WO2008036879A2 - Grammar generation for password recognition - Google Patents

Grammar generation for password recognition Download PDF

Info

Publication number
WO2008036879A2
WO2008036879A2 PCT/US2007/079131 US2007079131W WO2008036879A2 WO 2008036879 A2 WO2008036879 A2 WO 2008036879A2 US 2007079131 W US2007079131 W US 2007079131W WO 2008036879 A2 WO2008036879 A2 WO 2008036879A2
Authority
WO
WIPO (PCT)
Prior art keywords
grammar
speech recognition
string
pronounceable
password
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/US2007/079131
Other languages
French (fr)
Other versions
WO2008036879A3 (en
Inventor
Richard Breuer
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nuance Communications Inc
Original Assignee
Nuance Communications Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nuance Communications Inc filed Critical Nuance Communications Inc
Publication of WO2008036879A2 publication Critical patent/WO2008036879A2/en
Publication of WO2008036879A3 publication Critical patent/WO2008036879A3/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
    • G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
    • G10L15/193—Formal grammars, e.g. finite state automata, context free grammars or word networks
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase

Definitions

  • the invention generally relates to automatic speech recognition, and more specifically, to a speech recognition grammar for spoken passwords.
  • Embodiments of the present invention are directed to creating a password grammar for speech recognition.
  • a password is normalized into a list of strings of different character types including letters and numerals. For each string of letters, one or more corresponding letter permutations are determined that represent pronounceable combinations of that string. Then for each letter permutation, a corresponding recognition grammar entry is created for a speech recognition grammar.
  • one or more corresponding number permutations are also determined which represent pronounceable combinations of that string. And for each number permutation, a corresponding recognition grammar entry is also created for the speech recognition grammar.
  • a corresponding recognition grammar entry is also created for the speech recognition grammar.
  • the grammar may be, for example, a Speech Recognition Grammar Specification (SRGS) grammar.
  • SRGS Speech Recognition Grammar Specification
  • Figure 1 shows a flow chart of major functional steps for creating a speech recognition password grammar according to an embodiment of the present invention.
  • Figure 2 shows a normalized listing of a password according to an embodiment.
  • Figure 3 shows a permutation listing of a password according to an embodiment.
  • Embodiments of the present invention are directed to speech recognition techniques for analyzing a user password and creating a grammar for speech recognition of the password. Rejection of wrong passwords is based on the recognizer's features to reject out-of-grammar utterances.
  • SRGS Speech Recognition Grammar Specification
  • Figure 1 shows a flow chart of major functional steps for creating a speech recognition password grammar according to one specific embodiment of the present invention.
  • an existing password is normalized into a list of strings containing numeral strings or digits, strings of letters or single letters, and special characters, step 12.
  • the password 20 Hitt-222X is normalized to a letter string 21 with a value of Hitt 22, a special string -, a numeral string 222, and another letter string X.
  • all the characters sequences letters, numbers, and non-alphanumeric characters — are processed by creating permutations of all possible and meaningful substrings so as to determine string permutations, step 14.
  • a grammar entry is created for each remaining permutation, step 16.
  • the grammar contains one rule "password".
  • This rule contains a ⁇ one-of> for all alternative paths through the password.
  • Each ⁇ one-of> itself is a sequence of tokens.
  • Each token is created from one entry in the result list.
  • #lower and #upper are predefined rules, e.g.:
  • preferred embodiments may be implemented in a procedural programming language (e.g., C) or an object oriented programming language (e.g., C++ or Perl).
  • object oriented programming language e.g., C++ or Perl
  • Alternative embodiments of the invention may be implemented as preprogrammed hardware elements, other related components, or as a combination of hardware and software components.
  • Embodiments can be implemented as a computer program product for use with a computer system.
  • Such implementation may include a series of computer instructions fixed either on a tangible medium, such as a computer readable medium (e.g., a diskette, CD-ROM, ROM, or fixed disk) or transmittable to a computer system, via a modem or other interface device, such as a communications adapter connected to a network over a medium.
  • the medium may be either a tangible medium (e.g., optical or analog communications lines) or a medium implemented with wireless techniques (e.g., microwave, infrared or other transmission techniques).
  • the series of computer instructions embodies all or part of the functionality previously described herein with respect to the system.
  • Such computer instructions can be written in a number of programming languages for use with many computer architectures or operating systems. Furthermore, such instructions may be stored in any memory device, such as semiconductor, magnetic, optical or other memory devices, and may be transmitted using any communications technology, such as optical, infrared, microwave, or other transmission technologies. It is expected that such a computer program product may be distributed as a removable medium with accompanying printed or electronic documentation (e.g., shrink wrapped software), preloaded with a computer system (e.g., on system ROM or fixed disk), or distributed from a server or electronic bulletin board over the network (e.g., the Internet or World Wide Web).
  • printed or electronic documentation e.g., shrink wrapped software
  • preloaded with a computer system e.g., on system ROM or fixed disk
  • server or electronic bulletin board e.g., the Internet or World Wide Web

