| Dynamic grammar for voice-enabled applications -> Monitor Keywords |
|
Dynamic grammar for voice-enabled applicationsRelated Patent Categories: Data Processing: Speech Signal Processing, Linguistics, Language Translation, And Audio Compression/decompression, Linguistics, Natural LanguageDynamic grammar for voice-enabled applications description/claimsThe Patent Description & Claims data below is from USPTO Patent Application 20070179778, Dynamic grammar for voice-enabled applications. Brief Patent Description - Full Patent Description - Patent Application Claims CROSS-REFERENCE TO RELATED APPLICATIONS [0001] This application is a continuation of U.S. patent application Ser. No. 10/305,267, filed Nov. 27, 2002, which claims the benefit of U.S. Provisional Application No. 60/383,775, filed May 30, 2002, and titled DYNAMIC GRAMMAR WITH VISUAL CUES FOR VOICE-ENABLED MOBILE APPLICATIONS and from U.S. Provisional Application No. 60/354,324, filed Feb. 7, 2002, and titled MOBILE APPLICATION ARCHITECTURE, and is a Continuation-in-Part of U.S. application Ser. No. 10/131,216, filed Apr. 25, 2002, titled MULTI-MODAL SYNCHRONIZATION, U.S. application Ser. No. 10/157,030, filed May 30, 2002, titled USER INTERFACE FOR DATA ACCESS AND ENTRY, and U.S. application Ser. No. 10/184,069, filed Jun. 28, 2002, titled USER INTERFACE FOR DATA ACCESS AND ENTRY, all of which are hereby incorporated by reference in their entirety for all purposes. TECHNICAL FIELD [0002] Particular implementations relate generally to voice recognition techniques, and more particularly to using dynamic grammars with visual cues for voice-enabled mobile applications. BACKGROUND [0003] Conventional systems exist for the recognition of voice commands and other voice inputs. Such systems, however, may be relatively slow and/or inaccurate in inputting data, particularly when processing and/or memory limitations exist, as may be the case with mobile applications. In some data-input situations, voice commands can be avoided by using a physical input, such as a keyboard or stylus. However, in more text-intensive data entry, such physical inputs, particularly in the context of mobile applications, may be overly awkward or time-consuming. SUMMARY [0004] Implementations provide techniques for allowing fast, accurate inputting and recognition of voice data, even in mobile applications. Moreover, disclosed techniques allow a user to select between voice and physical inputs, as desired by the user. Implementations include a plurality of independent grammars, each associated with a category, such as a field within a form on a graphical user interface. The grammars may be dynamically activated or deactivated, depending upon which category or field is currently inputting data from the user. The currently active grammar may be indicated to the user by way of a visual cue associated with the, for example, field displayed on the graphical user interface. Thus, at a given point of time, only the selected field is active for data entry and subsequent display of the result of voice recognition, and a visual cue is used to indicate the active field. Also, a global grammar for inputting commands related to all of the categories, and/or to the device or application implementing the graphical user interface, may be kept active simultaneously with any one of the independent, category-associated grammars. [0005] According to one general aspect, an implementation may include a first grammar activated from among a plurality of independent grammars, the first grammar being identified with a first input category. At least a second grammar from among the plurality of independent grammars is deactivated, spoken data related to the first input category is input, and the spoken data is matched to stored data within the first grammar. [0006] Implementations may include one or more of the following features. For example, the plurality of independent grammars may define a first level of grammar, and, in activating the first grammar, a second level of grammar independent from the plurality of independent grammars may be activated. In this case, in deactivating the second grammar, all of the first-level grammars aside from the first grammar may be deactivated. [0007] A first-modality gateway and a second modality gateway may be synchronized, where both gateways may interface between a user and a server system. The synchronizing may allow either of the first-modality gateway or the second-modality gateway, at a given point in time, to interface with specific information in the server system. In this case, the specific information may be a field identification command for identifying a first field within a form on a graphical user interface, where the first field may be associated with the first input category. The specific information may be the stored data. [0008] Also, in synchronizing the first-modality gateway and the second-modality gateway, a browser and a voice gateway may also be synchronized, wherein the server system includes web pages. In this case, the first grammar may be activated in response to the first field being identified within the form. Each of the plurality of independent grammars may be stored separately. [0009] In activating the first grammar, it may be indicated to a user, perhaps aurally, that the first grammar has been activated. In this case, in indicating to the user that the first grammar has been activate, a visual cue identifying a first field within a graphical user interface, such as a web page, may be displayed, the first field being associated with the first input category. Also, the visual cue may be automatically advanced to a second field upon the matching of the spoken data to the stored data within the first grammar. Alternatively, the visual cue may be advanced to a second field, after the matching of the spoken data to the stored data within the first grammar, by inputting a field advancement voice command, wherein the field advancement voice command may be matched against a global grammar that is active at a same time as the first grammar. [0010] Additionally, the