In Various Implementations – Original Text

alternate routes google maps androidFurther, in various implementations, the input mechanism 105 can be coupled to other input modalities, in that various forms of input aside from voice can be processed and/oras well asand alsoandand alsoand alsoand alsoandandandas well asas well asandas well asand alsoas well asand alsoas well asand alsoand alsoas well asas well asandand alsoand alsoand alsoand alsoas well asand alsoand alsoand alsoandas well asas well asandas well asand alsoand alsoandandandand also correlated with one or more previous, current, or subsequent 'voice based' inputs.

The input mechanism 105 might be coupled to a touchscreen interface, a stylus/tablet interface, a keypad or keyboard, and akin devices or system interfaces, as might be apparent. Therefore a percentage of input information potentially available for system 100 to process voice might be maximized, as the user can clarify utterances or provide additional information about utterances using other input modalities. Actually, while also providing an utterance relating to the touched portion, as an example, the user could touch a stylus and akin pointing device to a portion of a map displayed on a 'touch screen' interface. In this example, system 100 may correlate the inputs to interpret around here as likely referring to the map touched portion, as distinct from the user's current location or another meaning.

Thus, for a given voice input, a decisional operation 420 may determine whether a nonvoice component accompanies an utterance in the voice input.

alternate routes google maps android In various implementations, the various input mechanisms associated with the voice user interface might be coupled to a Alternating Voice and Data system. Fact, input data may alternate between voice and data, or the input data might be multiplexed together in a single stream, let's say, to allocate processing resources where needed at a given moment. According to various invention aspects, the natural language voice user interface may dynamically generate and/orandandand alsoandandas well asas well asandand alsoand alsoandandas well asandas well asand alsoas well asand alsoand alsoas well asand alsoas well asandas well asas well asandas well asand alsoand alsoand alsoandand alsoas well asand alsoas well asandas well asand alsoas well asandandand alsoas well as load recognition grammars for interpreting what was said in an utterance. Information contained in the dynamic recognition grammars should be used by a navigation agent, a Automatic Speech Recognizer, a context stack, or various other components in the voice user interface that use grammar information. While processing bottlenecks can be avoided, conflicts can be reduced, and identical sides of interpreting an utterance using a recognition grammar can be optimized, By efficiently generating, updating, loading, extending, or otherwise building dynamic grammars on the basis of various factors. Actually a size of a generated grammar can be constrained by a quantity of resources available in a system. In another example, the dynamic size grammar can be reduced by eliminating redundant keywords, criteria, and similar information available in the context stack, the shared knowledge, and similar local sources. Thus, favorability of correct interpretations can be improved by reducing perplexity in the grammar.

I am sure that the topological domains can be subdivided into a plurality of tiles, may in turn be subdivided into a plurality of subtiles.

a civil organization topological domain may include a tile representing grammar information for a state, and the tile may include one or more subtiles for counties within the state. Further, the county subtiles may include subtiles for various cities, neighborhoods, and similar organizational boundaries within respective counties. Thus, the geographic proximities and topological domains used to build the dynamic grammar might be on the basis of a types of factors, and can be subdivided or weighed in various ways to determine what information to include in the grammar. Geographical chunks on the basis of physical, civil organization, temporal, directional, and akin proximities can be extended into various other domains in which a topological taxonomy can be placed. Nevertheless, the geographical chunking techniques may have particular relevance in navigation and similar 'locationdependent' voice recognition systems, yet the techniques can be suitably applied in various contexts or domains in which geography or location may have relevance.

While an available source of traffic data had been used to provide 'data driven' directions, in the aboveillustrated example, the response was personalized by framing directions regarding the the user's contacts.