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Character Discrimination (AREA)
  • Machine Translation (AREA)

Abstract

A password grammar for speech recognition is described. A password is normalized into a list of strings of a plurality of character types such as letters and numerals. For each string of letters, one or more corresponding letter permutations are determined which represent pronounceable combinations of that string. Then, for each letter permutation, a corresponding recognition grammar entry is created for a speech recognition grammar.

Description

Attorney Docket: 2639/B62WO Grammar Generation for Password Recognition
[0001] This application claims priority from U.S. Provisional Patent Application 60/826,400, filed September 21, 2006, the contents of which are incorporated herein by reference.
[0002] Field of the Invention
[0003] The invention generally relates to automatic speech recognition, and more specifically, to a speech recognition grammar for spoken passwords.
Background Art
[0004] Many computer applications require the user to provide a difficult to predict password, such as Hitt-222X. Typically, such a password must be typed in via a keyboard input device. Although speech recognition is becoming more commonly used for text input, speech recognition of such difficult to predict passwords is more difficult than for normal words.
Summary of the Invention
[0005] Embodiments of the present invention are directed to creating a password grammar for speech recognition. A password is normalized into a list of strings of different character types including letters and numerals. For each string of letters, one or more corresponding letter permutations are determined that represent pronounceable combinations of that string. Then for each letter permutation, a corresponding recognition grammar entry is created for a speech recognition grammar.
[0006] In further embodiments, for each string of numerals, one or more corresponding number permutations are also determined which represent pronounceable combinations of that string. And for each number permutation, a corresponding recognition grammar entry is also created for the speech recognition grammar. Similarly, in some embodiments, for each string of non-alpha-numeric characters, one or more corresponding character permutations are also determined which represent pronounceable combinations of that string. And for each character permutation, a corresponding recognition grammar entry is also created for the speech recognition grammar.
[0007] The grammar may be, for example, a Speech Recognition Grammar Specification (SRGS) grammar.
Brief Description of the Drawings
[0008] Figure 1 shows a flow chart of major functional steps for creating a speech recognition password grammar according to an embodiment of the present invention.
[0009] Figure 2 shows a normalized listing of a password according to an embodiment.
[0010] Figure 3 shows a permutation listing of a password according to an embodiment.
Detailed Description of Specific Embodiments
[0011] Embodiments of the present invention are directed to speech recognition techniques for analyzing a user password and creating a grammar for speech recognition of the password. Rejection of wrong passwords is based on the recognizer's features to reject out-of-grammar utterances. In the following discussion, we consider the sample password "Hitt-222X" and a closed Speech Recognition Grammar Specification (SRGS) grammar is created. Of course, this is simply an illustrative example which should not be understood to limit the scope of the invention.
[0012] Figure 1 shows a flow chart of major functional steps for creating a speech recognition password grammar according to one specific embodiment of the present invention. Initially, an existing password is normalized into a list of strings containing numeral strings or digits, strings of letters or single letters, and special characters, step 12. For example, as shown in Fig. 2, the password 20 Hitt-222X is normalized to a letter string 21 with a value of Hitt 22, a special string -, a numeral string 222, and another letter string X. [0013] Next, all the characters sequences — letters, numbers, and non-alphanumeric characters — are processed by creating permutations of all possible and meaningful substrings so as to determine string permutations, step 14. This is to create grammar paths containing all pronounceable substrings. More specifically, all possible permutations 30 are created as shown in Fig. 3. So for example, the letter string 31 Hitt 32 is permutated into all possible variations of that string, Hit t, Hi tt, Hi 11, etc. Then all letter permutations are removed that contain sequences longer than one letter without a vowel, which do not consist of all the same character, assuming these cannot / will not be spoken. In the example, nothing will change, since the combinations "H i tt" and "Hi tt" which would be removed, contain "tt", a sequence of the letter "t". Therefore they are not removed.
[0014] Once the string permutations have been developed, a grammar entry is created for each remaining permutation, step 16. For example, in one specific embodiment, the grammar contains one rule "password". This rule contains a <one-of> for all alternative paths through the password. Each <one-of> itself is a sequence of tokens. Each token is created from one entry in the result list. For each non-alphanumeric character, a reference to a matching predefined rule is created, e.g. <ruleref uri = "#hyphen"/>. If the first letter is lowercase, a <ruleref uri="# lower "/> is created, otherwise <ruleref uri="#upper"/>. #lower and #upper are predefined rules, e.g.:
<rule id="upper">
<item repeat= 'O- 11 >upper case</item>
</rule>
<rule id="lower">
<item repeat= 1O-I1 >lower case</item>
</rule>
If the sequence does not consist of all the same letter, the (lowercase) sequence of letters itself is put in the rule. Otherwise, if the letters occur two times or more, a "double x" sequence is created, etc. In applicable cases, a "<number> times x" is created. If the number is lower than a maximum (999.999), a natural number is created. Otherwise this alternative is omitted, knowing that shorter sequences are available as well. Additionally, sequences of the same digit are treated specially. If one digit occurs two times, a "double x" sequence is created. In any case "<number> times x" is created. [0015] Embodiments of the invention may be implemented in any conventional computer programming language. For example, preferred embodiments may be implemented in a procedural programming language (e.g., C) or an object oriented programming language (e.g., C++ or Perl). Alternative embodiments of the invention may be implemented as preprogrammed hardware elements, other related components, or as a combination of hardware and software components.
[0016] Embodiments can be implemented as a computer program product for use with a computer system. Such implementation may include a series of computer instructions fixed either on a tangible medium, such as a computer readable medium (e.g., a diskette, CD-ROM, ROM, or fixed disk) or transmittable to a computer system, via a modem or other interface device, such as a communications adapter connected to a network over a medium. The medium may be either a tangible medium (e.g., optical or analog communications lines) or a medium implemented with wireless techniques (e.g., microwave, infrared or other transmission techniques). The series of computer instructions embodies all or part of the functionality previously described herein with respect to the system. Those skilled in the art should appreciate that such computer instructions can be written in a number of programming languages for use with many computer architectures or operating systems. Furthermore, such instructions may be stored in any memory device, such as semiconductor, magnetic, optical or other memory devices, and may be transmitted using any communications technology, such as optical, infrared, microwave, or other transmission technologies. It is expected that such a computer program product may be distributed as a removable medium with accompanying printed or electronic documentation (e.g., shrink wrapped software), preloaded with a computer system (e.g., on system ROM or fixed disk), or distributed from a server or electronic bulletin board over the network (e.g., the Internet or World Wide Web). Of course, some embodiments of the invention may be implemented as a combination of both software (e.g., a computer program product) and hardware. Still other embodiments of the invention are implemented as entirely hardware, or entirely software (e.g., a computer program product). [0017] Although various exemplary embodiments of the invention have been disclosed, it should be apparent to those skilled in the art that various changes and modifications can be made which will achieve some of the advantages of the invention without departing from the true scope of the invention.

