CN102789781A - Mode supporting vocal print verification in Voice XML (Extensive Makeup Language) 2.0 - Google Patents
Mode supporting vocal print verification in Voice XML (Extensive Makeup Language) 2.0 Download PDFInfo
- Publication number
- CN102789781A CN102789781A CN2011101331686A CN201110133168A CN102789781A CN 102789781 A CN102789781 A CN 102789781A CN 2011101331686 A CN2011101331686 A CN 2011101331686A CN 201110133168 A CN201110133168 A CN 201110133168A CN 102789781 A CN102789781 A CN 102789781A
- Authority
- CN
- China
- Prior art keywords
- vocal print
- voicexml
- mode
- voice
- print verification
- 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.)
- Pending
Links
Images
Abstract
The invention relates to a mode supporting vocal print verification in Voice XML (Extensive Makeup Language) 2.0. The mode comprises the steps as follows: expanding builtin syntactic types by using type properties of a label (field), a Voice XML interpreter can be used for realizing appointed builtin types, and can provide functions of vocal print registration and vocal print verification, and a vocal print registration result and a vocal print verification result can be returned by shadow variables of the filed. By using the technical scheme, the vocal print verification function can be graciously realized by using existed syntactic structures of the Voice XML2.0. Compared with that of the (object) expanding mechanism self provided by the Voice XML2.0, the mode is more concise on the syntax aspect.
Description
Technical field
The present invention relates to biological characteristic and distinguish the field, be specifically related to a kind of mode of in VoiceXML 2.0, supporting the vocal print checking.
Background technology
VoiceXML is the international norm (http://www.w3.org/TR/voicexml20/) that is applied to voice flow, and the version of standard is 2.0 at present.
The vocal print checking is the mode according to personal voice biological characteristic uniqueness identity verification.The vocal print checking has registration (Voice Enrollment) and checking (Voice Verification) two links.Can be different because of specifically realizing, when registration, say specific statement several times on the whole by the user, say relevant statement during checking, judge whether the verifier is exactly the registrant.
Vocal print checking is the effective means of identifying user identity in the voice application, but VoiceXML 2.0 norm-settings in March, 2004, standard itself does not comprise the primary support (native support) to the vocal print authentication function as yet.Considered support among the VoiceXML 3.0, but this standard is still at draft stage (Working Draft) to the vocal print checking.
The mode of < object>self-defined object is arranged among the VoiceXML 2.0, can realize expansion the VoiceXML language.
But, through the mode of < object>self-defined object, there is following shortcoming:
-mode through < object>expansion vocal print checking is when writing VoiceXML, and is relatively complicated on the grammer;
-< object>extended mode with VoiceXML primary grammer support compare, lack gracefulness property, the readability of language.
Summary of the invention
The present invention seeks to overcome the above-mentioned shortcoming of prior art, a kind of mode of in VoiceXML2.0, supporting the vocal print checking is provided.The problem that the present invention solves is on VoiceXML 2.0 normative foundations, increases a kind of mode of vocal print authentication function simply, grazioso.
The technical matters that the present invention solved can adopt following technical scheme to realize:
A kind of mode of in VoiceXML 2.0, supporting the vocal print checking is characterized in that may further comprise the steps:
1.. utilize the type attribute of < field>label, expanding built-in syntactic type (builtin type)
2. the .VoiceXML interpreter is realized the built-in type according to appointment, and vocal print registration, vocal print authentication function are provided
3.. vocal print registration, vocal print checking result return through the shadow variable (Shadow Variables) of this field.
The present invention is characterised in that: the built-in syntactic type of expansion < field>label type attribute in VoiceXML 2.0, realize the vocal print authentication function.
The present invention is characterised in that: in VoiceXML2.0, use shadow variable (Shadow Variables) to return the vocal print result.
Beneficial effect: owing to adopt technique scheme, utilize VoiceXML 2.0 existing syntactic structures to realize the vocal print authentication function grazioso, more succinct on < object>extension mechanism grammer that itself provides than VoiceXML 2.0.
Description of drawings
Fig. 1 is a kind of mode process flow diagram of in VoiceXML 2.0, supporting the vocal print checking of the present invention;
Fig. 2 discloses a kind of mode specific embodiment of in VoiceXML 2.0, supporting the vocal print checking of most preferred embodiment of the present invention
Embodiment
For technological means, creation characteristic that the present invention is realized, reach purpose and effect and be easy to understand and understand, further set forth the present invention below in conjunction with concrete diagram.
Fig. 1 discloses a kind of mode process flow diagram of in VoiceXML 2.0, supporting the vocal print checking of the present invention, and step is following:
Step S101, the type attribute of utilization < field>label, expanding built-in syntactic type (builtin type);
Step S102, the VoiceXML interpreter is realized the built-in type according to appointment, and vocal print registration, vocal print authentication function are provided;
Step S103, vocal print registration, vocal print checking result return through the shadow variable (Shadow Variables) of this field.
The principle of the invention is: the value of < field>label type attribute; Will be in interpreter as builtin:grammar/builtin_type_name; Interpreter is realized and can be carried out vocal print registration, vocal print authentication function according to the builtin_type_name of appointment, rather than common speech identifying function; The result of vocal print checking will return through the voice identification result NLSML form of standard.