In another example, data that may affect routing can be identified and used to recalculate a route or identify alternate routes. Data can be obtained dynamically to identify alternate routes, recalculate routes, or otherwise provide optimal routing service, as such. In various implementations, data source should be on the basis of persistent models, dynamically received data, and akin information. Routes might be recalculated automatically, or the user can request recalculation through additional utterances. This is where it starts getting very interesting. Further, possible answers or responses to a given utterance might be filtered as indicated by a current route. Usually, continuing the 'aboveprovided' example, the user may later return to a point of origin, and personalized responses may include return directions, like Go back the way you came on 14th Street. Thus, the personalized responses may also create a natural feel to the directions, and might be depending on context that builds over time.

Each aspect or implementation may not necessarily include the particular feature, structure, or characteristic, aspects and implementations might be described as including a particular feature. Or characteristic.

Whether explicitly described, when a particular feature. Or characteristic is described in connection with an aspect or implementation. Structure, or characteristic in connection with other aspects or implementations. Then, thus, various changes and modifications should be made to the provided description without departing from the scope or invention spirit. So specification and drawings going to be regarded as exemplary only, and the invention scope to be determined solely by the appended claims, as such.

As further described herein, accordingly the method illustrated in FIG.

For instance, in similar fashion as described in the above cab driver example, the voice user interface may have knowledge that certain routes can be preferable to reach a certain destination from a current point of presence. Further, as may be described in greater detail in FIG.

Information might be associated persistently, or might be built dynamically as a function of processing multimodal voice inputs.

An user may maintain an address book of contacts, email addresses, street addresses, telephone numbers, and similar information using a commercial service provider. Then the information should be pulled and shared with a device that may be used to resolve the request, when an user makes a request in which the service provider manages information needed to resolve the request.a mobile phone might be integrated with the navigation voice user interface, and the mobile phone may initially have no local contacts, addresses, telephone numbers, and akin information. Thus, an user utterance of I'm running late for dinner at Jane's house, call her to let her know I'm on the way may result in a query being formulated to the service provider with an eye to retrieve an address and telephone number associated with Jane's house for the mobile phone to process accordingly. Information relating to being late can be processed to generate a route that avoids traffic, uses highways, or otherwise reduces a quantity of travel time.

Providing a conversational feel to system generated responses. Which should be syntactically. Andconsequently contextually sensitive.

Accordingly the intelligent response may present results of a performed task or an executed query to the user, and the response can be provided across modalities, when available. Verbal and/orand alsoand alsoas well asandand alsoas well asand alsoand alsoandand alsoandas well asas well asas well asand alsoand alsoand alsoandas well asas well asandand alsoand alsoand alsoas well asand alsoas well asandandas well asandand alsoand alsoand alsoas well asandas well asandandandandand alsoand non verbal outputs 180 should be used separately or in concert. Creating verbal responses having natural variation and personality, Further, a verbalized component of the 'cross modal' output 180 should be adapted to the user's manner of speaking.

According to various invention aspects, the natural language voice user interface may track user interactions with delivered advertisements.

In this way, affinity based models might be generated, for the sake of example, to ensure that promotions or advertisements could be delivered to a likely market sector. Furthermore, thus, an event relating to a given advertisement should be generated and/oras well asandandandand alsoand alsoas well asas well asand alsoand alsoas well asand alsoand alsoand alsoas well asas well asand alsoand alsoas well asas well asand alsoandas well asas well asandand alsoandandas well asand alsoas well asand alsoandas well asas well asas well asand alsoand alsoas well asas well asand alsoand alsoand detected when shared knowledge about an user's behavior, preferences, and similar characteristics match one or more criteria associated with 'peertopeer' affinities associated with the advertisement. In other examples, an advertising model may include mobile pay per use systems, peer to peer local guides or recommendations, and akin forms of advertising. Additionally, various advertising aspects model, like the local guides and recommendations, can be generated conforming to a mapping applied to various topological domains. Certain types of advertisements types can be dependent on geographic or topological characteristics, and such advertisements should be associated with a topological taxonomy on the basis of geographical chunks. Then, various advertising events should be generated and/oras well asandandand alsoand alsoand alsoandand alsoas well asandandas well asand alsoand alsoandandand alsoas well asand alsoas well asandas well asand alsoandas well asand alsoandas well asand alsoas well asand alsoas well asandandas well asandandand alsoandand alsoas well asas well asas well as detected in consonance with physical proximities, temporal proximities, directional proximities, civil organization proximities, or various combinations thereof.