Claims

What is claimed is:
1. A method for creating a password grammar for speech recognition comprising: normalizing a password into a list of strings of a plurality of character types, the character types including letters and numerals; for each string of letters, determining one or more corresponding letter permutations representing pronounceable combinations of the string; and for each letter permutation, creating a corresponding recognition grammar entry for a speech recognition grammar.
2. A method according to claim 1, further comprising: for each string of numerals, determining one or more corresponding number permutations representing pronounceable combinations of the string; and for each number permutation, creating a corresponding recognition grammar entry for the speech recognition grammar.
3. A method according to claim 1, further comprising: for each string of non-alphanumeric characters, determining one or more corresponding character permutations representing pronounceable combinations of the string; and for each character permutation, creating a corresponding recognition grammar entry for the speech recognition grammar.
4. A method according to claim 1, wherein the grammar is a Speech Recognition Grammar Specification (SRGS) grammar.
5. A speech recognition grammar for password recognition comprising: a recognition rule for each pronounceable permutation of each substring of letters.
6. A speech recognition grammar according to claim 5, further comprising: a recognition rule for each pronounceable permutation of each substring of numerals.
7. A speech recognition grammar according to claim 5, further comprising: a recognition rule for each pronounceable permutation of each substring of non- alphanumeric characters.
8. A speech recognition grammar according to claim 5, wherein the grammar is a Speech Recognition Grammar Specification (SRGS) grammar.
9. A computer program product for creating a password grammar for speech recognition, the product comprising: program code for normalizing a password into a list of strings of a plurality of character types, the character types including letters and numerals; program code for determining, for each string of letters, one or more corresponding letter permutations representing pronounceable combinations of the string; and program code for creating, for each letter permutation, a corresponding recognition grammar entry for a speech recognition grammar.
10. A computer program product according to claim 9, further comprising: program code for determining, for each string of numerals, one or more corresponding number permutations representing pronounceable combinations of the string; and program code for creating, for each number permutation, a corresponding recognition grammar entry for the speech recognition grammar.
11. A computer program product according to claim 1, further comprising: program code for determining, for each string of non-alphanumeric characters, one or more corresponding character permutations representing pronounceable combinations of the string; and program code for creating, for each character permutation, a corresponding recognition grammar entry for the speech recognition grammar.
12. A computer program product according to claim 1, wherein the grammar is a Speech Recognition Grammar Specification (SRGS) grammar.
PCT/US2007/079131 2006-09-21 2007-09-21 Grammar generation for password recognition Ceased WO2008036879A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US82640006P 2006-09-21 2006-09-21
US60/826,400 2006-09-21