first grammar may be deactivated, and the second grammar may then be activated. The second grammar may be identified with a second input category. Secondary spoken data related to the second input category may be input, and the secondary spoken data may be matched to secondary stored data within the second grammar. [0011] Also, a global grammar may be activated such that the first grammar and the global grammar are both active for a period of time, global spoken data may be input that identifies a second input category from among a plurality of input categories, the global spoken data may be matched to a portion of the global grammar, and activating the second grammar in response to the matching of the global spoken data, where the second grammar may be identified with the second input category. [0012] According to another general aspect, an apparatus comprises a storage medium having instructions stored thereon, and the instructions include a first code segment for activating a first grammar associated with a first category, a second code segment for activating a first data entry mechanism associated with the first category, a third code segment for receiving first voice data, a fourth codes segment for selecting a portion of the first grammar corresponding to the first voice data for input into the first data entry mechanism, a fifth code segment for deactivating the first grammar, a sixth code segment for activating a second grammar associated with a second category, a seventh code segment for activating a second data entry mechanism associated with the second category, an eighth code segment for receiving second voice data, and a ninth code segment for selecting a portion of the second grammar corresponding to the second voice data for input into the second data entry mechanism. [0013] Implementations may include one or more of the following features. For example, the first data entry mechanism may be a field in a graphical user interface, such as a web page, in which case the second code segment may be additionally for visually indicating the field. The first data entry mechanism may be an audio recording. [0014] The sixth code segment may be additionally for automatically activating the second grammar in response to the deactivating of the first grammar. Alternatively, the sixth code segment may be additionally for inputting a second-grammar activation signal from a user. In this case, the second-grammar activation signal may activate the second data entry mechanism associated with the second category for data entry. [0015] The second-grammar activation signal may include third voice data, and a tenth code segment may be included for matching the third voice data against a portion of a third grammar, wherein the third grammar remains active regardless of whether the first grammar or the second grammar are activated. Alternatively, the second-grammar activation signal may include a physical input. [0016] According to another general aspect, a system may comprise a first storage area operable to store a first grammar, a second storage area operable to store a second grammar, the second grammar being independent from the first grammar, a grammar activation and deactivation system operable to activate the first grammar and ensure that the second grammar is simultaneously inactive, a voice-recognition system operable to input spoken data and match the spoken data against a corresponding portion of the first grammar, and an input indication system operable to indicate the corresponding portion of the first grammar to a user. [0017] Implementations may include one or more of the following features. For example, a third rage area operable to store a third grammar may be included, and the third grammar may be independent from the first grammar and the second grammar and operable to be activated by the activation and deactivation system so that the third grammar and the first grammar are both active for a period of time. [0018] The input indication system may include a field within a graphical user interface operable to display the corresponding portion of the first grammar. The grammar activation and deactivation system may be further operable to output a grammar identifier to the user that identifies which of the first grammar and second grammar is currently active. In this case, The grammar identifier may include a visual cue identifying a first field or a second field within a graphical user interface, the first field and the second field being associated with the first grammar and the second grammar, respectively. [0019] The details of one or more implementations are set forth in the accompanying drawings and the description below. Other features will be apparent from the description, drawings, and the claims. DESCRIPTION OF DRAWINGS Continue reading about Dynamic grammar for voice-enabled applications... Full patent description for Dynamic grammar for voice-enabled applications Brief Patent Description - Full Patent Description - Patent Application Claims Click on the above for other options relating to this Dynamic grammar for voice-enabled applications patent application. ### 1. Sign up (takes 30 seconds). 2. Fill in the keywords to be monitored. 3. Each week you receive an email with patent applications related to your keywords. Start now! - Receive info on patent apps like Dynamic grammar for voice-enabled applications or other areas of interest. ### Previous Patent Application: Automatic grammar generation using distributedly collected knowledge Next Patent Application: Linguistic user interface Industry Class: Data processing: speech signal processing, linguistics, language translation, and audio compression/decompression ### FreshPatents.com Support Thank you for viewing the Dynamic grammar for voice-enabled applications patent info. IP-related news and info Results in 0.12459 seconds Other interesting Feshpatents.com categories: Medical: Surgery , Surgery(2) , Surgery(3) , Drug , Drug(2) , Prosthesis , Dentistry 174 |
* Protect your Inventions * US Patent Office filing
PATENT INFO |
|