According to various invention aspects, the natural language voice user interface may include dynamic grammars formed from one or more topological domains, can be subdivided into a plurality of tiles, might be further subdivided into a plurality of subtiles.

Thus, information used to build the dynamic grammar can be subdivided or weighed in various ways to determine what information could be included in the grammar. Geographical chunks on the basis of physical, civil organization, temporal, directional, and similar proximities might be extended into other domains in which a topological taxonomy can be placed. In addition to having relevance in navigation and similar location dependent systems, the geographical chunking techniques can be applied in other contexts or domains in which geography or location might be relevant. Further, a server operably coupled to the voice user interface may analyze various forms of information to build or refine a source of grammar information. Ok, and now one of the most important parts. When various devices communicate with the server, information should be communicated to the server can be used to update proximities, topological domains, tiles, subtiles, 'peer to peer' affinities, and similar grammar information.

According to various invention aspects, the natural language voice user interface may utilize various cognitive models, contextual models, userspecific models, and similar models to identify queries, commands, and akin requests in a voice input.

a given input may include information relating to one or more contextual domains, one or more of which might be invoked to interpret and/orandas well asandandand alsoas well asas well asas well asas well asandandand alsoandand alsoand alsoas well asandand alsoas well asand alsoandandandand alsoas well asandand alsoandand alsoas well asandandas well asand alsoand alsoas well asandandand alsoandas well asand alsoand also infer keywords, concepts, and similar information contained in the input. Shortterm and long time shared knowledge about an user's behavior and preferences might be used in a hybrid recognition model that also considers semantic analysis and contextual inferences. On top of that, certain syllables, words, phrases, requests, queries, commands, and similar information might be more gonna occur in a given context. Thus, the hybrid recognition model may analyze semantic patterns to resolve what was said by an utterance, and may further rely on contextual history and akin information to resolve what was meant by the utterance. The hybrid recognition model can be used in conjunction with, or independently of, a peer to peer recognition model.

FIG. For sake of example, to preserve system resources, information available to extend, update, or otherwise update the grammar should be stored remotely, as various implementations generate the recognition grammars dynamically. On top of this, thus, various implementations may include a system having a network connection, a data service, or another communication mechanism for establishing a link to the remote source. Based on the proximities and/orand alsoas well asas well asas well asand alsoand alsoas well asas well asand alsoand alsoandas well asandandas well asas well asandandas well asandandas well asandand alsoas well asand alsoas well asandand alsoand alsoand alsoandas well asand alsoand alsoand alsoand alsoas well asandas well asand alsoandand also the topological domains identified for a given location, context, utterance, or otherwise, one or more grammar tiles and/orandand alsoas well asandandas well asas well asas well asandas well asand alsoand alsoas well asas well asas well asandandandas well asand alsoandandand alsoand alsoandandas well asas well asand alsoand alsoandandandas well asand alsoandand alsoas well asas well asas well asas well asandas well as subtiles should be downloaded from the remote source at an operation Further, the remote source should be adapted to store, analyze, or otherwise process certain information to refine the grammar information stored therein. When a given device communicates with the remote source at operation 350, the remote source may receive identifying information relating to a device user, requested information, and similar information. As a result, on the basis of the received information, the remote source may dynamically update various tiles and/orandas well asandandas well asandand alsoandandand alsoandand alsoand alsoandas well asas well asas well asand alsoas well asas well asandas well asas well asandas well asandas well asand alsoandandand alsoandas well asas well asand alsoand alsoand alsoand alsoand alsoand alsoand also subtiles, build affinities, or perform other actions to refine a process by which relevant information can be identified.

It should be apparent that voice inputs need not necessarily include nonvoice components. When the voice input includes only utterances, as such verbalizations, and similar spoken components, decisional operation 420 may advance method 400 directly to an operation For instance, as might be apparent from the further descriptions provided elsewhere in this specification, the natural language voice user interface may efficiently resolve many requests that include only voice. Now, a received voice input can include standalone utterances, such that a navigation device, vehicular system, mobile phone, and akin device can be controlled in one step using voice, as such. Oftentimes using existing navigation systems and similar navigation interfaces, an user must often take multiple steps to configure a displayed map, even for fairly simple tasks. Using the natural language voice user interface, the user can simplify controlling a device using onestep voice control, may substantially reduce a number of device interactions needed to control the device.

According to various invention aspects. Accordingly the voice user interface may calculate routes, provide dynamic datadriven directions to a destination, provide dynamic routing to a destination, perform 'post processing' of full or partial destination entries, or otherwise provide various voice navigation services, as previously described. Thus, as illustrated in FIG. Then again, though FIG. Successive refinement can be implemented in various domains that enable an user to drill down to a specific piece of information or data through specifying more and more specific criteria about the information sought.

Besides, the conversational language processor 120 may utilize various other forms of knowledge to inform the intelligent generation hypothesis.

Various agents 125 may adaptively include domain specific or contextspecific vocabularies, concepts, available tasks, and similar forms of information relevant to the respective domain or context. Basically, the various components associated with the conversational language processor 120 can invoke a voice search engine 135 to resolve information that may not be internally available. The advertising related events that can be generated and/orand alsoand alsoand alsoand alsoandas well asand alsoas well asas well asandandas well asas well asandandandandandand alsoas well asas well asas well asandandas well asand alsoand alsoas well asandandandand alsoand alsoas well asas well asas well asandas well asandand alsoand alsoas well asand also detected in operation 620, the natural language voice user interface may generate additional events through awareness of context, shared knowledge about an user, external systems and devices, and similar information. As discussed above in reference to FIG. It could be apparent that the inference engine might be arranged within the voice user interface in various other ways. Did you know that the voice user interface may include the inference engine within a conversational language processor, where in such implementations, the inference engine may generate, detect, and distribute events to various voice components user interface. Fact, in another example, a managing inference engine may coordinate event generation and/orand alsoas well asand alsoand alsoas well asas well asand alsoas well asas well asas well asas well asandandandand alsoandas well asandas well asas well asandand alsoand alsoandand alsoandas well asandand alsoas well asand alsoas well asandand alsoas well asand alsoandandand alsoandand alsoas well asand detection among the inference engines associated with the agents. Now pay attention please. It going to be apparent that the voice user interface may include various suitable arrangements of one or more inference engines, such that events and inferences can be detected, generated, and distributed to various system components as they may arise, as such.

According to various invention aspects, the natural language voice user interface may include a 'agentbased' architecture for providing voice navigation services.

And therefore the agentbased architecture may include one or more domain or 'context specific' agents, include at least a navigation agent. Anyway, the navigation agent may include, among other things, various navigation specific content packages, response lists, personality profiles, substitution lists, or various other forms of navigationspecific information. Further, the navigation agent can be associated with pointers to local or remote data sources, parameters and operating data provided associated with other services in the architecture, or various other forms of information. So, the data sources used by the navigation agent may include data relating to navigation, 'points of interest', traffic, events, parking, personal data, peer affinities, or various other sources of information. Further, the data sources should be populated, extended, pruned, or otherwise constructed through adaptation, analysis of various models, communication with a data service, or in other ways, as may be apparent.

According to various invention aspects, various problems associated with existing systems can be addressed by a conversational, natural language voice user interface that provides an integrated voice navigation services environment. According to various invention aspects, the natural language voice user interface may accept natural language 'voice based' inputs to control an electronic device that can provide navigational information, in addition to various other devices associated with an environment in which the voice user interface operates. Various functional voice aspects user interface may reside at a client device, at a server, or various combinations thereof.

