. No.: 12/197503 with automatic speech recognition processes can be differen tiation of simultaneous input formultiple audio streams. Mul (22) Filed: Aug. 25, 2008 tiple audio streams contained in the audible challenge can be O O provided monaurally. Verifying that a human provided the Publication Classification response can include confirming the contents of one of the (51) Int. Cl. multiple audio streams. Audible human verification can be GIOL 2L/00 (2006.01) performed in combination with visual human verification. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://patentimages.storage.googleapis.com/5a/fe/37/03585eedb1af07/US20100049526A1.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |