Abstract: One or more systems and/or techniques for determining advertisement viewability are described herein. In an example where a webpage comprises a managed container within which an advertisement is populated, view percentage functionality associated with the managed container may be invoked to obtain a stream of viewable percentages of the managed container to determine a viewable percentage of the advertisement. In an example where the webpage comprises an unmanaged container in which the advertisement is populated, a grid may be generated and evaluated to determine a viewable percentage of the advertisement. When the viewable percentage of the advertisement is above a percentage threshold for a duration threshold a viewable impression beacon is generated for the managed container based upon the viewable percentage. The viewable impression beacon may be indicative of viewability of the advertisement (e.g., an amount of the advertisement that may be visible to a user).

Abstract: The present invention provides a system, method and software application for associating one or more phone numbers with an action on a phone and performing an action on the phone in response to the user initiating a call to one of such phone numbers. Certain phone numbers are associated with an action. The user's phone, or a server with which the user's phone communicates, maintains a table of the phone numbers associated with an action, and each phone number in the table is related to an action. Software on the user's phone listens for call initiated by a user. When the user initiates a call, software on the phone “intercepts” the call, and the phone (or a server with which the phone communicates) determines whether the call is to a phone number that is in the table. If the phone number is in the table, then it is associated with an action, and the user's phone performs that action at a time specified by instructions for such action.

Abstract: The present invention provides a system, method and software application for associating one or more phone numbers with an action on a phone and performing an action on the phone in response to the user initiating a call to one of such phone numbers. Certain phone numbers are associated with an action. The user's phone, or a server with which the user's phone communicates, maintains a table of the phone numbers associated with an action, and each phone number in the table is related to an action. Software on the user's phone listens for call initiated by a user. When the user initiates a call, software on the phone “intercepts” the call, and the phone (or a server with which the phone communicates) determines whether the call is to a phone number that is in the table. If the phone number is in the table, then it is associated with an action, and the user's phone performs that action at a time specified by instructions for such action.

Abstract: A method and software application reduce the occurrence of misdirected calls to one or more select destinations The software application resides on a user's phone and “listens” to phone numbers dialed by a user to determine if the user has dialed a phone number for one of such select destinations. In response to the user dialing one of such phone numbers, the software application on the phone effectively “intercepts” the call and enables the phone to provide the user with a list of destination options prior to placing the call to the dialed phone number. In one embodiment, the list is provided in audio form by playing a voice prompt with the list, as well as in visual form by displaying the list in the user interface of the user's phone. The list helps disambiguate the intent of the user in dialing the phone number by asking the user to either (i) confirm he wants the destination associated with the phone number or (ii) select another option.

Abstract: The present invention provides a system, method and software application for associating one or more phone numbers with an action on a phone and performing an action on the phone in response to the user initiating a call to one of such phone numbers. Certain phone numbers are associated with an action. The user's phone, or a server with which the user's phone communicates, maintains a table of the phone numbers associated with an action, and each phone number in the table is related to an action. Software on the user's phone listens for call initiated by a user. When the user initiates a call, software on the phone “intercepts” the call, and the phone (or a server with which the phone communicates) determines whether the call is to a phone number that is in the table. If the phone number is in the table, then it is associated with an action, and the user's phone performs that action at a time specified by instructions for such action.

Abstract: A unified clustering tree (500) generates phoneme clusters based on an input sequence of phonemes. The number of possible clusters is significantly less than the number of possible combinations of input phonemes. Nodes (510, 511) in the unified clustering tree are arranged into levels such that the clustering tree generates clusters for multiple speech recognition models. Models that correspond to higher levels in the unified clustering tree are coarse models relative to more fine-grain models at lower levels of the clustering tree.

Abstract: A unified clustering tree (500) generates phoneme clusters based on an input sequence of phonemes. The number of possible clusters is significantly less than the number of possible combinations of input phonemes. Nodes (510, 511) in the unified clustering tree are arranged into levels such that the clustering tree generates clusters for multiple speech recognition models. Models that correspond to higher levels in the unified clustering tree are coarse models relative to more fine-grain models at lower levels of the clustering tree.

Abstract: A dictionary creation component [316] converts the normal orthographic written representation of a word into a sequence of symbols that relate to the pronunciation of the word. The symbols may be used to train conventional models for speech recognition. The symbols are not phonemes and do not need to be defined by a speech expert. The symbols are created automatically by the dictionary creation component based on the written representation of the word.