According to various invention aspects, the natural language voice user interface may include one or more inference engines, can generate various inferences through awareness of previous context, shortterm or long time shared knowledge, command histories, states of vehicular systems, user interface states, and various other data sources. In various implementations, one or agents more should be associated with a respective inference engine that can generate inferences using domainspecific knowledge, rules, policies, and similar criteria. For instance, the inference engines may identify keywords or criteria missing in an utterance, infer intended meanings, autonomously suggest available tasks, or otherwise assist an associated agent in identifying queries, commands, and similar requests contained in an utterance. Also, when information cannot be suitably resolved using information sources associated with the navigation agent, or through generating inferences, the information might be requested from one or more other agents, other devices, network information sources, or in other ways, as might be apparent. Nonetheless, upon identifying the information through one or other more sources, the requesting agent might be adapted to make the information subsequently available. Thus, various devices, applications, systems, and similar components of an architecture may cooperatively share available information and services. Accordingly, the architecture may provide an integrated voice navigation services environment in which users can speak natural language requests relating to various available contexts, domains, applications, devices, information sources, or various combinations thereof.

The voice destination input can be parsed or otherwise analyzed using one or more dynamically adaptable recognition grammars, as an example, as described above in reference to FIG. Recognition grammars can be loaded, generated, extended, pruned, or otherwise adapted on the basis of various factors, including a proximity to an user's point of presence, a contextual history, and similar factors, as might be apparent. An operation 520 may include generating one or more voice interpretations destination input, should be analyzed using various data sources in case you are going to generate an N best list of possible destinations, as such.

System 100 may also enable the user and the system 100 to share assumptions and expectations relating to a given utterance, conversation, and similar interaction. I know that the conversational language processor 120 should be coupled to one or more data repositories 160 that store shortterm and 'longterm' shared knowledge that inform decision making in the conversational language processor The shortterm shared knowledge may accumulate information during a current conversation, thus dynamically establishing awareness of a 'crossmodal' voice state user interface. Certain data might be expired right after a psychologically appropriate time, short torage term knowledge might be modeled after human interaction, and information with 'longterm' significance can be added to longterm shared knowledge. Now look, the 'long term' shared knowledge may profile or otherwise model environmental, cognitive, historical, demographic, and akin facts of an user depending on information accumulated over time, as such.

Voice inputs should be used to perform compound requests, could otherwise be impossible to perform using a single manual input. By the way, a single voice based input may include a compound map control request, similar to Show me downtown Seattle. Operation 450 may perform tasks of retrieving a map of Seattle and automatically zooming in on a downtown Seattle area map, as such. While identifying possible points of interest to the user, or searching for traffic or event notifications, among other things, one or more responses and similar outputs should be generated, similar to suggesting a route to a frequent destination. Many other variations may be apparent, including received characteristics inputs, the requested queries or commands, the generated responses, and the performed tasks, among other things. Yes, that's right! It gonna be apparent that the method 400 illustrated herein may enable users to request many different navigation related tasks verbally, nonverbally, or various combinations thereof, such that the users can request various kinds of information or tasks available in the environment, as such. Thus, method 400 may operate in an environment in which the natural language voice user interface was associated with one or more devices that provide navigation services.

While parking, personal data, peer affinities, The data sources 260 used by the navigation agent 225 a may include, among other things, data relating to navigation, pointsofinterest, traffic.

The data sources 260 should be populated in various ways, like being depending on one or models, received via a data service, extended or refined through adaptation, or in other ways, as might be apparent. Known in line with various invention aspects, the natural language voice user interface may generate dynamic recognition grammars using techniques of geographical chunking. As a result, the topological domains may reflect physical proximities, civil organization proximities, temporal proximities, directional proximities, or various combinations thereof. By mapping the user's geographic proximities to one or more topological domains, dynamic grammars can be pruned, extended, swapped in or out of memory, or otherwise generated and/orand alsoandandas well asand alsoandandas well asand alsoas well asas well asand alsoandas well asas well asas well asandas well asas well asand alsoand alsoas well asas well asandas well asandandas well asandas well asand alsoand alsoas well asand alsoandand alsoas well asandandand alsoand alsoas well asas well as loaded to provide optimal recognition on the basis of location, time, travel, and similar factors.