Fig. 2 discloses a kind of mode specific embodiment of in VoiceXML 2.0, supporting the vocal print checking of most preferred embodiment of the present invention, and it is following that the VoiceXML of vocal print checking implements code:
From specific embodiment, can find out, utilize the existing syntactic structures of VoiceXML 2.0 to realize the vocal print authentication function grazioso, more succinct on < object>extension mechanism grammer that itself provides than VoiceXML 2.0.
More than show and described ultimate principle of the present invention and principal character and advantage of the present invention.The technician of the industry should understand; The present invention is not restricted to the described embodiments; The present invention that just explains who describes in the foregoing description and the instructions supports one type of mode of vocal print checking in VoiceXML 2.0; Under the prerequisite that does not break away from spirit and scope of the invention, the present invention is applicable to other similar fashion of in VoiceXML 2.0, supporting the vocal print checking, and this checking content also falls in the scope of the invention that requires protection.The present invention requires protection domain to be defined by appending claims and equivalent thereof.
Claims (3)
1. in VoiceXML 2.0, support the mode that vocal print is verified for one kind, it is characterized in that may further comprise the steps:
1.. utilize the type attribute of < field>label, expanding built-in syntactic type (builtin type)
2. the .VoiceXML interpreter is realized the built-in type according to appointment, and vocal print registration, vocal print authentication function are provided
3.. vocal print registration, vocal print checking result return through the shadow variable (Shadow Variables) of this field.
2. a kind of mode of in VoiceXML 2.0, supporting the vocal print checking according to claim 1 is characterized in that: the built-in syntactic type of expansion < field>label type attribute in VoiceXML 2.0, realize the vocal print authentication function.
3. a kind of mode of in VoiceXML 2.0, supporting the vocal print checking according to claim 1 is characterized in that: in VoiceXML2.0, use shadow variable (Shadow Variables) to return the vocal print result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011101331686A CN102789781A (en) | 2011-05-20 | 2011-05-20 | Mode supporting vocal print verification in Voice XML (Extensive Makeup Language) 2.0 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011101331686A CN102789781A (en) | 2011-05-20 | 2011-05-20 | Mode supporting vocal print verification in Voice XML (Extensive Makeup Language) 2.0 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102789781A true CN102789781A (en) | 2012-11-21 |
Family
ID=47155168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011101331686A Pending CN102789781A (en) | 2011-05-20 | 2011-05-20 | Mode supporting vocal print verification in Voice XML (Extensive Makeup Language) 2.0 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102789781A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113724711A (en) * | 2021-09-01 | 2021-11-30 | 云从科技集团股份有限公司 | Method, device, system, medium and equipment for realizing voice recognition service |
-
2011
- 2011-05-20 CN CN2011101331686A patent/CN102789781A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113724711A (en) * | 2021-09-01 | 2021-11-30 | 云从科技集团股份有限公司 | Method, device, system, medium and equipment for realizing voice recognition service |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE60125397D1 (en) | LANGUAGE-DEPENDENT VOTING BASED USER INTERFACE | |
CN103942137A (en) | Browser compatibility testing method and device | |
DE60334185D1 (en) | Import and export hierarchically structured data | |
WO2006017493A3 (en) | Approach for creating a tag or attribute in a markup language document | |
WO2007139624A3 (en) | Replacing text representing a concept with an alternate written form of the concept | |
ATE514162T1 (en) | DYNAMIC CONTEXT GENERATION FOR LANGUAGE RECOGNITION | |
DE60318021D1 (en) | VOICE-CONTROLLED DATA ENTRY | |
TW200739367A (en) | System and method for text legibility enhancement | |
Ginev et al. | The LATEXML daemon: Editable math on the collaborative web | |
WO2009158093A8 (en) | Extended user profile | |
DE602007012523D1 (en) | LANGUAGE RECOGNITION SCRIPT FOR HEADSET DEVICE AND CONFIGURATION | |
CN104679726A (en) | Type setting method and device of word files | |
CN103376990B (en) | The sound control method of a kind of web page operation and system | |
CN101727497B (en) | Method for generating interactive document structure from web page document | |
CN102789781A (en) | Mode supporting vocal print verification in Voice XML (Extensive Makeup Language) 2.0 | |
CN109343835A (en) | A kind of rapid build business scaffold code instrumentation based on template | |
Bradley | Sibilant voicing in highland Ecuadorian Spanish | |
CN104732976A (en) | Voice recognition method for converting mandarin into dialects | |
CN101419598A (en) | System for establishing digital signature in file template and method thereof | |
EP1374227A4 (en) | Method of performing speech recognition of dynamic utterances | |
ATE326754T1 (en) | HOMOPHONE CHOICE IN LANGUAGE RECOGNITION | |
Bianchi et al. | Complementizer deletion | |
CN102800313A (en) | Method for supporting multi-voice recognition engine in Voice extensible markup language (XML) 2.0 | |
CN107766302A (en) | A kind of document underscore dynamic adjusting method, device and terminal | |
CN102479178A (en) | Regional dialect translating method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20121121 |