Publications (2)

Publication Number Publication Date
WO2008036879A2 true WO2008036879A2 (en) 2008-03-27
WO2008036879A3 WO2008036879A3 (en) 2008-05-08

Family

ID=39092558

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2007/079131 Ceased WO2008036879A2 (en) 2006-09-21 2007-09-21 Grammar generation for password recognition

Country Status (2)

Country Link
US (1) US8065147B2 (en)
WO (1) WO2008036879A2 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8536976B2 (en) 2008-06-11 2013-09-17 Veritrix, Inc. Single-channel multi-factor authentication
US8166297B2 (en) 2008-07-02 2012-04-24 Veritrix, Inc. Systems and methods for controlling access to encrypted data stored on a mobile device
WO2010051342A1 (en) 2008-11-03 2010-05-06 Veritrix, Inc. User authentication for social networks
JP5646675B2 (en) * 2013-03-19 2014-12-24 ヤフー株式会社 Information processing apparatus and method

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5668928A (en) * 1995-01-31 1997-09-16 Kor Team International, Inc. Speech recognition system and method with automatic syntax generation
US5913192A (en) * 1997-08-22 1999-06-15 At&T Corp Speaker identification with user-selected password phrases
US6223158B1 (en) 1998-02-04 2001-04-24 At&T Corporation Statistical option generator for alpha-numeric pre-database speech recognition correction
US6978238B2 (en) 1999-07-12 2005-12-20 Charles Schwab & Co., Inc. Method and system for identifying a user by voice
US7031923B1 (en) * 2000-03-06 2006-04-18 International Business Machines Corporation Verbal utterance rejection using a labeller with grammatical constraints
WO2002010887A2 (en) 2000-07-28 2002-02-07 Jan Pathuel Method and system of securing data and systems
US20030055649A1 (en) * 2001-09-17 2003-03-20 Bin Xu Methods for accessing information on personal computers using voice through landline or wireless phones
US7599837B2 (en) * 2004-09-15 2009-10-06 Microsoft Corporation Creating a speech recognition grammar for alphanumeric concepts
US8095912B2 (en) * 2005-10-06 2012-01-10 Microsoft Corporation Testing a context-free language compiler

Also Published As

Publication number Publication date
WO2008036879A3 (en) 2008-05-08
US8065147B2 (en) 2011-11-22
US20080077405A1 (en) 2008-03-27

Similar Documents

Publication Publication Date Title
EP2585962B1 (en) Password checking
US8903726B2 (en) Voice entry of sensitive information
US10528766B2 (en) Techniques for masking electronic data
JP5268923B2 (en) Character position based password recovery
CN101286094A (en) Multimodal input method editor
US20190384818A1 (en) Contextual validation of synonyms in otology driven natural language processing
CN104008093A (en) Method and system for chinese name transliteration
US20070245149A1 (en) Method for obtaining meaningless password by inputting meaningful linguistic sentence
Dave et al. Neural compound-word (Sandhi) generation and splitting in Sanskrit language
US9710451B2 (en) Natural-language processing based on DNA computing
WO2008036879A2 (en) Grammar generation for password recognition
Hranický et al. On practical aspects of pcfg password cracking
US11481547B2 (en) Framework for chinese text error identification and correction
US7809566B2 (en) One-step repair of misrecognized recognition strings
US9613019B2 (en) Techniques for automatically generating test data
Bentley et al. CAPTCHA challenge strings: Problems and improvements
CN114281669B (en) Application reinforcement detection method, device, readable medium and electronic device
Amin et al. An efficient unicode based sorting algorithm for bengali words
Manohar et al. Spellchecker for Malayalam using finite state transition models
EP4625220B1 (en) Method and system for detecting passphrases in plain text
KR100388144B1 (en) The user identifier information processing method
KR100309219B1 (en) Network-based speaker learning and verification method and system thereof
CN110489962B (en) Method and system for improving user password complexity under operating system
CN108509060A (en) A method of remote phonetic transcriptions of Chinese characters code is registered by input method electronic dictionary
KR20200040989A (en) Password generation method based on Hangeul characters

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07842953

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 07842953

Country of ref document: EP

Kind code of ref document: A2