According to various invention aspects, the natural language voice user interface may include one or more advertising models for generating and/orand alsoand alsoas well asas well asand alsoas well asand alsoas well asand alsoas well asas well asand alsoand alsoand alsoand alsoandand alsoandas well asand alsoand alsoandas well asandand alsoandand alsoandandand alsoand alsoand alsoand alsoas well asas well asand alsoandandand alsoas well asas well as detecting events relating to location dependent advertisements for navigation systems.

Navigation systems typically include various mechanisms for determining a current location. The location detection system may thus detect information associated with a radio frequency identifier over a data channel used by a marketer to provide advertisements. Essentially, the marketer may broadcast the advertisement via the data channel, such that the navigation system triggers an event when within a suitable RFIDs proximity. Thus, information associated with the event should be filtered in line with the current routing information and similar contextual parameters to determine what action might be taken in response thereto. In other instances, advertisements can be uploaded to a server by one or more advertising partners, wherein the uploaded advertisements can be associated with metadata and similar descriptive information that identifies a market, location dependent information, and similar criteria. You can find a lot more info about it on this site^^curely-bracket^^long time shared knowledge about the user, previous utterances in a current conversation, common requests in a given environment, and similar information. Consequently, thus, the hybrid recognition model for operation 440 may include various processes for analyzing semantic patterns to resolve what was said by an utterance, in addition to various processes for relying on contextual history to resolve what was meant by the utterance.

As illustrated in FIG. Actually a given approximation of a final destination should be associated with a finite number of possible destinations, and the system might be able to unambiguously identify the final destination from among the finite possible destinations by generating inferences, by relying on context, shared knowledge, and similar information, or by other ways, as may be apparent. In another example, successively refining the destination should be modeled after patterns of human interaction between passengers in a taxicab, and similar similar situations in which a route or a destination should be narrowed down or otherwise refined over a course of interaction. Passengers in taxicabs sometimes specify a general approximation of a destination, may result in a cab driver for a while a preferred route to the approximated destination. You see, the passenger and/oras well asand alsoas well asand alsoas well asandandand alsoand alsoandas well asas well asandand alsoandand alsoas well asas well asas well asand alsoand alsoand alsoand alsoas well asand alsoand alsoandas well asas well asand alsoas well asandand alsoas well asandas well asas well asandas well asandand alsoandand the driver may cooperate to refine the final destination through one or more subsequent interactions, while en route to the approximated destination.

According to various invention aspects, the natural language voice user interface may include an input mechanism that receives a 'voicebased' input, includes at least an utterance or verbalization spoken by an user. The input mechanism may include a suitable device or combination of devices that can receive voicebased inputs. Consequently, the input mechanism can be optimized to maximize gain in a direction of an user, cancel echoes, null point noise sources, perform variable rate sampling, filter out background conversations or environmental noise, or otherwise optimize fidelity of encoded speech. Also, the input mechanism may generate encoded speech generated in a manner that tolerates noise and akin factors that could otherwise interfere with interpreting speech, as such. Further, in various implementations, the input mechanism may include one or more other input modalities, can be processed and/oras well asandand alsoand alsoand alsoand alsoas well asas well asand alsoandas well asas well asand alsoas well asas well asand alsoandand alsoand alsoandas well asand alsoandandand alsoandandand alsoand alsoandand alsoand alsoandas well asas well asand alsoand alsoandandas well asas well asas well asas well as correlated with one or more previous, current, or subsequent utterances and akin voicebased inputs. So an user can provide other forms of input using a touch screen interface, a stylus/tablet interface, a keypad or keyboard, and similar input interfaces, as an example, to clarify utterances or provide additional information about the utterances using other input modalities, as such. While also providing an utterance relating to the touched portion, for example, the user could touch a stylus and akin pointing device to a portion of a map displayed on a touchscreen interface. Just think for a moment. In this example, the inputs can be correlated to interpret around here as likely referring to the map touched portion, as distinct from the user's current location or some other meaning.

