System and method for generating challenge items for CAPTCHAs

• US 8,744,850 B2
• Filed: 01/14/2013
• Issued: 06/03/2014
• Est. Priority Date: 06/23/2008
• Status: Active Grant

• Current Assignee: Knapp Investment Company Limited
• Original Assignee: John Nicholas and Kristin Gross
• Inventors: Gross, John Nicholas
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): ADESANYA, OLUJIMI A
• Application Number:
  US13/740,589
• Publication Number:
  US 20130132093A1
• Time in Patent Office: 505 Days
• Field of Search: 704/246
• US Class Current: 704/246
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: H04L 63/102 Entity profiles
• CPC Class Codes: H04L 63/123 received data contents, e.g. message integrity
• CPC Class Codes: H04M 2203/2027 Live party detection

Abstract

Challenge items for an audible based electronic challenge system are generated using a variety of techniques to identify optimal candidates. The challenge items are intended for use in a computing system that discriminates between humans and text to speech (TTS) system.

Claims

1. A method implemented by a computing system for selecting challenge items to discriminate between humans and machines in determining access to data and/or resources of a target computing system, comprising:

(a) providing data identifying a first set of diphones to be assessed by the computing system, wherein each of said first set of diphones represents a sound associated with an articulation of a pair of phonemes in a natural language;

(b) generating a plurality of articulation scores using the computing system based on measuring acoustical characteristics of a reference machine text to speech (TTS) system articulation of each of said first set of diphones; and

(c) selecting challenge text including words and phrases from the natural language using the computing system based on said plurality of articulation scores;

wherein said challenge text has machine-indicative acoustical characteristics detectable by a speech processing computing system when articulated by the reference machine TTS system or another machine TTS system such that said challenge text is useable by an utterance-based challenge system for discriminating between humans and machines.

2. The method of claim 1 further including a step:

processing input speech by an entity using said utterance-based challenge system and a challenge item database populated with said challenge text to distinguish between a human and a machine synthesized voice.

3. The method of claim 1 wherein said acoustical characteristics include measurements of transition differences between phonemes.

4. The method of claim 1 wherein said challenge text includes sentences extracted from a corpus of human-authored documents.

5. The method of claim 1 wherein said challenge text includes sentences automatically generated from said natural language by the computing system based on said diphone articulation scores.

6. The method of claim 1 wherein said word and phrases are given articulation scores.

8. The method of claim 2 further including a step:

processing input speech by an entity using said reference challenge item to distinguish between a human and a machine synthesized voice.

7. A method of selecting challenge data using a computing system to be used for accessing data and/or resources of a target computing system comprising:

a) selecting a candidate challenge item which includes one or both of text words or visual images;

b) measuring first computer-related acoustical characteristics of a computer synthesized utterance consisting of audio of challenge content associated with said candidate challenge item using the computing system;

c) measuring second human-related acoustical characteristics of a human utterance consisting of audio of said challenge content;

d) generating a challenge item score based on measuring a difference in said first computer-related and second human-related acoustical characteristics; and

e) designating said candidate challenge item as a reference challenge item when said challenge item score exceeds a target threshold, indicating that said challenge content has machine-indicative acoustical characteristics detectable by a speech processing system.

9. The method of claim 7, wherein said challenge item score is also based on one or more topics associated with said text words and/or visual images and which are identified and measured in said computer synthesized utterance and human utterance respectively.

10. The method of claim 7, wherein said challenge item score is also based on prosodic elements associated with said text words and/or visual images and which are identified and measured in said computer synthesized utterance and human utterance respectively.

11. The method of claim 7, wherein said challenge item score is also based on a collaborative filtering score generated by measuring responses to a sequence of two or more of said candidate challenge items identified in said in said computer synthesized utterances and human utterances respectively.

12. The method of claim 11 wherein said collaborative filtering score is derived by identifying at least a first reference correlation between at least a first reference text descriptor for a first challenge item and a second reference text descriptor for a second challenge item, including a probability that a human reviewer identifying said first reference text descriptor when presented with said first challenge item also provides said second reference text descriptor when presented with said second challenge item, or vice-versa.

13. The method of claim 11 wherein said collaborative filtering score is derived by identifying at least a first reference correlation between a first challenge item presented in incomplete form, and a predicted response for completing said challenge item.

14. A method implemented by a computing system for accessing data and/or resources of a target computing system comprising:

a) defining a plurality of demographic groups, said demographic groups being based on one or more of age, sex, or domicile;

b) providing a plurality of Completely Automatic Public Turing Test To Tell Humans and Computers Apart (CAPTCHA) challenge items consisting of a combination of images and solicited utterances with the computing system;

c) for each of said challenge items, using the computing system to compare a first reference acoustic response of a machine entity and a second reference acoustic response provided by a representative of each of said plurality of demographic groups; and

d) for each demographic group, selecting an optimal set of CAPTCHA challenge items determined by the computing system to yield the greatest acoustic response difference between said second reference acoustic response of said representative and said first reference acoustic response of said machine entity.

15. The method of claim 14 further including a step:

identifying a demographic group for an entity; and

processing input speech by said entity using at least one of said optimal set of CAPTCHA challenge items for said demographic group to determine if it is a human or a machine synthesized voice.

16. A system for identifying challenge data to be used for accessing data and/or resources of a target computing system comprising:

a first computing system; and

one or more software routines embodied in a non-transitory computer readable medium that, when executed, cause the first computing system to;

(a) provide data identifying a first set of diphones to be assessed the first computing system, wherein each of said first set of diphones represents a sound associated with an articulation of a pair of phonemes in a natural language;

(b) generate a plurality of articulation scores based on measuring acoustical characteristics of a reference machine text to speech (TTS) system articulation of each of said first set of diphones; and

(c) select challenge text including words and phrases from the natural language using the computing system based on said plurality of articulation scores;

wherein said challenge text has machine-indicative acoustical characteristics detectable by a speech processing computing system when articulated by the machine TTS system or another machine TTS system such that said challenge text is useable by an utterance-based challenge system for discriminating between humans and machines.

17. A system for identifying challenge data to be used for accessing data and/or resources of a target computing system comprising:

a first computing system; and

one or more software routines embodied in a computer readable medium that, when executed, cause the first computing system to;

a) select a candidate challenge item which includes one or both of text words or visual images;

b) measure first computer-related acoustical characteristics of a computer synthesized utterance consisting of audio of challenge content associated with said candidate challenge item;

c) measure second human-related acoustical characteristics of a human utterance consisting of audio of said challenge content;

d) generate a challenge item score based on measuring a difference in said first computer-related and second human-related acoustical characteristics; and

e) designate said candidate challenge item as a reference challenge item when said challenge item score exceeds a target threshold, indicating that said challenge content has machine-indicative acoustical characteristics detectable by a speech processing system.

18. A system for identifying challenge data to be used for accessing data and/or resources of a target computing system comprising:

a first computing system; and

one or more software routines embodied in a computer readable medium that, when executed, cause the computing system to;

a) define a plurality of demographic groups, said demographic groups being based on one or more of age, sex, or domicile;

b) provide a plurality of Completely Automatic Public Turing Test To Tell Humans and Computers Apart (CAPTCHA) challenge items consisting of a combination of images and solicited utterances;

c) for each of said challenge items, compare a first reference response of a machine entity and a second reference response provided by a representative of each of said demographic groups; and

d) for each demographic group, select an optimal set of CAPTCHA challenge items determined by the computing system to yield the greatest response difference between said second reference acoustic response of said representative and said first reference acoustic response of said machine entity.