Thus, the one or more inference engines may utilize awareness of context, shared knowledge about an user, dynamic data sources, data and services associated with external or devices, among other information to generate and/oras well asandand alsoand alsoas well asand alsoas well asandas well asandas well asand alsoand alsoas well asas well asandand alsoas well asandandand alsoandand alsoand alsoandand alsoandas well asas well asandas well asandas well asand alsoandandand alsoand alsoand alsoas well asand alsoas well asand detect the events and similar inferences identified in operation When the events and akin inferences occur when a current navigation route exists, the events and akin inferences can be filtered in operation 650 prior to being a response being generated and/orand alsoand alsoas well asas well asas well asas well asas well asandandas well asandas well asand alsoas well asandas well asas well asas well asas well asas well asand alsoas well asas well asandand alsoand alsoand alsoandandandas well asandandandas well asas well asandand alsoandas well asand alsoand alsoand also a task being performed in operation 660.

In yet another example, various types of external types system awareness may trigger events and resulting voice responses from the voice user interface. Whenever providing awareness over a state of such systems, the voice user interface should be coupled to various vehicular or telematics systems. Remember, whenever resulting in a voice response prompting an user to stop for gas, an event should be generated when the vehicular system indicates that the vehicle will soon run out of gas. That gas level won't be sufficient to get for ages the route. Wherein a calculation can be made indicating that a level of gas should be sufficient to get for a while the route. That's where it starts getting interestinginteresting, right, right? The routebased filtering operation 650 may result in a response being generated in operation 660 that provides a voice warning that the user must stop for gas at the next gas station.

According to various invention aspects, the natural language voice user interface may include a navigation agent, can be coupled with various sources of information, and may use context, communicating with various other adaptable agents and other system components to provide voice navigation services.

By the way, the navigation agent may use contextual information relating to a navigation domain, including tracked topics, user locations, routes traveled, previous requests, user interface states, user behaviors, preferences, demographics, and akin characteristics, or various other types of contextual types information. Actually, the navigation agent may have various sources of knowledge and resources available to resolve voice navigation requests. I'm sure you heard about this. I know that the navigation agent may generate inferences using the available knowledge and resources to apply various rules, policies, and similar inferencing techniques to generate interpretations of an utterance. Normally, the navigation agent can infer keywords or criteria not explicitly provided in the utterance, determine suitable responses to subjective or indeterminate utterances, generate events, identify peer affinities, or otherwise generate inferences for resolving navigation related requests, as such.

The present invention relates to a natural language voice user interface that facilitates cooperative, conversational interactions in an integrated voice navigation services environment, and particularly, to a natural language voice user interface in which users can request navigation services using conversational, natural language queries or commands. As described in greater detail herein, the calculated route should be dynamically adjusted or rerouted on the basis of subsequent inputs, generated inferences, dynamic data, or various other sources of information. Notice that thus. The voice user interface may use the method illustrated in FIG.

Returning to operation 630, 'user provided' voice inputs may also be processed in view of current routing information. Interpretations of what was said in a voice input should be depending on various phonetic models, dictionaries, context histories, dialogue histories, and similar information that can form a dynamic recognition grammar, as previously discussed. Usually, context, shared knowledge, and available data and services, among other information, can be used to interpret what meant by the voice input. That's right! Using the various techniques described herein and in the incorporated patent applications and issued patents, a query, command, and akin request contained in the utterance should be identified in an operation When a current route exists, a domain of possible tasks, commands, query answers, responses, and/orand alsoand alsoandas well asas well asand alsoas well asandandandand alsoas well asandas well asand alsoandas well asandandandand alsoand alsoand alsoas well asandas well asand alsoas well asandas well asas well asandas well asand alsoandas well asas well asas well asandas well asas well asandand also other system actions should be filtered in line with the current route. Of course a voice input of Where's the closest bathroom should be analyzed in current view route. Various proximities may then be utilized to determine what bathrooms can be appropriate in current view route. For the sake of example, when a route for awhile distance, a bathroom at a rest area twenty miles ahead should be favored over a bathroom at a restaurant ten miles off a highway.

N weighed list best destinations can be evaluated in an operation 540 to determine a suitably identifiable destination exists in the list. Now, a full or partial voice destination entry can be ambiguous, or certain criteria or keywords in a voice destination entry should be unrecognizable, such that a highest ranked destination in the weighted list does not exceed a minimal confidence level needed to identify a destination. Normally, an user located in Oklahoma may utter a partial destination, for the sake of example and the decisional operation 540 may return a negative indication when the voice user interface cannot disambiguate between Washington state, Washington, Washington University in Saint Louis, and a town of Washington located slightly south of Oklahoma City. In another example, an user originating in Saint Louis may provide a voice destination entry of Take me to Springfield, could result in an unidentifiable destination even when multiple destinations may satisfy the minimal confidence level. Now pay attention please. In this example, Springfield can be unidentifiable as a destination because Springfield. Springfield. Saint Louis, yet directions of travel to either destination should be entirely opposite. While processing may instead branch to an operation 550 to generate a prompt for resolving the destination, to avoid routing the user in a direction opposite from an intended destination.

It should be apparent that various available information sources can be utilized to generate and/orand alsoas well asas well asas well asandas well asand alsoandandand alsoandas well asand alsoandand alsoas well asas well asandandandas well asas well asas well asand alsoand alsoas well asand alsoandas well asand alsoand alsoand alsoandandas well asas well asand alsoas well asand alsoandand alsoas well asas well as detect events, although the 'aboveprovided' example illustrates an event generated using personal information.

Events might be depending on transient or dynamic data relating to communities, traffic, weather, and/orand alsoandandandand alsoas well asandand alsoandas well asandas well asand alsoas well asand alsoand alsoas well asandand alsoandas well asand alsoand alsoas well asand alsoandas well asand alsoandand alsoand alsoandand alsoand alsoand alsoand alsoandas well asand alsoas well asand alsoandand also many other sources of data. Therefore, system 100 may also include a Automatic Speech Recognizer 110 that receives the encoded voice input and generates one or more preliminary interpretations thereof. The Automatic Speech Recognizer 110 may recognize the voicebased input using phonetic dictation to recognize a stream of phonemes on the basis of a dynamically adaptable recognition grammar. By the way, the Automatic Speech Recognizer 110 may provide out of vocabulary capabilities, should be tolerant of an user misspeaking, portions of a speech signal being writeped, and akin factors that could interfere with interpreting an utterance. The dynamically adaptable recognition grammar might be on the basis of dictionaries or phrases from various input domains. Consequently, further, Automatic performance Speech Recognizer 110 can be improved, for instance, by pruning a search space associated with the recognition grammar. It is thus, using these and other techniques, Automatic Speech Recognizer 110 may analyze an incoming encoded utterance to represent utterance portions as a series of phonemes or syllables, can be further broken down into core components of an onset, a nucleus, and a coda, among other 'subcategories'. Phonemes series or syllables can then be analyzed to identify a plurality of preliminary interpretations or best guesses as to what was actually spoken by the user. It might be apparent, however, that the Automatic Speech Recognizer 110 may use various techniques to generate the encoded preliminary interpretations utterance, including those described, for instance, in patent application Ser. No. It is dynamic Speech Sharpening, issued as Pat. No. Dec.